From 06657fd91e2aebe9e712ed2177375925fe2533ae Mon Sep 17 00:00:00 2001
From: Amit Sharma <amit_sharma@live.com>
Date: Wed, 19 Oct 2022 16:48:46 +0530
Subject: [PATCH] Version Bump [Update/v0.9] (#334)

* updated notebook to always use opposite as desired class

* updated version number and docs

* removed nbsphinx allow errors
---
 MANIFEST.in                                   |    1 +
 docs/_modules/dice_ml/constants.html          |    9 +-
 .../dice_ml/counterfactual_explanations.html  |   10 +-
 docs/_modules/dice_ml/data.html               |    6 +-
 .../private_data_interface.html               |  146 +-
 .../public_data_interface.html                |  149 +-
 docs/_modules/dice_ml/dice.html               |   88 +-
 .../dice_ml/diverse_counterfactuals.html      |   14 +-
 .../dice_ml/explainer_interfaces/dice_KD.html |   35 +-
 .../explainer_interfaces/dice_genetic.html    |   54 +-
 .../explainer_interfaces/dice_pytorch.html    |   89 +-
 .../explainer_interfaces/dice_random.html     |   25 +-
 .../dice_tensorflow1.html                     |   60 +-
 .../dice_tensorflow2.html                     |   58 +-
 .../explainer_interfaces/explainer_base.html  |   84 +-
 .../feasible_base_vae.html                    |    6 +-
 .../feasible_model_approx.html                |    6 +-
 docs/_modules/dice_ml/model.html              |    6 +-
 .../dice_ml/model_interfaces/base_model.html  |    6 +-
 .../keras_tensorflow_model.html               |   13 +-
 .../model_interfaces/pytorch_model.html       |   26 +-
 docs/_modules/dice_ml/utils/exception.html    |    6 +-
 docs/_modules/dice_ml/utils/helpers.html      |   53 +-
 .../utils/sample_architecture/vae_model.html  |    6 +-
 docs/_modules/dice_ml/utils/serialize.html    |    7 +-
 docs/_modules/index.html                      |    7 +-
 docs/_static/basic.css                        |   13 +-
 docs/_static/doctools.js                      |  382 +-
 docs/_static/documentation_options.js         |    6 +-
 docs/_static/jquery.js                        |    4 +-
 docs/_static/language_data.js                 |  100 +-
 docs/_static/pygments.css                     |   34 +-
 docs/_static/searchtools.js                   |  825 +++--
 docs/dice_ml.data_interfaces.html             |   84 +-
 docs/dice_ml.explainer_interfaces.html        |  125 +-
 docs/dice_ml.html                             |  451 ++-
 docs/dice_ml.model_interfaces.html            |   24 +-
 docs/dice_ml.schema.html                      |   10 +-
 docs/dice_ml.utils.html                       |   68 +-
 docs/dice_ml.utils.sample_architecture.html   |   55 +-
 docs/genindex.html                            |   73 +-
 docs/index.html                               |   40 +-
 docs/modules.html                             |  106 +-
 ...king_different_CF_explanation_methods.html |  425 +--
 docs/notebooks/DiCE_feature_importances.html  |  732 ++--
 docs/notebooks/DiCE_getting_started.html      |  838 ++++-
 .../DiCE_getting_started_feasible.html        |  700 ++--
 docs/notebooks/DiCE_model_agnostic_CFs.html   | 3229 ++---------------
 ...ticlass_classification_and_regression.html |  112 +-
 .../notebooks/DiCE_with_advanced_options.html |  777 +---
 docs/notebooks/DiCE_with_private_data.html    |  388 +-
 docs/notebooks/nb_index.html                  |   12 +-
 docs/objects.inv                              |  Bin 9593 -> 9847 bytes
 docs/py-modindex.html                         |   11 +-
 docs/readme.html                              |   32 +-
 docs/search.html                              |    6 +-
 docs/searchindex.js                           |    2 +-
 docs/source/conf.py                           |    3 +-
 docs/source/dice_ml.utils.rst                 |    8 +
 .../notebooks/DiCE_model_agnostic_CFs.ipynb   |   10 +-
 setup.py                                      |    2 +-
 61 files changed, 4292 insertions(+), 6365 deletions(-)

diff --git a/MANIFEST.in b/MANIFEST.in
index c4c5ed93..6b8d6fab 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -5,6 +5,7 @@ include requirements-linting.txt
 include environment.yml
 include environment-deeplearning.yml
 include LICENSE
+include CODEOWNERS
 recursive-include docs *
 recursive-include tests *.py
 include dice_ml/utils/sample_trained_models/*
diff --git a/docs/_modules/dice_ml/constants.html b/docs/_modules/dice_ml/constants.html
index ede7f876..2f5c5702 100644
--- a/docs/_modules/dice_ml/constants.html
+++ b/docs/_modules/dice_ml/constants.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.constants &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.constants &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -96,7 +98,8 @@ <h1>Source code for dice_ml.constants</h1><div class="highlight"><pre>
 <div class="viewcode-block" id="SamplingStrategy"><a class="viewcode-back" href="../../dice_ml.html#dice_ml.constants.SamplingStrategy">[docs]</a><span class="k">class</span> <span class="nc">SamplingStrategy</span><span class="p">:</span>
     <span class="n">Random</span> <span class="o">=</span> <span class="s1">&#39;random&#39;</span>
     <span class="n">Genetic</span> <span class="o">=</span> <span class="s1">&#39;genetic&#39;</span>
-    <span class="n">KdTree</span> <span class="o">=</span> <span class="s1">&#39;kdtree&#39;</span></div>
+    <span class="n">KdTree</span> <span class="o">=</span> <span class="s1">&#39;kdtree&#39;</span>
+    <span class="n">Gradient</span> <span class="o">=</span> <span class="s1">&#39;gradient&#39;</span></div>
 
 
 <div class="viewcode-block" id="ModelTypes"><a class="viewcode-back" href="../../dice_ml.html#dice_ml.constants.ModelTypes">[docs]</a><span class="k">class</span> <span class="nc">ModelTypes</span><span class="p">:</span>
diff --git a/docs/_modules/dice_ml/counterfactual_explanations.html b/docs/_modules/dice_ml/counterfactual_explanations.html
index 8b701503..542a3055 100644
--- a/docs/_modules/dice_ml/counterfactual_explanations.html
+++ b/docs/_modules/dice_ml/counterfactual_explanations.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.counterfactual_explanations &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.counterfactual_explanations &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -249,7 +251,7 @@ <h1>Source code for dice_ml.counterfactual_explanations</h1><div class="highligh
                 <span class="n">combined_test_instance_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">serialized_cf_examples</span><span class="p">[</span>
                     <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">TEST_INSTANCE_LIST</span><span class="p">])</span>
                 <span class="n">combined_final_cfs_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">serialized_cf_examples</span><span class="p">[</span>
-                    <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FIANL_CFS_LIST</span><span class="p">])</span>
+                    <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FINAL_CFS_LIST</span><span class="p">])</span>
                 <span class="n">data_interface</span> <span class="o">=</span> <span class="n">serialized_cf_examples</span><span class="p">[</span>
                     <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">DATA_INTERFACE</span><span class="p">]</span>
                 <span class="n">feature_names</span> <span class="o">=</span> <span class="n">serialized_cf_examples</span><span class="p">[</span>
@@ -335,7 +337,7 @@ <h1>Source code for dice_ml.counterfactual_explanations</h1><div class="highligh
                     <span class="c1"># counterfactual example.</span>
                     <span class="n">cf_examples_str</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span>
                         <span class="p">{</span>
-                            <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FIANL_CFS_LIST</span><span class="p">:</span> <span class="n">json_dict</span><span class="p">[</span>
+                            <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FINAL_CFS_LIST</span><span class="p">:</span> <span class="n">json_dict</span><span class="p">[</span>
                                 <span class="n">_CounterfactualExpV2SchemaConstants</span><span class="o">.</span><span class="n">CFS_LIST</span><span class="p">][</span><span class="n">index</span><span class="p">],</span>
                             <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">TEST_INSTANCE_LIST</span><span class="p">:</span> <span class="n">json_dict</span><span class="p">[</span>
                                 <span class="n">_CounterfactualExpV2SchemaConstants</span><span class="o">.</span><span class="n">TEST_DATA</span><span class="p">][</span><span class="n">index</span><span class="p">],</span>
diff --git a/docs/_modules/dice_ml/data.html b/docs/_modules/dice_ml/data.html
index ab560d6a..ef18d240 100644
--- a/docs/_modules/dice_ml/data.html
+++ b/docs/_modules/dice_ml/data.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.data &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.data &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/data_interfaces/private_data_interface.html b/docs/_modules/dice_ml/data_interfaces/private_data_interface.html
index 92704b2e..94e25a20 100644
--- a/docs/_modules/dice_ml/data_interfaces/private_data_interface.html
+++ b/docs/_modules/dice_ml/data_interfaces/private_data_interface.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.data_interfaces.private_data_interface &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.data_interfaces.private_data_interface &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -86,9 +88,11 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
 <span class="kn">import</span> <span class="nn">collections</span>
 <span class="kn">import</span> <span class="nn">logging</span>
 <span class="kn">import</span> <span class="nn">sys</span>
+<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">defaultdict</span>
 
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
+<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">LabelEncoder</span>
 
 <span class="kn">from</span> <span class="nn">dice_ml.data_interfaces.base_data_interface</span> <span class="kn">import</span> <span class="n">_BaseData</span>
 
@@ -115,9 +119,9 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
 <span class="sd">                               Default MAD value is 1 for all features.</span>
 <span class="sd">        :param data_name (optional): Dataset name</span>
 <span class="sd">        &quot;&quot;&quot;</span>
-        <span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span> <span class="o">&gt;</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">])</span> <span class="ow">in</span> <span class="p">[</span><span class="nb">dict</span><span class="p">,</span> <span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">]:</span>
+        <span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span> <span class="o">&gt;</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">],</span> <span class="p">(</span><span class="nb">dict</span><span class="p">,</span> <span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">)):</span>
             <span class="n">features_dict</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">]</span>
-        <span class="k">elif</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span> <span class="o">&lt;=</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">])</span> <span class="ow">is</span> <span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">:</span>
+        <span class="k">elif</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span> <span class="o">&lt;=</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">],</span> <span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">):</span>
             <span class="n">features_dict</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;features&#39;</span><span class="p">]</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
@@ -129,22 +133,20 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
         <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_type_and_precision</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span> <span class="o">=</span> <span class="p">[]</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span> <span class="o">=</span> <span class="p">{}</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span> <span class="o">=</span> <span class="p">[]</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">categorical_levels</span> <span class="o">=</span> <span class="p">{}</span>
 
         <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="n">features_dict</span><span class="p">:</span>
-            <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span> <span class="ow">is</span> <span class="nb">int</span><span class="p">:</span>  <span class="c1"># continuous feature</span>
+            <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span> <span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">)):</span>  <span class="c1"># continuous feature</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">feature</span><span class="p">)</span>
-                <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span>
             <span class="k">else</span><span class="p">:</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">feature</span><span class="p">)</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">categorical_levels</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_mad</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
-
-        <span class="c1"># self.continuous_feature_names + self.categorical_feature_names</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_permitted_range</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">,</span> <span class="n">features_dict</span><span class="o">=</span><span class="n">features_dict</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">features_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">number_of_features</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">)</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_indexes</span> <span class="o">=</span> <span class="p">[</span><span class="nb">list</span><span class="p">(</span><span class="n">features_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span><span class="o">.</span><span class="n">index</span><span class="p">(</span>
             <span class="n">name</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span> <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">features_dict</span><span class="p">]</span>
@@ -156,20 +158,6 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
             <span class="k">if</span> <span class="n">feature_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_and_precision</span><span class="p">:</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">type_and_precision</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;int&#39;</span>
 
-                <span class="c1"># # Initializing a label encoder to obtain label-encoded values for categorical variables</span>
-                <span class="c1"># self.labelencoder = {}</span>
-                <span class="c1">#</span>
-                <span class="c1"># self.label_encoded_data = {}</span>
-                <span class="c1">#</span>
-                <span class="c1"># for column in self.categorical_feature_names:</span>
-                <span class="c1">#     self.labelencoder[column] = LabelEncoder()</span>
-                <span class="c1">#     self.label_encoded_data[column] = \</span>
-                <span class="c1">#           self.labelencoder[column].fit_transform(self.categorical_levels[column])</span>
-
-                <span class="c1"># self.max_range = -np.inf</span>
-                <span class="c1"># for feature in self.continuous_feature_names:</span>
-                <span class="c1">#     self.max_range = max(self.max_range, self.permitted_range[feature][1])</span>
-
         <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_data_name</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
 
     <span class="k">def</span> <span class="nf">_validate_and_set_type_and_precision</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
@@ -190,20 +178,34 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
         <span class="sd">&quot;&quot;&quot;One-hot-encodes the data.&quot;&quot;&quot;</span>
         <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">drop_first</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">columns</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">)</span></div>
 
-<div class="viewcode-block" id="PrivateData.normalize_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data">[docs]</a>    <span class="k">def</span> <span class="nf">normalize_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;one-hot&#39;</span><span class="p">):</span>
+<div class="viewcode-block" id="PrivateData.normalize_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data">[docs]</a>    <span class="k">def</span> <span class="nf">normalize_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Normalizes continuous features to make them fall in the range [0,1].&quot;&quot;&quot;</span>
         <span class="n">result</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-        <span class="k">for</span> <span class="n">feature_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">:</span>
-            <span class="n">max_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
-            <span class="n">min_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
-            <span class="n">result</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="n">max_value</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span>
-
-        <span class="c1"># if encoding == &#39;label&#39;: # need not do this if not required</span>
-        <span class="c1">#     for ix in self.categorical_feature_indexes:</span>
-        <span class="c1">#         feature_name = self.feature_names[ix]</span>
-        <span class="c1">#         max_value = len(self.categorical_levels[feature_name])-1</span>
-        <span class="c1">#         min_value = 0</span>
-        <span class="c1">#         result[feature_name] = (df[feature_name] - min_value) / (max_value - min_value)</span>
+        <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
+            <span class="k">for</span> <span class="n">feature_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">:</span>
+                <span class="n">max_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
+                <span class="n">min_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
+                <span class="k">if</span> <span class="n">min_value</span> <span class="o">==</span> <span class="n">max_value</span><span class="p">:</span>
+                    <span class="n">result</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
+                <span class="k">else</span><span class="p">:</span>
+                    <span class="n">result</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="n">max_value</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span>
+        <span class="k">else</span><span class="p">:</span>
+            <span class="n">result</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s1">&#39;float&#39;</span><span class="p">)</span>
+            <span class="k">for</span> <span class="n">feature_index</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_indexes</span><span class="p">:</span>
+                <span class="n">feature_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">[</span><span class="n">feature_index</span><span class="p">]</span>
+                <span class="n">max_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
+                <span class="n">min_value</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
+                <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
+                    <span class="k">if</span> <span class="n">min_value</span> <span class="o">==</span> <span class="n">max_value</span><span class="p">:</span>
+                        <span class="n">value</span> <span class="o">=</span> <span class="mi">0</span>
+                    <span class="k">else</span><span class="p">:</span>
+                        <span class="n">value</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="n">feature_index</span><span class="p">]</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="n">max_value</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span>
+                    <span class="n">result</span><span class="p">[</span><span class="n">feature_index</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
+                <span class="k">else</span><span class="p">:</span>
+                    <span class="k">if</span> <span class="n">min_value</span> <span class="o">==</span> <span class="n">max_value</span><span class="p">:</span>
+                        <span class="n">result</span><span class="p">[:,</span> <span class="n">feature_index</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="p">[:,</span> <span class="n">feature_index</span><span class="p">]))</span>
+                    <span class="k">else</span><span class="p">:</span>
+                        <span class="n">result</span><span class="p">[:,</span> <span class="n">feature_index</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="p">[:,</span> <span class="n">feature_index</span><span class="p">]</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="n">max_value</span> <span class="o">-</span> <span class="n">min_value</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">result</span></div>
 
 <div class="viewcode-block" id="PrivateData.de_normalize_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.de_normalize_data">[docs]</a>    <span class="k">def</span> <span class="nf">de_normalize_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span>
@@ -259,7 +261,25 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
         <span class="k">if</span> <span class="n">return_mads</span><span class="p">:</span>
             <span class="k">return</span> <span class="n">mads</span></div>
 
-<div class="viewcode-block" id="PrivateData.create_ohe_params"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params">[docs]</a>    <span class="k">def</span> <span class="nf">create_ohe_params</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<div class="viewcode-block" id="PrivateData.get_features_range"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range">[docs]</a>    <span class="k">def</span> <span class="nf">get_features_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">permitted_range_input</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">features_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+        <span class="k">if</span> <span class="n">features_dict</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+            <span class="n">features_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span>
+
+        <span class="n">ranges</span> <span class="o">=</span> <span class="p">{}</span>
+        <span class="c1"># Getting default ranges based on the dataset</span>
+        <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="n">features_dict</span><span class="p">:</span>
+            <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span> <span class="ow">is</span> <span class="nb">int</span><span class="p">:</span>  <span class="c1"># continuous feature</span>
+                <span class="n">ranges</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span>
+            <span class="k">else</span><span class="p">:</span>
+                <span class="n">ranges</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">features_dict</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span>
+        <span class="n">feature_ranges_orig</span> <span class="o">=</span> <span class="n">ranges</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
+        <span class="c1"># Overwriting the ranges for a feature if input provided</span>
+        <span class="k">if</span> <span class="n">permitted_range_input</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+            <span class="k">for</span> <span class="n">feature_name</span><span class="p">,</span> <span class="n">feature_range</span> <span class="ow">in</span> <span class="n">permitted_range_input</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
+                <span class="n">ranges</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">feature_range</span>
+        <span class="k">return</span> <span class="n">ranges</span><span class="p">,</span> <span class="n">feature_ranges_orig</span></div>
+
+<div class="viewcode-block" id="PrivateData.create_ohe_params"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params">[docs]</a>    <span class="k">def</span> <span class="nf">create_ohe_params</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">one_hot_encoded_data</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
         <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
             <span class="c1"># simulating sklearn&#39;s one-hot-encoding</span>
             <span class="c1"># continuous features on the left</span>
@@ -325,6 +345,13 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
                     <span class="n">ixs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">colidx</span><span class="p">)</span>
             <span class="k">return</span> <span class="n">ixs</span></div>
 
+<div class="viewcode-block" id="PrivateData.fit_label_encoders"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders">[docs]</a>    <span class="k">def</span> <span class="nf">fit_label_encoders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="n">labelencoders</span> <span class="o">=</span> <span class="p">{}</span>
+        <span class="k">for</span> <span class="n">column</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
+            <span class="n">labelencoders</span><span class="p">[</span><span class="n">column</span><span class="p">]</span> <span class="o">=</span> <span class="n">LabelEncoder</span><span class="p">()</span>
+            <span class="n">labelencoders</span><span class="p">[</span><span class="n">column</span><span class="p">]</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">column</span><span class="p">])</span>
+        <span class="k">return</span> <span class="n">labelencoders</span></div>
+
 <div class="viewcode-block" id="PrivateData.from_label"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.from_label">[docs]</a>    <span class="k">def</span> <span class="nf">from_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Transforms label encoded data back to categorical values&quot;&quot;&quot;</span>
         <span class="n">out</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
@@ -348,16 +375,22 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
             <span class="n">out</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="n">cols</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">out</span></div>
 
-<div class="viewcode-block" id="PrivateData.get_decimal_precisions"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions">[docs]</a>    <span class="k">def</span> <span class="nf">get_decimal_precisions</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<div class="viewcode-block" id="PrivateData.get_decimal_precisions"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions">[docs]</a>    <span class="k">def</span> <span class="nf">get_decimal_precisions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">output_type</span><span class="o">=</span><span class="s2">&quot;list&quot;</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;&quot;Gets the precision of continuous features in the data.&quot;&quot;&quot;</span>
-        <span class="n">precisions</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">)</span>
+        <span class="n">precisions_dict</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
+        <span class="n">precisions</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">)</span>
         <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">feature_name</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">):</span>
             <span class="n">type_prec</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_and_precision</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span>
             <span class="k">if</span> <span class="n">type_prec</span> <span class="o">==</span> <span class="s1">&#39;int&#39;</span><span class="p">:</span>
-                <span class="n">precisions</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
+                <span class="n">prec</span> <span class="o">=</span> <span class="mi">0</span>
             <span class="k">else</span><span class="p">:</span>
-                <span class="n">precisions</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_and_precision</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
-        <span class="k">return</span> <span class="n">precisions</span></div>
+                <span class="n">prec</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_and_precision</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
+            <span class="n">precisions</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> <span class="o">=</span> <span class="n">prec</span>
+            <span class="n">precisions_dict</span><span class="p">[</span><span class="n">feature_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">prec</span>
+        <span class="k">if</span> <span class="n">output_type</span> <span class="o">==</span> <span class="s2">&quot;list&quot;</span><span class="p">:</span>
+            <span class="k">return</span> <span class="n">precisions</span>
+        <span class="k">elif</span> <span class="n">output_type</span> <span class="o">==</span> <span class="s2">&quot;dict&quot;</span><span class="p">:</span>
+            <span class="k">return</span> <span class="n">precisions_dict</span></div>
 
 <div class="viewcode-block" id="PrivateData.get_decoded_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decoded_data">[docs]</a>    <span class="k">def</span> <span class="nf">get_decoded_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;one-hot&#39;</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Gets the original data from encoded data.&quot;&quot;&quot;</span>
@@ -367,11 +400,11 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
         <span class="n">index</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">))]</span>
         <span class="k">if</span> <span class="n">encoding</span> <span class="o">==</span> <span class="s1">&#39;one-hot&#39;</span><span class="p">:</span>
             <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">):</span>
-                <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
+                <span class="k">return</span> <span class="n">data</span>
             <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span>
                 <span class="n">data</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">data</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="n">index</span><span class="p">,</span>
                                     <span class="n">columns</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">)</span>
-                <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
+                <span class="k">return</span> <span class="n">data</span>
             <span class="k">else</span><span class="p">:</span>
                 <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;data should be a pandas dataframe or a numpy array&quot;</span><span class="p">)</span>
 
@@ -430,23 +463,42 @@ <h1>Source code for dice_ml.data_interfaces.private_data_interface</h1><div clas
         <span class="sd">&quot;&quot;&quot;Transforms query_instance into one-hot-encoded and min-max normalized data. query_instance should be a dict,</span>
 <span class="sd">           a dataframe, a list, or a list of dicts&quot;&quot;&quot;</span>
         <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_query_instance</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
-        <span class="n">temp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ohe_base_df</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">sort</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
+        <span class="n">ohe_base_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_df_for_ohe_encoding</span><span class="p">()</span>
+        <span class="n">temp</span> <span class="o">=</span> <span class="n">ohe_base_df</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">sort</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
         <span class="n">temp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">one_hot_encode_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span>
         <span class="n">temp</span> <span class="o">=</span> <span class="n">temp</span><span class="o">.</span><span class="n">tail</span><span class="p">(</span><span class="n">query_instance</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
         <span class="c1"># returns a pandas dataframe</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">normalize_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span></div>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">normalize_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">to_numeric</span><span class="p">)</span></div>
 
 <div class="viewcode-block" id="PrivateData.get_inverse_ohe_min_max_normalized_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_inverse_ohe_min_max_normalized_data">[docs]</a>    <span class="k">def</span> <span class="nf">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transformed_data</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Transforms one-hot-encoded and min-max normalized data into raw user-fed data format. transformed_data</span>
 <span class="sd">           should be a dataframe or an array&quot;&quot;&quot;</span>
-        <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">transformed_data</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;one-hot&#39;</span><span class="p">)</span>
+        <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">transformed_data</span><span class="p">)</span>
         <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">de_normalize_data</span><span class="p">(</span><span class="n">raw_data</span><span class="p">)</span>
         <span class="n">precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_decimal_precisions</span><span class="p">()</span>
         <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">feature</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">):</span>
             <span class="n">raw_data</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">raw_data</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">float</span><span class="p">)</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">precisions</span><span class="p">[</span><span class="n">ix</span><span class="p">])</span>
         <span class="n">raw_data</span> <span class="o">=</span> <span class="n">raw_data</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">]</span>
         <span class="c1"># returns a pandas dataframe</span>
-        <span class="k">return</span> <span class="n">raw_data</span></div></div>
+        <span class="k">return</span> <span class="n">raw_data</span></div>
+
+<div class="viewcode-block" id="PrivateData.get_all_dummy_colnames"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames">[docs]</a>    <span class="k">def</span> <span class="nf">get_all_dummy_colnames</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="n">max_vals</span> <span class="o">=</span> <span class="nb">max</span><span class="p">([</span><span class="nb">len</span><span class="p">(</span><span class="n">val</span><span class="p">)</span> <span class="k">for</span> <span class="n">col</span><span class="p">,</span> <span class="n">val</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
+        <span class="n">sample_data_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">col</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="n">val</span><span class="p">,</span> <span class="n">max_vals</span><span class="p">)</span> <span class="k">for</span> <span class="n">col</span><span class="p">,</span> <span class="n">val</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
+        <span class="n">sample_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">sample_data_dict</span><span class="p">)</span>
+        <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">sample_df</span><span class="p">)</span><span class="o">.</span><span class="n">columns</span></div>
+
+<div class="viewcode-block" id="PrivateData.get_valid_feature_range"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range">[docs]</a>    <span class="k">def</span> <span class="nf">get_valid_feature_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">feature_range_input</span><span class="p">,</span> <span class="n">normalized</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+        <span class="sd">&quot;&quot;&quot;Gets the min/max value of features in normalized or de-normalized</span>
+<span class="sd">        form. Assumes that all features are already encoded to numerical form</span>
+<span class="sd">        such that the number of features remains the same.</span>
+
+<span class="sd">        # TODO needs work adhere to label encoded max and to support permitted_range for</span>
+<span class="sd">        both continuous and discrete when provided in _generate_counterfactuals.</span>
+<span class="sd">        &quot;&quot;&quot;</span>
+        <span class="k">if</span> <span class="n">normalized</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">&quot;Normalized feature range not supported for private data interface&quot;</span><span class="p">)</span>
+        <span class="k">return</span> <span class="n">feature_range_input</span></div></div>
 </pre></div>
 
            </div>
diff --git a/docs/_modules/dice_ml/data_interfaces/public_data_interface.html b/docs/_modules/dice_ml/data_interfaces/public_data_interface.html
index 233055f5..b2f040b5 100644
--- a/docs/_modules/dice_ml/data_interfaces/public_data_interface.html
+++ b/docs/_modules/dice_ml/data_interfaces/public_data_interface.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.data_interfaces.public_data_interface &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.data_interfaces.public_data_interface &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -89,6 +91,7 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
 
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
+<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">LabelEncoder</span>
 
 <span class="kn">from</span> <span class="nn">dice_ml.data_interfaces.base_data_interface</span> <span class="kn">import</span> <span class="n">_BaseData</span>
 <span class="kn">from</span> <span class="nn">dice_ml.utils.exception</span> <span class="kn">import</span> <span class="p">(</span><span class="n">SystemException</span><span class="p">,</span>
@@ -137,28 +140,7 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                 <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">,</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">)</span>
 
-        <span class="c1"># should move the below snippet to gradient based dice interfaces</span>
-        <span class="c1"># self.one_hot_encoded_data = self.one_hot_encode_data(self.data_df)</span>
-        <span class="c1"># self.ohe_encoded_feature_names = [x for x in self.one_hot_encoded_data.columns.tolist(</span>
-        <span class="c1">#     ) if x not in np.array([self.outcome_name])]</span>
-
-        <span class="c1"># should move the below snippet to model agnostic dice interfaces</span>
-        <span class="c1"># # Initializing a label encoder to obtain label-encoded values for categorical variables</span>
-        <span class="c1"># self.labelencoder = {}</span>
-        <span class="c1">#</span>
-        <span class="c1"># self.label_encoded_data = self.data_df.copy()</span>
-        <span class="c1">#</span>
-        <span class="c1"># for column in self.categorical_feature_names:</span>
-        <span class="c1">#     self.labelencoder[column] = LabelEncoder()</span>
-        <span class="c1">#     self.label_encoded_data[column] = self.labelencoder[column].fit_transform(self.data_df[column])</span>
-
         <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_permitted_range</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
-
-        <span class="c1"># should move the below snippet to model agnostic dice interfaces</span>
-        <span class="c1"># self.max_range = -np.inf</span>
-        <span class="c1"># for feature in self.continuous_feature_names:</span>
-        <span class="c1">#     self.max_range = max(self.max_range, self.permitted_range[feature][1])</span>
-
         <span class="bp">self</span><span class="o">.</span><span class="n">_validate_and_set_data_name</span><span class="p">(</span><span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
 
     <span class="k">def</span> <span class="nf">_validate_and_set_dataframe</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
@@ -183,7 +165,7 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
         <span class="k">if</span> <span class="s1">&#39;continuous_features&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">params</span><span class="p">:</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;continuous_features should be provided&#39;</span><span class="p">)</span>
 
-        <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;continuous_features&#39;</span><span class="p">])</span> <span class="ow">is</span> <span class="nb">list</span><span class="p">:</span>
+        <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;continuous_features&#39;</span><span class="p">],</span> <span class="nb">list</span><span class="p">):</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;continuous_features&#39;</span><span class="p">]</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
@@ -205,22 +187,6 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
         <span class="k">else</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">continuous_features_precision</span> <span class="o">=</span> <span class="kc">None</span>
 
-    <span class="k">def</span> <span class="nf">_validate_and_set_permitted_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
-        <span class="sd">&quot;&quot;&quot;Validate and set the dictionary of permitted ranges for continuous features.&quot;&quot;&quot;</span>
-        <span class="n">input_permitted_range</span> <span class="o">=</span> <span class="kc">None</span>
-        <span class="k">if</span> <span class="s1">&#39;permitted_range&#39;</span> <span class="ow">in</span> <span class="n">params</span><span class="p">:</span>
-            <span class="n">input_permitted_range</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;permitted_range&#39;</span><span class="p">]</span>
-
-            <span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">&#39;feature_names&#39;</span><span class="p">):</span>
-                <span class="k">raise</span> <span class="n">SystemException</span><span class="p">(</span><span class="s1">&#39;Feature names not correctly set in public data interface&#39;</span><span class="p">)</span>
-
-            <span class="k">for</span> <span class="n">input_permitted_range_feature_name</span> <span class="ow">in</span> <span class="n">input_permitted_range</span><span class="p">:</span>
-                <span class="k">if</span> <span class="n">input_permitted_range_feature_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">:</span>
-                    <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
-                        <span class="s2">&quot;permitted_range contains some feature names which are not part of columns in dataframe&quot;</span>
-                    <span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_features_range</span><span class="p">(</span><span class="n">input_permitted_range</span><span class="p">)</span>
-
     <span class="k">def</span> <span class="nf">_set_feature_dtypes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data_df</span><span class="p">,</span> <span class="n">categorical_feature_names</span><span class="p">,</span>
                             <span class="n">continuous_feature_names</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Set the correct type of each feature column.&quot;&quot;&quot;</span>
@@ -240,38 +206,7 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                         <span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">data_df</span>
 
-<div class="viewcode-block" id="PublicData.check_features_to_vary"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_features_to_vary">[docs]</a>    <span class="k">def</span> <span class="nf">check_features_to_vary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">):</span>
-        <span class="k">if</span> <span class="n">features_to_vary</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">features_to_vary</span> <span class="o">!=</span> <span class="s1">&#39;all&#39;</span><span class="p">:</span>
-            <span class="n">not_training_features</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">features_to_vary</span><span class="p">)</span> <span class="o">-</span> <span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">)</span>
-            <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">not_training_features</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
-                <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span><span class="s2">&quot;Got features </span><span class="si">{0}</span><span class="s2"> which are not present in training data&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
-                    <span class="n">not_training_features</span><span class="p">))</span></div>
-
-<div class="viewcode-block" id="PublicData.check_permitted_range"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_permitted_range">[docs]</a>    <span class="k">def</span> <span class="nf">check_permitted_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">permitted_range</span><span class="p">):</span>
-        <span class="k">if</span> <span class="n">permitted_range</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
-            <span class="n">permitted_range_features</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">permitted_range</span><span class="p">)</span>
-            <span class="n">not_training_features</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">permitted_range_features</span><span class="p">)</span> <span class="o">-</span> <span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">)</span>
-            <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">not_training_features</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
-                <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span><span class="s2">&quot;Got features </span><span class="si">{0}</span><span class="s2"> which are not present in training data&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
-                    <span class="n">not_training_features</span><span class="p">))</span>
-
-            <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="n">permitted_range_features</span><span class="p">:</span>
-                <span class="k">if</span> <span class="n">feature</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
-                    <span class="n">train_categories</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span>
-                    <span class="k">for</span> <span class="n">test_category</span> <span class="ow">in</span> <span class="n">permitted_range</span><span class="p">[</span><span class="n">feature</span><span class="p">]:</span>
-                        <span class="k">if</span> <span class="n">test_category</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">train_categories</span><span class="p">:</span>
-                            <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
-                                <span class="s1">&#39;The category </span><span class="si">{0}</span><span class="s1"> does not occur in the training data for feature </span><span class="si">{1}</span><span class="s1">.&#39;</span>
-                                <span class="s1">&#39; Allowed categories are </span><span class="si">{2}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">test_category</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="n">train_categories</span><span class="p">))</span></div>
-
-<div class="viewcode-block" id="PublicData.check_mad_validity"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_mad_validity">[docs]</a>    <span class="k">def</span> <span class="nf">check_mad_validity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">feature_weights</span><span class="p">):</span>
-        <span class="sd">&quot;&quot;&quot;checks feature MAD validity and throw warnings.</span>
-<span class="sd">           TODO: add comments as to where this is used if this function is necessary, else remove.</span>
-<span class="sd">        &quot;&quot;&quot;</span>
-        <span class="k">if</span> <span class="n">feature_weights</span> <span class="o">==</span> <span class="s2">&quot;inverse_mad&quot;</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">get_valid_mads</span><span class="p">(</span><span class="n">display_warnings</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">return_mads</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div>
-
-<div class="viewcode-block" id="PublicData.get_features_range"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range">[docs]</a>    <span class="k">def</span> <span class="nf">get_features_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">permitted_range_input</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+<div class="viewcode-block" id="PublicData.get_features_range"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range">[docs]</a>    <span class="k">def</span> <span class="nf">get_features_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">permitted_range_input</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">features_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
         <span class="n">ranges</span> <span class="o">=</span> <span class="p">{}</span>
         <span class="c1"># Getting default ranges based on the dataset</span>
         <span class="k">for</span> <span class="n">feature_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">:</span>
@@ -390,25 +325,6 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                 <span class="n">minx</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="n">idx</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
                 <span class="n">maxx</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="n">idx</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">permitted_range</span><span class="p">[</span><span class="n">feature_name</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span>
         <span class="k">return</span> <span class="n">minx</span><span class="p">,</span> <span class="n">maxx</span></div>
-        <span class="c1"># if encoding==&#39;one-hot&#39;:</span>
-        <span class="c1">#    minx = np.array([[0.0] * len(self.ohe_encoded_feature_names)])</span>
-        <span class="c1">#    maxx = np.array([[1.0] * len(self.ohe_encoded_feature_names)])</span>
-
-        <span class="c1">#    for idx, feature_name in enumerate(self.continuous_feature_names):</span>
-        <span class="c1">#        max_value = self.train_df[feature_name].max()</span>
-        <span class="c1">#        min_value = self.train_df[feature_name].min()</span>
-
-        <span class="c1">#        if normalized:</span>
-        <span class="c1">#            minx[0][idx] = (self.permitted_range[feature_name]</span>
-        <span class="c1">#                            [0] - min_value) / (max_value - min_value)</span>
-        <span class="c1">#            maxx[0][idx] = (self.permitted_range[feature_name]</span>
-        <span class="c1">#                            [1] - min_value) / (max_value - min_value)</span>
-        <span class="c1">#        else:</span>
-        <span class="c1">#            minx[0][idx] = self.permitted_range[feature_name][0]</span>
-        <span class="c1">#            maxx[0][idx] = self.permitted_range[feature_name][1]</span>
-        <span class="c1"># else:</span>
-        <span class="c1">#    minx = np.array([[0.0] * len(self.feature_names)])</span>
-        <span class="c1">#    maxx = np.array([[1.0] * len(self.feature_names)])</span>
 
 <div class="viewcode-block" id="PublicData.get_mads"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_mads">[docs]</a>    <span class="k">def</span> <span class="nf">get_mads</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">normalized</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Computes Median Absolute Deviation of features.&quot;&quot;&quot;</span>
@@ -453,24 +369,17 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                         <span class="nb">list</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">normalized_train_df</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">tolist</span><span class="p">())))),</span> <span class="n">quantile</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">quantiles</span></div>
 
-<div class="viewcode-block" id="PublicData.create_ohe_params"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params">[docs]</a>    <span class="k">def</span> <span class="nf">create_ohe_params</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<div class="viewcode-block" id="PublicData.create_ohe_params"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params">[docs]</a>    <span class="k">def</span> <span class="nf">create_ohe_params</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">one_hot_encoded_data</span><span class="p">):</span>
         <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
-            <span class="n">one_hot_encoded_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">one_hot_encode_data</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_df</span><span class="p">)</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">one_hot_encoded_data</span><span class="o">.</span><span class="n">columns</span><span class="o">.</span><span class="n">tolist</span><span class="p">(</span>
                 <span class="p">)</span> <span class="k">if</span> <span class="n">x</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">])]</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="c1"># one-hot-encoded data is same as original data if there is no categorical features.</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">feat</span> <span class="k">for</span> <span class="n">feat</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">]</span>
-
-        <span class="c1"># base dataframe for doing one-hot-encoding</span>
-        <span class="c1"># ohe_encoded_feature_names and ohe_base_df are created (and stored as data class&#39;s parameters)</span>
-        <span class="c1"># when get_data_params_for_gradient_dice() is called from gradient-based DiCE explainers</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">ohe_base_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_df_for_ohe_encoding</span><span class="p">()</span></div>
+            <span class="bp">self</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">feat</span> <span class="k">for</span> <span class="n">feat</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">]</span></div>
 
 <div class="viewcode-block" id="PublicData.get_data_params_for_gradient_dice"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_data_params_for_gradient_dice">[docs]</a>    <span class="k">def</span> <span class="nf">get_data_params_for_gradient_dice</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Gets all data related params for DiCE.&quot;&quot;&quot;</span>
 
-        <span class="bp">self</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">()</span>
         <span class="n">minx</span><span class="p">,</span> <span class="n">maxx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_minx_maxx</span><span class="p">(</span><span class="n">normalized</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 
         <span class="c1"># get the column indexes of categorical and continuous features after one-hot-encoding</span>
@@ -515,6 +424,13 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                     <span class="n">ixs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">colidx</span><span class="p">)</span>
             <span class="k">return</span> <span class="n">ixs</span></div>
 
+<div class="viewcode-block" id="PublicData.fit_label_encoders"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders">[docs]</a>    <span class="k">def</span> <span class="nf">fit_label_encoders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="n">labelencoders</span> <span class="o">=</span> <span class="p">{}</span>
+        <span class="k">for</span> <span class="n">column</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
+            <span class="n">labelencoders</span><span class="p">[</span><span class="n">column</span><span class="p">]</span> <span class="o">=</span> <span class="n">LabelEncoder</span><span class="p">()</span>
+            <span class="n">labelencoders</span><span class="p">[</span><span class="n">column</span><span class="p">]</span> <span class="o">=</span> <span class="n">labelencoders</span><span class="p">[</span><span class="n">column</span><span class="p">]</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="n">column</span><span class="p">])</span>
+        <span class="k">return</span> <span class="n">labelencoders</span></div>
+
 <div class="viewcode-block" id="PublicData.from_label"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.from_label">[docs]</a>    <span class="k">def</span> <span class="nf">from_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Transforms label encoded data back to categorical values&quot;&quot;&quot;</span>
         <span class="n">out</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
@@ -580,11 +496,11 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
         <span class="n">index</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">))]</span>
         <span class="k">if</span> <span class="n">encoding</span> <span class="o">==</span> <span class="s1">&#39;one-hot&#39;</span><span class="p">:</span>
             <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">):</span>
-                <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
+                <span class="k">return</span> <span class="n">data</span>
             <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span>
                 <span class="n">data</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">data</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="n">index</span><span class="p">,</span>
                                     <span class="n">columns</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">)</span>
-                <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
+                <span class="k">return</span> <span class="n">data</span>
             <span class="k">else</span><span class="p">:</span>
                 <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;data should be a pandas dataframe or a numpy array&quot;</span><span class="p">)</span>
 
@@ -643,42 +559,31 @@ <h1>Source code for dice_ml.data_interfaces.public_data_interface</h1><div class
                                         <span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">)</span>
         <span class="k">return</span> <span class="n">test</span></div>
 
-        <span class="c1"># TODO: create a new method, get_LE_min_max_normalized_data() to get label-encoded and normalized data. Keep this</span>
-        <span class="c1">#       method only for converting query_instance to pd.DataFrame</span>
-        <span class="c1"># if encoding == &#39;label&#39;:</span>
-        <span class="c1">#     for column in self.categorical_feature_names:</span>
-        <span class="c1">#         test[column] = self.labelencoder[column].transform(test[column])</span>
-        <span class="c1">#     return self.normalize_data(test, encoding)</span>
-        <span class="c1">#</span>
-        <span class="c1"># elif encoding == &#39;one-hot&#39;:</span>
-        <span class="c1">#     temp = self.prepare_df_for_encoding()</span>
-        <span class="c1">#     temp = temp.append(test, ignore_index=True, sort=False)</span>
-        <span class="c1">#     temp = self.one_hot_encode_data(temp)</span>
-        <span class="c1">#     temp = self.normalize_data(temp)</span>
-        <span class="c1">#</span>
-        <span class="c1">#     return temp.tail(test.shape[0]).reset_index(drop=True)</span>
-
 <div class="viewcode-block" id="PublicData.get_ohe_min_max_normalized_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_ohe_min_max_normalized_data">[docs]</a>    <span class="k">def</span> <span class="nf">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Transforms query_instance into one-hot-encoded and min-max normalized data. query_instance should be a dict,</span>
 <span class="sd">           a dataframe, a list, or a list of dicts&quot;&quot;&quot;</span>
         <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_query_instance</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
-        <span class="n">temp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ohe_base_df</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">sort</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
+        <span class="n">ohe_base_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_df_for_ohe_encoding</span><span class="p">()</span>
+        <span class="n">temp</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">([</span><span class="n">ohe_base_df</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">],</span> <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">sort</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
         <span class="n">temp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">one_hot_encode_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span>
         <span class="n">temp</span> <span class="o">=</span> <span class="n">temp</span><span class="o">.</span><span class="n">tail</span><span class="p">(</span><span class="n">query_instance</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span><span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">drop</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-        <span class="c1"># returns a pandas dataframe</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">normalize_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span></div>
+        <span class="c1"># returns a pandas dataframe with all numeric values</span>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">normalize_data</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">to_numeric</span><span class="p">)</span></div>
 
 <div class="viewcode-block" id="PublicData.get_inverse_ohe_min_max_normalized_data"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_inverse_ohe_min_max_normalized_data">[docs]</a>    <span class="k">def</span> <span class="nf">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transformed_data</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Transforms one-hot-encoded and min-max normalized data into raw user-fed data format. transformed_data</span>
 <span class="sd">           should be a dataframe or an array&quot;&quot;&quot;</span>
-        <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">transformed_data</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;one-hot&#39;</span><span class="p">)</span>
+        <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">from_dummies</span><span class="p">(</span><span class="n">transformed_data</span><span class="p">)</span>
         <span class="n">raw_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">de_normalize_data</span><span class="p">(</span><span class="n">raw_data</span><span class="p">)</span>
         <span class="n">precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_decimal_precisions</span><span class="p">()</span>
         <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">feature</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">continuous_feature_names</span><span class="p">):</span>
             <span class="n">raw_data</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="n">raw_data</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">float</span><span class="p">)</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">precisions</span><span class="p">[</span><span class="n">ix</span><span class="p">])</span>
         <span class="n">raw_data</span> <span class="o">=</span> <span class="n">raw_data</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">]</span>
         <span class="c1"># returns a pandas dataframe</span>
-        <span class="k">return</span> <span class="n">raw_data</span></div></div>
+        <span class="k">return</span> <span class="n">raw_data</span></div>
+
+<div class="viewcode-block" id="PublicData.get_all_dummy_colnames"><a class="viewcode-back" href="../../../dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames">[docs]</a>    <span class="k">def</span> <span class="nf">get_all_dummy_colnames</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+        <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span><span class="o">.</span><span class="n">columns</span></div></div>
 </pre></div>
 
            </div>
diff --git a/docs/_modules/dice_ml/dice.html b/docs/_modules/dice_ml/dice.html
index 2bc5bb81..fd3026d8 100644
--- a/docs/_modules/dice_ml/dice.html
+++ b/docs/_modules/dice_ml/dice.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.dice &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.dice &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -108,7 +110,7 @@ <h1>Source code for dice_ml.dice</h1><div class="highlight"><pre>
         <span class="k">if</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Sklearn</span><span class="p">:</span>
             <span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data_interface</span><span class="p">,</span> <span class="n">PrivateData</span><span class="p">):</span>
                 <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
-                    <span class="s1">&#39;Private data interface is not supported with sklearn kdtree explainer&#39;</span>
+                    <span class="s1">&#39;Private data interface is not supported with kdtree explainer&#39;</span>
                     <span class="s1">&#39; since kdtree explainer needs access to entire training data&#39;</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span> <span class="o">=</span> <span class="n">decide</span><span class="p">(</span><span class="n">model_interface</span><span class="p">,</span> <span class="n">method</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">,</span> <span class="n">model_interface</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
@@ -129,48 +131,54 @@ <h1>Source code for dice_ml.dice</h1><div class="highlight"><pre>
 <span class="sd">    subpackage and import-and-return the class in an elif loop as shown in</span>
 <span class="sd">    the below method.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
-    <span class="k">if</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Sklearn</span><span class="p">:</span>
-        <span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Random</span><span class="p">:</span>
-            <span class="c1"># random sampling of CFs</span>
-            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_random</span> <span class="kn">import</span> <span class="n">DiceRandom</span>
-            <span class="k">return</span> <span class="n">DiceRandom</span>
-        <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Genetic</span><span class="p">:</span>
-            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_genetic</span> <span class="kn">import</span> <span class="n">DiceGenetic</span>
-            <span class="k">return</span> <span class="n">DiceGenetic</span>
-        <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span><span class="p">:</span>
-            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_KD</span> <span class="kn">import</span> <span class="n">DiceKD</span>
-            <span class="k">return</span> <span class="n">DiceKD</span>
+    <span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Random</span><span class="p">:</span>
+        <span class="c1"># random sampling of CFs</span>
+        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_random</span> <span class="kn">import</span> <span class="n">DiceRandom</span>
+        <span class="k">return</span> <span class="n">DiceRandom</span>
+    <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Genetic</span><span class="p">:</span>
+        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_genetic</span> <span class="kn">import</span> <span class="n">DiceGenetic</span>
+        <span class="k">return</span> <span class="n">DiceGenetic</span>
+    <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span><span class="p">:</span>
+        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_KD</span> <span class="kn">import</span> <span class="n">DiceKD</span>
+        <span class="k">return</span> <span class="n">DiceKD</span>
+    <span class="k">elif</span> <span class="n">method</span> <span class="o">==</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Gradient</span><span class="p">:</span>
+        <span class="k">if</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Tensorflow1</span><span class="p">:</span>
+            <span class="c1"># pretrained Keras Sequential model with Tensorflow 1.x backend</span>
+            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_tensorflow1</span> <span class="kn">import</span> \
+                <span class="n">DiceTensorFlow1</span>
+            <span class="k">return</span> <span class="n">DiceTensorFlow1</span>
+
+        <span class="k">elif</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Tensorflow2</span><span class="p">:</span>
+            <span class="c1"># pretrained Keras Sequential model with Tensorflow 2.x backend</span>
+            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_tensorflow2</span> <span class="kn">import</span> \
+                <span class="n">DiceTensorFlow2</span>
+            <span class="k">return</span> <span class="n">DiceTensorFlow2</span>
+
+        <span class="k">elif</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Pytorch</span><span class="p">:</span>
+            <span class="c1"># PyTorch backend</span>
+            <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_pytorch</span> <span class="kn">import</span> <span class="n">DicePyTorch</span>
+            <span class="k">return</span> <span class="n">DicePyTorch</span>
         <span class="k">else</span><span class="p">:</span>
-            <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span><span class="s2">&quot;Unsupported sample strategy </span><span class="si">{0}</span><span class="s2"> provided. &quot;</span>
-                                                <span class="s2">&quot;Please choose one of </span><span class="si">{1}</span><span class="s2">, </span><span class="si">{2}</span><span class="s2"> or </span><span class="si">{3}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
-                                                    <span class="n">method</span><span class="p">,</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Random</span><span class="p">,</span>
-                                                    <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Genetic</span><span class="p">,</span>
-                                                    <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span>
-                                                <span class="p">))</span>
-
-    <span class="k">elif</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Tensorflow1</span><span class="p">:</span>
-        <span class="c1"># pretrained Keras Sequential model with Tensorflow 1.x backend</span>
-        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_tensorflow1</span> <span class="kn">import</span> \
-            <span class="n">DiceTensorFlow1</span>
-        <span class="k">return</span> <span class="n">DiceTensorFlow1</span>
-
-    <span class="k">elif</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Tensorflow2</span><span class="p">:</span>
-        <span class="c1"># pretrained Keras Sequential model with Tensorflow 2.x backend</span>
-        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_tensorflow2</span> <span class="kn">import</span> \
-            <span class="n">DiceTensorFlow2</span>
-        <span class="k">return</span> <span class="n">DiceTensorFlow2</span>
-
-    <span class="k">elif</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="n">BackEndTypes</span><span class="o">.</span><span class="n">Pytorch</span><span class="p">:</span>
-        <span class="c1"># PyTorch backend</span>
-        <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.dice_pytorch</span> <span class="kn">import</span> <span class="n">DicePyTorch</span>
-        <span class="k">return</span> <span class="n">DicePyTorch</span>
-
-    <span class="k">else</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
+                    <span class="s2">&quot;</span><span class="si">{0}</span><span class="s2"> is only supported for differentiable neural network models. &quot;</span>
+                    <span class="s2">&quot;Please choose one of </span><span class="si">{1}</span><span class="s2">, </span><span class="si">{2}</span><span class="s2"> or </span><span class="si">{3}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+                        <span class="n">method</span><span class="p">,</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Random</span><span class="p">,</span>
+                        <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Genetic</span><span class="p">,</span>
+                        <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span>
+                    <span class="p">))</span>
+    <span class="k">elif</span> <span class="n">method</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
         <span class="c1"># all other backends</span>
         <span class="n">backend_dice</span> <span class="o">=</span> <span class="n">model_interface</span><span class="o">.</span><span class="n">backend</span><span class="p">[</span><span class="s1">&#39;explainer&#39;</span><span class="p">]</span>
         <span class="n">module_name</span><span class="p">,</span> <span class="n">class_name</span> <span class="o">=</span> <span class="n">backend_dice</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">)</span>
         <span class="n">module</span> <span class="o">=</span> <span class="nb">__import__</span><span class="p">(</span><span class="s2">&quot;dice_ml.explainer_interfaces.&quot;</span> <span class="o">+</span> <span class="n">module_name</span><span class="p">,</span> <span class="n">fromlist</span><span class="o">=</span><span class="p">[</span><span class="n">class_name</span><span class="p">])</span>
-        <span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">module</span><span class="p">,</span> <span class="n">class_name</span><span class="p">)</span></div>
+        <span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">module</span><span class="p">,</span> <span class="n">class_name</span><span class="p">)</span>
+    <span class="k">else</span><span class="p">:</span>
+        <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span><span class="s2">&quot;Unsupported sample strategy </span><span class="si">{0}</span><span class="s2"> provided. &quot;</span>
+                                            <span class="s2">&quot;Please choose one of </span><span class="si">{1}</span><span class="s2">, </span><span class="si">{2}</span><span class="s2"> or </span><span class="si">{3}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+                                                <span class="n">method</span><span class="p">,</span> <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Random</span><span class="p">,</span>
+                                                <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">Genetic</span><span class="p">,</span>
+                                                <span class="n">SamplingStrategy</span><span class="o">.</span><span class="n">KdTree</span>
+                                            <span class="p">))</span></div>
 </pre></div>
 
            </div>
diff --git a/docs/_modules/dice_ml/diverse_counterfactuals.html b/docs/_modules/dice_ml/diverse_counterfactuals.html
index 5084ce2c..0ba3c7fb 100644
--- a/docs/_modules/dice_ml/diverse_counterfactuals.html
+++ b/docs/_modules/dice_ml/diverse_counterfactuals.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.diverse_counterfactuals &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.diverse_counterfactuals &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -107,7 +109,7 @@ <h1>Source code for dice_ml.diverse_counterfactuals</h1><div class="highlight"><
     <span class="n">FEATURE_NAMES_INCLUDING_TARGET</span> <span class="o">=</span> <span class="s1">&#39;feature_names_including_target&#39;</span>
     <span class="n">FEATURE_NAMES</span> <span class="o">=</span> <span class="s1">&#39;feature_names&#39;</span>
     <span class="n">TEST_INSTANCE_LIST</span> <span class="o">=</span> <span class="s1">&#39;test_instance_list&#39;</span>
-    <span class="n">FIANL_CFS_LIST</span> <span class="o">=</span> <span class="s1">&#39;final_cfs_list&#39;</span>
+    <span class="n">FINAL_CFS_LIST</span> <span class="o">=</span> <span class="s1">&#39;final_cfs_list&#39;</span>
 
 
 <div class="viewcode-block" id="json_converter"><a class="viewcode-back" href="../../dice_ml.html#dice_ml.diverse_counterfactuals.json_converter">[docs]</a><span class="k">def</span> <span class="nf">json_converter</span><span class="p">(</span><span class="n">obj</span><span class="p">):</span>
@@ -187,7 +189,7 @@ <h1>Source code for dice_ml.diverse_counterfactuals</h1><div class="highlight"><
                                   <span class="n">is_notebook_console</span><span class="o">=</span><span class="n">is_notebook_console</span><span class="p">)</span>
             <span class="k">elif</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span> <span class="s1">&#39;data_df&#39;</span><span class="p">):</span>  <span class="c1"># for private data</span>
                 <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\n</span><span class="s1">Diverse Counterfactual set without sparsity correction since only metadata about each&#39;</span><span class="p">,</span>
-                      <span class="s1">&#39; feature is available (new outcome: &#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">new_outcome</span><span class="p">)</span>
+                      <span class="s1">&#39; feature is available (new outcome: </span><span class="si">%i</span><span class="s1">)&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">new_outcome</span><span class="p">))</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">_dump_output</span><span class="p">(</span><span class="n">content</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs_df</span><span class="p">,</span> <span class="n">show_only_changes</span><span class="o">=</span><span class="n">show_only_changes</span><span class="p">,</span>
                                   <span class="n">is_notebook_console</span><span class="o">=</span><span class="n">is_notebook_console</span><span class="p">)</span>
             <span class="k">else</span><span class="p">:</span>
@@ -282,7 +284,7 @@ <h1>Source code for dice_ml.diverse_counterfactuals</h1><div class="highlight"><
 
             <span class="n">alternate_obj</span> <span class="o">=</span> <span class="p">{</span>
                 <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">TEST_INSTANCE_LIST</span><span class="p">:</span> <span class="n">test_instance_df_as_list</span><span class="p">,</span>
-                <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FIANL_CFS_LIST</span><span class="p">:</span> <span class="n">final_cfs_df_as_as_list</span><span class="p">,</span>
+                <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FINAL_CFS_LIST</span><span class="p">:</span> <span class="n">final_cfs_df_as_as_list</span><span class="p">,</span>
                 <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">DATA_INTERFACE</span><span class="p">:</span> <span class="n">dummy_data_interface_dict</span><span class="p">,</span>
                 <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FEATURE_NAMES</span><span class="p">:</span> <span class="n">feature_names</span><span class="p">,</span>
                 <span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FEATURE_NAMES_INCLUDING_TARGET</span><span class="p">:</span> <span class="n">feature_names_including_target</span><span class="p">,</span>
@@ -314,7 +316,7 @@ <h1>Source code for dice_ml.diverse_counterfactuals</h1><div class="highlight"><
                                           <span class="n">desired_range</span><span class="o">=</span><span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV1SchemaConstants</span><span class="o">.</span><span class="n">DESIRED_RANGE</span><span class="p">],</span>
                                           <span class="n">model_type</span><span class="o">=</span><span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV1SchemaConstants</span><span class="o">.</span><span class="n">MODEL_TYPE</span><span class="p">])</span>
         <span class="k">else</span><span class="p">:</span>
-            <span class="n">final_cfs_list</span> <span class="o">=</span> <span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FIANL_CFS_LIST</span><span class="p">]</span>
+            <span class="n">final_cfs_list</span> <span class="o">=</span> <span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FINAL_CFS_LIST</span><span class="p">]</span>
             <span class="n">test_instance_list</span> <span class="o">=</span> <span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">TEST_INSTANCE_LIST</span><span class="p">]</span>
             <span class="n">feature_names_including_target</span> <span class="o">=</span> <span class="n">cf_example_dict</span><span class="p">[</span><span class="n">_DiverseCFV2SchemaConstants</span><span class="o">.</span><span class="n">FEATURE_NAMES_INCLUDING_TARGET</span><span class="p">]</span>
 
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_KD.html b/docs/_modules/dice_ml/explainer_interfaces/dice_KD.html
index a1a7bef6..4730321a 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_KD.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_KD.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_KD &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_KD &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -108,15 +110,17 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
         <span class="bp">self</span><span class="o">.</span><span class="n">total_random_inits</span> <span class="o">=</span> <span class="mi">0</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>  <span class="c1"># initiating data related parameters</span>
 
-        <span class="c1"># As DiCE KD uses one-hot-encoding</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">()</span>
-
         <span class="c1"># initializing model variables</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading pickled trained model if applicable</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">feed_data_params</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">initialize_transform_func</span><span class="p">()</span>
 
+        <span class="c1"># As DiCE KD uses one-hot-encoding</span>
+        <span class="c1"># temp data to create some attributes like encoded feature names</span>
+        <span class="n">temp_ohe_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="o">.</span><span class="n">iloc</span><span class="p">[[</span><span class="mi">0</span><span class="p">]])</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">(</span><span class="n">temp_ohe_data</span><span class="p">)</span>
+
         <span class="c1"># loading trained model</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>
 
@@ -131,7 +135,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
                                   <span class="n">features_to_vary</span><span class="o">=</span><span class="s2">&quot;all&quot;</span><span class="p">,</span>
                                   <span class="n">permitted_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sparsity_weight</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
                                   <span class="n">feature_weights</span><span class="o">=</span><span class="s2">&quot;inverse_mad&quot;</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span>
-                                  <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+                                  <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="o">=</span><span class="mi">10000</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Generates diverse counterfactual explanations</span>
 
 <span class="sd">        :param query_instance: A dictionary of feature names and values. Test point of interest.</span>
@@ -155,6 +159,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
 <span class="sd">                                           varying from 10k to 1000k) and only if the features share a monotonic</span>
 <span class="sd">                                           relationship with predicted outcome in the model.</span>
 <span class="sd">        :param verbose: Parameter to determine whether to print &#39;Diverse Counterfactuals found!&#39;</span>
+<span class="sd">        :param limit_steps_ls: Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</span>
 
 <span class="sd">        :return: A CounterfactualExamples object to store and visualize the resulting counterfactual explanations</span>
 <span class="sd">                 (see diverse_counterfactuals.py).</span>
@@ -198,7 +203,9 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
                                                               <span class="n">sparsity_weight</span><span class="p">,</span>
                                                               <span class="n">stopping_threshold</span><span class="p">,</span>
                                                               <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
-                                                              <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">verbose</span><span class="p">)</span>
+                                                              <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                              <span class="n">verbose</span><span class="p">,</span>
+                                                              <span class="n">limit_steps_ls</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span> <span class="o">=</span> <span class="n">cfs_preds</span>
 
         <span class="k">return</span> <span class="n">exp</span><span class="o">.</span><span class="n">CounterfactualExamples</span><span class="p">(</span><span class="n">data_interface</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span>
@@ -299,16 +306,23 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
 <div class="viewcode-block" id="DiceKD.find_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">find_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data_df_copy</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">query_instance_orig</span><span class="p">,</span> <span class="n">desired_range</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span>
                              <span class="n">total_CFs</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">,</span> <span class="n">permitted_range</span><span class="p">,</span>
                              <span class="n">sparsity_weight</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
-                             <span class="n">verbose</span><span class="p">):</span>
+                             <span class="n">verbose</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Finds counterfactuals by querying a K-D tree for the nearest data points in the desired class from the dataset.&quot;&quot;&quot;</span>
 
         <span class="n">start_time</span> <span class="o">=</span> <span class="n">timeit</span><span class="o">.</span><span class="n">default_timer</span><span class="p">()</span>
 
         <span class="c1"># Making the one-hot-encoded version of query instance match the one-hot encoded version of the dataset</span>
         <span class="n">query_instance_df_dummies</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">query_instance_orig</span><span class="p">)</span>
-        <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">data_df_copy</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span><span class="o">.</span><span class="n">columns</span><span class="p">:</span>
+
+        <span class="n">data_df_columns</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">data_df_copy</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span><span class="o">.</span><span class="n">columns</span>
+        <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">data_df_columns</span><span class="p">:</span>
             <span class="k">if</span> <span class="n">col</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">query_instance_df_dummies</span><span class="o">.</span><span class="n">columns</span><span class="p">:</span>
                 <span class="n">query_instance_df_dummies</span><span class="p">[</span><span class="n">col</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
+
+        <span class="c1"># Fix order of columns in the query instance. This is necessary because KD-tree treats data as a simple array</span>
+        <span class="c1"># instead of a dataframe.</span>
+        <span class="n">query_instance_df_dummies</span> <span class="o">=</span> <span class="n">query_instance_df_dummies</span><span class="o">.</span><span class="n">reindex</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="n">data_df_columns</span><span class="p">)</span>
+
         <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">,</span> <span class="n">cfs_preds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">vary_valid</span><span class="p">(</span><span class="n">query_instance_df_dummies</span><span class="p">,</span>
                                                     <span class="n">total_CFs</span><span class="p">,</span>
                                                     <span class="n">features_to_vary</span><span class="p">,</span>
@@ -323,7 +337,8 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_KD</h1><div class="highlig
                 <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">deepcopy</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">)</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs_df_sparse</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span>
                                                                                 <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
-                                                                                <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+                                                                                <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                                                <span class="n">limit_steps_ls</span><span class="p">)</span>
             <span class="k">else</span><span class="p">:</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="k">else</span><span class="p">:</span>
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_genetic.html b/docs/_modules/dice_ml/explainer_interfaces/dice_genetic.html
index 75d3c4ad..96ae25b9 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_genetic.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_genetic.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_genetic &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_genetic &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -91,11 +93,11 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
 
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
-<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">LabelEncoder</span>
 
 <span class="kn">from</span> <span class="nn">dice_ml</span> <span class="kn">import</span> <span class="n">diverse_counterfactuals</span> <span class="k">as</span> <span class="n">exp</span>
 <span class="kn">from</span> <span class="nn">dice_ml.constants</span> <span class="kn">import</span> <span class="n">ModelTypes</span>
 <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.explainer_base</span> <span class="kn">import</span> <span class="n">ExplainerBase</span>
+<span class="kn">from</span> <span class="nn">dice_ml.utils.exception</span> <span class="kn">import</span> <span class="n">UserConfigValidationException</span>
 
 
 <div class="viewcode-block" id="DiceGenetic"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic">[docs]</a><span class="k">class</span> <span class="nc">DiceGenetic</span><span class="p">(</span><span class="n">ExplainerBase</span><span class="p">):</span>
@@ -107,11 +109,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
 <span class="sd">        :param model_interface: an interface class to access trained ML model.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">,</span> <span class="n">model_interface</span><span class="p">)</span>  <span class="c1"># initiating data related parameters</span>
-
-        <span class="c1"># number of output nodes of ML model</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_num_output_nodes2</span><span class="p">(</span>
-                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">1</span><span class="p">][</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="kc">None</span>
 
         <span class="c1"># variables required to generate CFs - see generate_counterfactuals() for more info</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">cfs</span> <span class="o">=</span> <span class="p">[]</span>
@@ -121,15 +119,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
         <span class="bp">self</span><span class="o">.</span><span class="n">feature_weights_input</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
 
         <span class="c1"># Initializing a label encoder to obtain label-encoded values for categorical variables</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">labelencoder</span> <span class="o">=</span> <span class="p">{}</span>
-
-        <span class="bp">self</span><span class="o">.</span><span class="n">label_encoded_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-
-        <span class="k">for</span> <span class="n">column</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">labelencoder</span><span class="p">[</span><span class="n">column</span><span class="p">]</span> <span class="o">=</span> <span class="n">LabelEncoder</span><span class="p">()</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">label_encoded_data</span><span class="p">[</span><span class="n">column</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">labelencoder</span><span class="p">[</span><span class="n">column</span><span class="p">]</span><span class="o">.</span><span class="n">fit_transform</span><span class="p">(</span>
-                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="n">column</span><span class="p">])</span>
-
+        <span class="bp">self</span><span class="o">.</span><span class="n">labelencoder</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">fit_label_encoders</span><span class="p">()</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">predicted_outcome_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span> <span class="o">+</span> <span class="s1">&#39;_pred&#39;</span>
 
 <div class="viewcode-block" id="DiceGenetic.update_hyperparameters"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.update_hyperparameters">[docs]</a>    <span class="k">def</span> <span class="nf">update_hyperparameters</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">proximity_weight</span><span class="p">,</span> <span class="n">sparsity_weight</span><span class="p">,</span>
@@ -149,7 +139,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
         <span class="c1"># define the loss parts</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">yloss_type</span> <span class="o">=</span> <span class="n">yloss_type</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">diversity_loss_type</span> <span class="o">=</span> <span class="n">diversity_loss_type</span>
-
         <span class="c1"># define feature weights</span>
         <span class="k">if</span> <span class="n">feature_weights</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_weights_input</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">feature_weights_input</span> <span class="o">=</span> <span class="n">feature_weights</span>
@@ -171,8 +160,8 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
                     <span class="k">if</span> <span class="n">feature</span> <span class="ow">in</span> <span class="n">feature_weights</span><span class="p">:</span>
                         <span class="n">feature_weights_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">feature_weights</span><span class="p">[</span><span class="n">feature</span><span class="p">])</span>
                     <span class="k">else</span><span class="p">:</span>
-                        <span class="c1"># TODO: why is the weight the max value of the encoded feature</span>
-                        <span class="n">feature_weights_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">label_encoded_data</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">max</span><span class="p">())</span>
+                        <span class="c1"># the weight is inversely proportional to max value</span>
+                        <span class="n">feature_weights_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="mi">1</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_range</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">max</span><span class="p">(),</span> <span class="mi">2</span><span class="p">))</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">feature_weights_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">feature_weights_list</span><span class="p">]</span></div>
 
 <div class="viewcode-block" id="DiceGenetic.do_random_init"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_random_init">[docs]</a>    <span class="k">def</span> <span class="nf">do_random_init</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">num_inits</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">desired_range</span><span class="p">):</span>
@@ -343,6 +332,11 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
 <span class="sd">                 (see diverse_counterfactuals.py).</span>
 <span class="sd">        &quot;&quot;&quot;</span>
 
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span> <span class="s1">&#39;data_df&#39;</span><span class="p">)</span> <span class="ow">and</span> <span class="n">initialization</span> <span class="o">==</span> <span class="s2">&quot;kdtree&quot;</span><span class="p">:</span>
+            <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
+                    <span class="s2">&quot;kd-tree initialization is not supported for private data&quot;</span>
+                    <span class="s2">&quot; interface because training data to build kd-tree is not available.&quot;</span><span class="p">)</span>
+
         <span class="bp">self</span><span class="o">.</span><span class="n">population_size</span> <span class="o">=</span> <span class="mi">10</span> <span class="o">*</span> <span class="n">total_CFs</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">start_time</span> <span class="o">=</span> <span class="n">timeit</span><span class="o">.</span><span class="n">default_timer</span><span class="p">()</span>
@@ -355,18 +349,24 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
                 <span class="n">query_instance</span><span class="o">=</span><span class="n">query_instance_orig</span><span class="p">)</span>
         <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">prepare_query_instance</span><span class="p">(</span>
                 <span class="n">query_instance</span><span class="o">=</span><span class="n">query_instance</span><span class="p">)</span>
+        <span class="c1"># number of output nodes of ML model</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="kc">None</span>
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_num_output_nodes2</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
+
         <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label_encode</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
         <span class="n">query_instance</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">query_instance</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">x1</span> <span class="o">=</span> <span class="n">query_instance</span>
 
         <span class="c1"># find the predicted value of query_instance</span>
         <span class="n">test_pred</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
+
         <span class="bp">self</span><span class="o">.</span><span class="n">test_pred</span> <span class="o">=</span> <span class="n">test_pred</span>
 
         <span class="n">desired_class</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">misc_init</span><span class="p">(</span><span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">desired_range</span><span class="p">,</span> <span class="n">test_pred</span><span class="p">)</span>
 
         <span class="n">query_instance_df_dummies</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="n">query_instance_orig</span><span class="p">)</span>
-        <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">pd</span><span class="o">.</span><span class="n">get_dummies</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span><span class="o">.</span><span class="n">columns</span><span class="p">:</span>
+        <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_all_dummy_colnames</span><span class="p">():</span>
             <span class="k">if</span> <span class="n">col</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">query_instance_df_dummies</span><span class="o">.</span><span class="n">columns</span><span class="p">:</span>
                 <span class="n">query_instance_df_dummies</span><span class="p">[</span><span class="n">col</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
 
@@ -390,12 +390,17 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
 <div class="viewcode-block" id="DiceGenetic.predict_fn_scores"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn_scores">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn_scores</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Returns prediction scores.&quot;&quot;&quot;</span>
         <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label_decode</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span></div>
+        <span class="n">out</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span>
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span> <span class="ow">and</span> <span class="n">out</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="c1"># DL models return only 1 for binary classification</span>
+            <span class="n">out</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">hstack</span><span class="p">((</span><span class="mi">1</span><span class="o">-</span><span class="n">out</span><span class="p">,</span> <span class="n">out</span><span class="p">))</span>
+        <span class="k">return</span> <span class="n">out</span></div>
 
 <div class="viewcode-block" id="DiceGenetic.predict_fn"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Returns actual prediction.&quot;&quot;&quot;</span>
         <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label_decode</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">,</span> <span class="n">model_score</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div>
+        <span class="n">preds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">,</span> <span class="n">model_score</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
+        <span class="k">return</span> <span class="n">preds</span></div>
 
     <span class="k">def</span> <span class="nf">_predict_fn_custom</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Checks that the maximum predicted score lies in the desired class.&quot;&quot;&quot;</span>
@@ -407,6 +412,9 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_genetic</h1><div class="hi
 
         <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label_decode</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span>
         <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">,</span> <span class="n">model_score</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span> <span class="ow">and</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">output</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
+            <span class="c1"># DL models return only 1 for binary classification</span>
+            <span class="n">output</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">hstack</span><span class="p">((</span><span class="mi">1</span><span class="o">-</span><span class="n">output</span><span class="p">,</span> <span class="n">output</span><span class="p">))</span>
         <span class="n">desired_class</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">desired_class</span><span class="p">)</span>
         <span class="n">maxvalues</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
         <span class="n">predicted_values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_pytorch.html b/docs/_modules/dice_ml/explainer_interfaces/dice_pytorch.html
index d1814803..731194c8 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_pytorch.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_pytorch.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_pytorch &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_pytorch &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -92,7 +94,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 <span class="kn">import</span> <span class="nn">torch</span>
 
 <span class="kn">from</span> <span class="nn">dice_ml</span> <span class="kn">import</span> <span class="n">diverse_counterfactuals</span> <span class="k">as</span> <span class="n">exp</span>
-<span class="kn">from</span> <span class="nn">dice_ml.counterfactual_explanations</span> <span class="kn">import</span> <span class="n">CounterfactualExplanations</span>
 <span class="kn">from</span> <span class="nn">dice_ml.explainer_interfaces.explainer_base</span> <span class="kn">import</span> <span class="n">ExplainerBase</span>
 
 
@@ -106,20 +107,17 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="c1"># initiating data related parameters</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_categorical_feature_indexes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_continuous_feature_indexes</span><span class="p">,</span> \
-            <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_data_params_for_gradient_dice</span><span class="p">()</span>
-
         <span class="c1"># initializing model related variables</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading trained model</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">func</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>  <span class="c1"># TODO: this error is probably too big - need to change it.</span>
-            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Gradient-based DiCE currently &quot;</span>
-                             <span class="s2">&quot;(1) accepts the data only in raw categorical and continuous formats, &quot;</span>
-                             <span class="s2">&quot;(2) does one-hot-encoding and min-max-normalization internally, &quot;</span>
-                             <span class="s2">&quot;(3) expects the ML model the accept the data in this same format. &quot;</span>
-                             <span class="s2">&quot;If your problem supports this, please initialize model class again &quot;</span>
-                             <span class="s2">&quot;with no custom transformation function.&quot;</span><span class="p">)</span>
-        <span class="c1"># number of output nodes of ML model</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">feed_data_params</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">initialize_transform_func</span><span class="p">()</span>
+        <span class="c1"># temp data to create some attributes like encoded feature names</span>
+        <span class="n">temp_ohe_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="o">.</span><span class="n">iloc</span><span class="p">[[</span><span class="mi">0</span><span class="p">]])</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">(</span><span class="n">temp_ohe_data</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_categorical_feature_indexes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_continuous_feature_indexes</span><span class="p">,</span> \
+            <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_data_params_for_gradient_dice</span><span class="p">()</span>
+
         <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_num_output_nodes</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">))</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
 
         <span class="c1"># variables required to generate CFs - see generate_counterfactuals() for more info</span>
@@ -131,19 +129,22 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
         <span class="bp">self</span><span class="o">.</span><span class="n">hyperparameters</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]</span>  <span class="c1"># proximity_weight, diversity_weight, categorical_penalty</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">optimizer_weights</span> <span class="o">=</span> <span class="p">[]</span>  <span class="c1"># optimizer, learning_rate</span>
 
-<div class="viewcode-block" id="DicePyTorch.generate_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.generate_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">generate_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">proximity_weight</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
-                                 <span class="n">diversity_weight</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">categorical_penalty</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">algorithm</span><span class="o">=</span><span class="s2">&quot;DiverseCF&quot;</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="o">=</span><span class="s2">&quot;all&quot;</span><span class="p">,</span>
-                                 <span class="n">permitted_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">yloss_type</span><span class="o">=</span><span class="s2">&quot;hinge_loss&quot;</span><span class="p">,</span> <span class="n">diversity_loss_type</span><span class="o">=</span><span class="s2">&quot;dpp_style:inverse_dist&quot;</span><span class="p">,</span>
-                                 <span class="n">feature_weights</span><span class="o">=</span><span class="s2">&quot;inverse_mad&quot;</span><span class="p">,</span> <span class="n">optimizer</span><span class="o">=</span><span class="s2">&quot;pytorch:adam&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span>
-                                 <span class="n">max_iter</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span> <span class="n">project_iter</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
-                                 <span class="n">init_near_query_instance</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">tie_random</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
-                                 <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">):</span>
+    <span class="k">def</span> <span class="nf">_generate_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="p">,</span>
+                                  <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">desired_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+                                  <span class="n">proximity_weight</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
+                                  <span class="n">diversity_weight</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">categorical_penalty</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">algorithm</span><span class="o">=</span><span class="s2">&quot;DiverseCF&quot;</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="o">=</span><span class="s2">&quot;all&quot;</span><span class="p">,</span>
+                                  <span class="n">permitted_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">yloss_type</span><span class="o">=</span><span class="s2">&quot;hinge_loss&quot;</span><span class="p">,</span> <span class="n">diversity_loss_type</span><span class="o">=</span><span class="s2">&quot;dpp_style:inverse_dist&quot;</span><span class="p">,</span>
+                                  <span class="n">feature_weights</span><span class="o">=</span><span class="s2">&quot;inverse_mad&quot;</span><span class="p">,</span> <span class="n">optimizer</span><span class="o">=</span><span class="s2">&quot;pytorch:adam&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span>
+                                  <span class="n">max_iter</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span> <span class="n">project_iter</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+                                  <span class="n">init_near_query_instance</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">tie_random</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
+                                  <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="o">=</span><span class="mi">10000</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Generates diverse counterfactual explanations.</span>
 
 <span class="sd">        :param query_instance: Test point of interest. A dictionary of feature names and values or a single row dataframe</span>
 <span class="sd">        :param total_CFs: Total number of counterfactuals required.</span>
 <span class="sd">        :param desired_class: Desired counterfactual class - can take 0 or 1. Default value is &quot;opposite&quot; to the outcome class</span>
 <span class="sd">                              of query_instance for binary classification.</span>
+<span class="sd">        :param desired_range: Not supported currently.</span>
 <span class="sd">        :param proximity_weight: A positive float. Larger this weight, more close the counterfactuals are to the</span>
 <span class="sd">                                 query_instance.</span>
 <span class="sd">        :param diversity_weight: A positive float. Larger this weight, more diverse the counterfactuals are.</span>
@@ -177,6 +178,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 <span class="sd">                                           Prefer binary search when a feature range is large</span>
 <span class="sd">                                           (for instance, income varying from 10k to 1000k) and only if the features</span>
 <span class="sd">                                           share a monotonic relationship with predicted outcome in the model.</span>
+<span class="sd">        :param limit_steps_ls: Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</span>
 
 <span class="sd">        :return: A CounterfactualExamples object to store and visualize the resulting</span>
 <span class="sd">                 counterfactual explanations (see diverse_counterfactuals.py).</span>
@@ -187,10 +189,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 
         <span class="c1"># check permitted range for continuous features</span>
         <span class="k">if</span> <span class="n">permitted_range</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
-            <span class="c1"># if not self.data_interface.check_features_range(permitted_range):</span>
-            <span class="c1">#     raise ValueError(</span>
-            <span class="c1">#         &quot;permitted range of features should be within their original range&quot;)</span>
-            <span class="c1"># else:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">permitted_range</span> <span class="o">=</span> <span class="n">permitted_range</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_minx_maxx</span><span class="p">(</span><span class="n">normalized</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span> <span class="o">=</span> <span class="p">[]</span>
@@ -210,9 +208,9 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
             <span class="bp">self</span><span class="o">.</span><span class="n">find_counterfactuals</span><span class="p">(</span>
                 <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span> <span class="n">max_iter</span><span class="p">,</span>
                 <span class="n">project_iter</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="p">,</span> <span class="n">verbose</span><span class="p">,</span> <span class="n">init_near_query_instance</span><span class="p">,</span>
-                <span class="n">tie_random</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+                <span class="n">tie_random</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">)</span>
 
-        <span class="n">counterfactual_explanations</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">CounterfactualExamples</span><span class="p">(</span>
+        <span class="k">return</span> <span class="n">exp</span><span class="o">.</span><span class="n">CounterfactualExamples</span><span class="p">(</span>
             <span class="n">data_interface</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span>
             <span class="n">final_cfs_df</span><span class="o">=</span><span class="n">final_cfs_df</span><span class="p">,</span>
             <span class="n">test_instance_df</span><span class="o">=</span><span class="n">test_instance_df</span><span class="p">,</span>
@@ -220,21 +218,24 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
             <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="n">posthoc_sparsity_param</span><span class="p">,</span>
             <span class="n">desired_class</span><span class="o">=</span><span class="n">desired_class</span><span class="p">)</span>
 
-        <span class="k">return</span> <span class="n">CounterfactualExplanations</span><span class="p">(</span><span class="n">cf_examples_list</span><span class="o">=</span><span class="p">[</span><span class="n">counterfactual_explanations</span><span class="p">])</span></div>
-
-<div class="viewcode-block" id="DicePyTorch.get_model_output"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output">[docs]</a>    <span class="k">def</span> <span class="nf">get_model_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
+<div class="viewcode-block" id="DicePyTorch.get_model_output"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output">[docs]</a>    <span class="k">def</span> <span class="nf">get_model_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">,</span>
+                         <span class="n">transform_data</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">out_tensor</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;get output probability of ML model&quot;&quot;&quot;</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)[(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span><span class="o">-</span><span class="mi">1</span><span class="p">):]</span></div>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span>
+                <span class="n">input_instance</span><span class="p">,</span>
+                <span class="n">transform_data</span><span class="o">=</span><span class="n">transform_data</span><span class="p">,</span>
+                <span class="n">out_tensor</span><span class="o">=</span><span class="n">out_tensor</span><span class="p">)[(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span><span class="o">-</span><span class="mi">1</span><span class="p">):]</span></div>
 
 <div class="viewcode-block" id="DicePyTorch.predict_fn"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function&quot;&quot;&quot;</span>
         <span class="k">if</span> <span class="ow">not</span> <span class="n">torch</span><span class="o">.</span><span class="n">is_tensor</span><span class="p">(</span><span class="n">input_instance</span><span class="p">):</span>
             <span class="n">input_instance</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_model_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span></div>
+        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_model_output</span><span class="p">(</span>
+                <span class="n">input_instance</span><span class="p">,</span> <span class="n">transform_data</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">out_tensor</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div>
 
 <div class="viewcode-block" id="DicePyTorch.predict_fn_for_sparsity"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn_for_sparsity">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn_for_sparsity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function for sparsity correction&quot;&quot;&quot;</span>
-        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">iloc</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span>
         <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">())</span></div>
 
 <div class="viewcode-block" id="DicePyTorch.do_cf_initializations"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_cf_initializations">[docs]</a>    <span class="k">def</span> <span class="nf">do_cf_initializations</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">total_CFs</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">):</span>
@@ -500,13 +501,9 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 <div class="viewcode-block" id="DicePyTorch.find_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">find_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span>
                              <span class="n">max_iter</span><span class="p">,</span> <span class="n">project_iter</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="p">,</span> <span class="n">verbose</span><span class="p">,</span>
                              <span class="n">init_near_query_instance</span><span class="p">,</span> <span class="n">tie_random</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
-                             <span class="n">posthoc_sparsity_algorithm</span><span class="p">):</span>
+                             <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Finds counterfactuals by gradient-descent.&quot;&quot;&quot;</span>
-
-        <span class="c1"># Prepares user defined query_instance for DiCE.</span>
-        <span class="c1"># query_instance = self.data_interface.prepare_query_instance(query_instance=query_instance, encoding=&#39;one-hot&#39;)</span>
-        <span class="c1"># query_instance = query_instance.iloc[0].values</span>
-        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">iloc</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">x1</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
 
         <span class="c1"># find the predicted value of query_instance</span>
@@ -645,19 +642,25 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_pytorch</h1><div class="hi
 
         <span class="c1"># do inverse transform of CFs to original user-fed format</span>
         <span class="n">cfs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">))])</span>
-        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">)</span>
+        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">))</span>
+        <span class="c1"># rounding off to 3 decimal places</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">preds</span><span class="o">.</span><span class="n">flatten</span><span class="p">()</span><span class="o">.</span><span class="n">tolist</span><span class="p">(),</span> <span class="mi">3</span><span class="p">)</span> <span class="k">for</span> <span class="n">preds</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span><span class="p">]</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">item</span> <span class="k">for</span> <span class="n">sublist</span> <span class="ow">in</span> <span class="n">cfs_preds</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">sublist</span><span class="p">]</span>
         <span class="n">final_cfs_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">cfs_preds</span><span class="p">)</span>
 
-        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
+        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">))</span>
         <span class="n">test_instance_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">test_pred</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
 
         <span class="c1"># post-hoc operation on continuous features to enhance sparsity - only for public data</span>
         <span class="k">if</span> <span class="n">posthoc_sparsity_param</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">posthoc_sparsity_param</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> <span class="s1">&#39;data_df&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">final_cfs_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span>
-                <span class="n">final_cfs_df_sparse</span><span class="p">,</span> <span class="n">test_instance_df</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="n">final_cfs_df_sparse</span><span class="p">,</span>
+                                                                       <span class="n">test_instance_df</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                                       <span class="n">limit_steps_ls</span><span class="p">)</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="kc">None</span>
 
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_random.html b/docs/_modules/dice_ml/explainer_interfaces/dice_random.html
index 40a9d181..83e36586 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_random.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_random.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_random &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_random &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -107,7 +109,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>  <span class="c1"># initiating data related parameters</span>
 
-        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">()</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading pickled trained model if applicable</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">feed_data_params</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
@@ -122,7 +123,8 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
     <span class="k">def</span> <span class="nf">_generate_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="p">,</span> <span class="n">desired_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
                                   <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">permitted_range</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
                                   <span class="n">features_to_vary</span><span class="o">=</span><span class="s2">&quot;all&quot;</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span>
-                                  <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">sample_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">random_seed</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+                                  <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">sample_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="n">random_seed</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+                                  <span class="n">limit_steps_ls</span><span class="o">=</span><span class="mi">10000</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Generate counterfactuals by randomly sampling features.</span>
 
 <span class="sd">        :param query_instance: Test point of interest. A dictionary of feature names and values or a single row dataframe.</span>
@@ -142,6 +144,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
 <span class="sd">                                           share a monotonic relationship with predicted outcome in the model.</span>
 <span class="sd">        :param sample_size: Sampling size</span>
 <span class="sd">        :param random_seed: Random seed for reproducibility</span>
+<span class="sd">        :param limit_steps_ls: Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</span>
 
 <span class="sd">        :returns: A CounterfactualExamples object that contains the dataframe of generated counterfactuals as an attribute.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
@@ -158,7 +161,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
         <span class="c1"># Do predictions once on the query_instance and reuse across to reduce the number</span>
         <span class="c1"># inferences.</span>
         <span class="n">model_predictions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
-
         <span class="c1"># number of output nodes of ML model</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
@@ -251,8 +253,13 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
         <span class="k">if</span> <span class="n">posthoc_sparsity_param</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">posthoc_sparsity_param</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> \
                 <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="s1">&#39;data_df&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">final_cfs_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span>
-                <span class="n">final_cfs_df_sparse</span><span class="p">,</span> <span class="n">test_instance_df</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="n">final_cfs_df_sparse</span><span class="p">,</span>
+                                                                       <span class="n">test_instance_df</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                                       <span class="n">limit_steps_ls</span><span class="p">)</span>
+        <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">final_cfs_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="kc">None</span>
 
@@ -285,10 +292,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_random</h1><div class="hig
         <span class="c1"># first get required parameters</span>
         <span class="n">precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decimal_precisions</span><span class="p">(</span><span class="n">output_type</span><span class="o">=</span><span class="s2">&quot;dict&quot;</span><span class="p">)</span>
 
-        <span class="n">categorical_features_frequencies</span> <span class="o">=</span> <span class="p">{}</span>
-        <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
-            <span class="n">categorical_features_frequencies</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">value_counts</span><span class="p">())</span>
-
         <span class="k">if</span> <span class="n">sampling_random_seed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
             <span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="n">sampling_random_seed</span><span class="p">)</span>
 
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html b/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html
index a12139eb..f570e00e 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_tensorflow1 &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_tensorflow1 &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -108,6 +110,14 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="c1"># initiating data related parameters</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
+        <span class="c1"># initializing model related variables</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading trained model</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">feed_data_params</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">initialize_transform_func</span><span class="p">()</span>
+        <span class="c1"># temp data to create some attributes like encoded feature names</span>
+        <span class="n">temp_ohe_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="o">.</span><span class="n">iloc</span><span class="p">[[</span><span class="mi">0</span><span class="p">]])</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">(</span><span class="n">temp_ohe_data</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_categorical_feature_indexes</span><span class="p">,</span> \
             <span class="bp">self</span><span class="o">.</span><span class="n">encoded_continuous_feature_indexes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span><span class="p">,</span> \
             <span class="bp">self</span><span class="o">.</span><span class="n">cont_maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_data_params_for_gradient_dice</span><span class="p">()</span>
@@ -118,18 +128,8 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
         <span class="k">else</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">dice_sess</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">InteractiveSession</span><span class="p">()</span>
 
-        <span class="c1"># initializing model related variables</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading trained model</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">input_tensor</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">Variable</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>  <span class="c1"># placeholder variables for model predictions</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">output_tensor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">input_tensor</span><span class="p">)</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">func</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>  <span class="c1"># TODO: this error is probably too big - need to change it.</span>
-            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Gradient-based DiCE currently &quot;</span>
-                             <span class="s2">&quot;(1) accepts the data only in raw categorical and continuous formats, &quot;</span>
-                             <span class="s2">&quot;(2) does one-hot-encoding and min-max-normalization internally, &quot;</span>
-                             <span class="s2">&quot;(3) expects the ML model the accept the data in this same format. &quot;</span>
-                             <span class="s2">&quot;If your problem supports this, please initialize model class again &quot;</span>
-                             <span class="s2">&quot;with no custom transformation function.&quot;</span><span class="p">)</span>
         <span class="c1"># number of output nodes of ML model</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dice_sess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_num_output_nodes</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">)))</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
@@ -153,7 +153,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
                                  <span class="n">optimizer</span><span class="o">=</span><span class="s2">&quot;tensorflow:adam&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span> <span class="n">max_iter</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span>
                                  <span class="n">project_iter</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
                                  <span class="n">init_near_query_instance</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">tie_random</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
-                                 <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">):</span>
+                                 <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="o">=</span><span class="mi">10000</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Generates diverse counterfactual explanations</span>
 
 <span class="sd">        :param query_instance: Test point of interest. A dictionary of feature names and values or a single row dataframe.</span>
@@ -196,6 +196,8 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
 <span class="sd">                                           Prefer binary search when a feature range is large</span>
 <span class="sd">                                           (for instance, income varying from 10k to 1000k) and only if the features</span>
 <span class="sd">                                           share a monotonic relationship with predicted outcome in the model.</span>
+<span class="sd">        :param limit_steps_ls: Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</span>
+
 
 <span class="sd">        :return: A CounterfactualExamples object to store and visualize the resulting counterfactual explanations</span>
 <span class="sd">                 (see diverse_counterfactuals.py).</span>
@@ -208,10 +210,6 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
 
         <span class="c1"># check permitted range for continuous features</span>
         <span class="k">if</span> <span class="n">permitted_range</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
-            <span class="c1"># if not self.data_interface.check_features_range(permitted_range):</span>
-            <span class="c1">#     raise ValueError(</span>
-            <span class="c1">#         &quot;permitted range of features should be within their original range&quot;)</span>
-            <span class="c1"># else:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">permitted_range</span> <span class="o">=</span> <span class="n">permitted_range</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_minx_maxx</span><span class="p">(</span><span class="n">normalized</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span> <span class="o">=</span> <span class="p">[]</span>
@@ -242,7 +240,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
             <span class="bp">self</span><span class="o">.</span><span class="n">update_hyperparameters</span><span class="p">(</span><span class="n">proximity_weight</span><span class="p">,</span> <span class="n">diversity_weight</span><span class="p">,</span> <span class="n">categorical_penalty</span><span class="p">)</span>
 
         <span class="n">final_cfs_df</span><span class="p">,</span> <span class="n">test_instance_df</span><span class="p">,</span> <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">find_counterfactuals</span><span class="p">(</span>
-            <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span> <span class="n">max_iter</span><span class="p">,</span> <span class="n">project_iter</span><span class="p">,</span>
+            <span class="n">query_instance</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span> <span class="n">max_iter</span><span class="p">,</span> <span class="n">project_iter</span><span class="p">,</span>
             <span class="n">loss_diff_thres</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="p">,</span> <span class="n">verbose</span><span class="p">,</span> <span class="n">init_near_query_instance</span><span class="p">,</span> <span class="n">tie_random</span><span class="p">,</span>
             <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
 
@@ -312,7 +310,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
 
 <div class="viewcode-block" id="DiceTensorFlow1.predict_fn_for_sparsity"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.predict_fn_for_sparsity">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn_for_sparsity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function for sparsity correction&quot;&quot;&quot;</span>
-        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()</span>
         <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span></div>
 
 <div class="viewcode-block" id="DiceTensorFlow1.compute_yloss"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_yloss">[docs]</a>    <span class="k">def</span> <span class="nf">compute_yloss</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">method</span><span class="p">):</span>
@@ -433,7 +431,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
                 <span class="n">feature_weights</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="o">=</span> <span class="nb">round</span><span class="p">(</span><span class="mi">1</span><span class="o">/</span><span class="n">normalized_mads</span><span class="p">[</span><span class="n">feature</span><span class="p">],</span> <span class="mi">2</span><span class="p">)</span>
 
         <span class="n">feature_weights_list</span> <span class="o">=</span> <span class="p">[]</span>
-        <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">encoded_feature_names</span><span class="p">:</span>
+        <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">:</span>
             <span class="k">if</span> <span class="n">feature</span> <span class="ow">in</span> <span class="n">feature_weights</span><span class="p">:</span>
                 <span class="n">feature_weights_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">feature_weights</span><span class="p">[</span><span class="n">feature</span><span class="p">])</span>
             <span class="k">else</span><span class="p">:</span>
@@ -603,19 +601,16 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
             <span class="bp">self</span><span class="o">.</span><span class="n">loss_converge_iter</span> <span class="o">=</span> <span class="mi">0</span>
             <span class="k">return</span> <span class="kc">False</span></div>
 
-<div class="viewcode-block" id="DiceTensorFlow1.find_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">find_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span>
+<div class="viewcode-block" id="DiceTensorFlow1.find_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">find_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span>
                              <span class="n">max_iter</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span> <span class="n">project_iter</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
                              <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">init_near_query_instance</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">tie_random</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
                              <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Finds counterfactuals by gradient-descent.&quot;&quot;&quot;</span>
 
-        <span class="c1"># Prepares user defined query_instance for DiCE.</span>
-        <span class="c1"># query_instance = self.data_interface.prepare_query_instance(query_instance=query_instance, encoding=&#39;one-hot&#39;)</span>
-        <span class="c1"># query_instance = np.array([query_instance.iloc[0].values], dtype=np.float32)</span>
-        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()</span>
 
         <span class="c1"># find the predicted value of query_instance</span>
-        <span class="n">test_pred</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
+        <span class="n">test_pred</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">))[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
         <span class="k">if</span> <span class="n">desired_class</span> <span class="o">==</span> <span class="s2">&quot;opposite&quot;</span><span class="p">:</span>
             <span class="n">desired_class</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="nb">round</span><span class="p">(</span><span class="n">test_pred</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([[</span><span class="n">desired_class</span><span class="p">]])</span>
@@ -734,19 +729,24 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow1</h1><div class
 
         <span class="c1"># do inverse transform of CFs to original user-fed format</span>
         <span class="n">cfs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">))])</span>
-        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">)</span>
+        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+               <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">))</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">preds</span><span class="o">.</span><span class="n">flatten</span><span class="p">()</span><span class="o">.</span><span class="n">tolist</span><span class="p">(),</span> <span class="mi">3</span><span class="p">)</span> <span class="k">for</span> <span class="n">preds</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span><span class="p">]</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">item</span> <span class="k">for</span> <span class="n">sublist</span> <span class="ow">in</span> <span class="n">cfs_preds</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">sublist</span><span class="p">]</span>
         <span class="n">final_cfs_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">cfs_preds</span><span class="p">)</span>
 
-        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
+        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">))</span>
         <span class="n">test_instance_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">test_pred</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
 
         <span class="c1"># post-hoc operation on continuous features to enhance sparsity - only for public data</span>
         <span class="k">if</span> <span class="n">posthoc_sparsity_param</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">posthoc_sparsity_param</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> <span class="s1">&#39;data_df&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">final_cfs_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span>
-                <span class="n">final_cfs_df_sparse</span><span class="p">,</span> <span class="n">test_instance_df</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="n">final_cfs_df_sparse</span><span class="p">,</span>
+                                                                       <span class="n">test_instance_df</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                                       <span class="n">limit_steps_ls</span><span class="p">)</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="kc">None</span>
 
diff --git a/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html b/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html
index 626871fd..86e4333a 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.dice_tensorflow2 &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.dice_tensorflow2 &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -106,20 +108,20 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="c1"># initiating data related parameters</span>
         <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_categorical_feature_indexes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_continuous_feature_indexes</span><span class="p">,</span> \
-            <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_data_params_for_gradient_dice</span><span class="p">()</span>
-
         <span class="c1"># initializing model related variables</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">model_interface</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_model</span><span class="p">()</span>  <span class="c1"># loading trained model</span>
-        <span class="c1"># TODO: this error is probably too big - need to change it.</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">func</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
-            <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Gradient-based DiCE currently &quot;</span>
-                             <span class="s2">&quot;(1) accepts the data only in raw categorical and continuous formats, &quot;</span>
-                             <span class="s2">&quot;(2) does one-hot-encoding and min-max-normalization internally, &quot;</span>
-                             <span class="s2">&quot;(3) expects the ML model the accept the data in this same format. &quot;</span>
-                             <span class="s2">&quot;If your problem supports this, please initialize model class again &quot;</span>
-                             <span class="s2">&quot;with no custom transformation function.&quot;</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">feed_data_params</span><span class="p">(</span><span class="n">data_interface</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">initialize_transform_func</span><span class="p">()</span>
+        <span class="c1"># temp data to create some attributes like encoded feature names</span>
+        <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span> <span class="s2">&quot;data_df&quot;</span><span class="p">):</span>
+            <span class="n">temp_ohe_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">data_df</span><span class="o">.</span><span class="n">iloc</span><span class="p">[[</span><span class="mi">0</span><span class="p">]])</span>
+        <span class="k">else</span><span class="p">:</span>
+            <span class="n">temp_ohe_data</span> <span class="o">=</span> <span class="kc">None</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">create_ohe_params</span><span class="p">(</span><span class="n">temp_ohe_data</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_categorical_feature_indexes</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoded_continuous_feature_indexes</span><span class="p">,</span> \
+            <span class="bp">self</span><span class="o">.</span><span class="n">cont_minx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_maxx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cont_precisions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_data_params_for_gradient_dice</span><span class="p">()</span>
+
         <span class="c1"># number of output nodes of ML model</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_num_output_nodes</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">ohe_encoded_feature_names</span><span class="p">))</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
 
@@ -139,7 +141,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
                                  <span class="n">optimizer</span><span class="o">=</span><span class="s2">&quot;tensorflow:adam&quot;</span><span class="p">,</span> <span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.05</span><span class="p">,</span> <span class="n">min_iter</span><span class="o">=</span><span class="mi">500</span><span class="p">,</span> <span class="n">max_iter</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span>
                                  <span class="n">project_iter</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
                                  <span class="n">init_near_query_instance</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">tie_random</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
-                                 <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">):</span>
+                                 <span class="n">posthoc_sparsity_param</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="o">=</span><span class="s2">&quot;linear&quot;</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="o">=</span><span class="mi">10000</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Generates diverse counterfactual explanations</span>
 
 <span class="sd">        :param query_instance: Test point of interest. A dictionary of feature names and values or a single row dataframe</span>
@@ -181,6 +183,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
 <span class="sd">                                           Prefer binary search when a feature range is large</span>
 <span class="sd">                                           (for instance, income varying from 10k to 1000k) and only if the features</span>
 <span class="sd">                                           share a monotonic relationship with predicted outcome in the model.</span>
+<span class="sd">        :param limit_steps_ls: Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</span>
 
 <span class="sd">        :return: A CounterfactualExamples object to store and visualize the resulting counterfactual explanations</span>
 <span class="sd">                (see diverse_counterfactuals.py).</span>
@@ -216,7 +219,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
                                       <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span> <span class="n">max_iter</span><span class="p">,</span> <span class="n">project_iter</span><span class="p">,</span>
                                       <span class="n">loss_diff_thres</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="p">,</span> <span class="n">verbose</span><span class="p">,</span>
                                       <span class="n">init_near_query_instance</span><span class="p">,</span> <span class="n">tie_random</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span>
-                                      <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+                                      <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">)</span>
 
         <span class="n">counterfactual_explanations</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">CounterfactualExamples</span><span class="p">(</span>
             <span class="n">data_interface</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="p">,</span>
@@ -235,7 +238,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
 
 <div class="viewcode-block" id="DiceTensorFlow2.predict_fn_for_sparsity"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.predict_fn_for_sparsity">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn_for_sparsity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function for sparsity correction&quot;&quot;&quot;</span>
-        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">input_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()</span>
         <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="n">input_instance</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">))</span></div>
 
 <div class="viewcode-block" id="DiceTensorFlow2.do_cf_initializations"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_cf_initializations">[docs]</a>    <span class="k">def</span> <span class="nf">do_cf_initializations</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">total_CFs</span><span class="p">,</span> <span class="n">algorithm</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">):</span>
@@ -503,13 +506,10 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
 <div class="viewcode-block" id="DiceTensorFlow2.find_counterfactuals"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals">[docs]</a>    <span class="k">def</span> <span class="nf">find_counterfactuals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">desired_class</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">learning_rate</span><span class="p">,</span> <span class="n">min_iter</span><span class="p">,</span>
                              <span class="n">max_iter</span><span class="p">,</span> <span class="n">project_iter</span><span class="p">,</span> <span class="n">loss_diff_thres</span><span class="p">,</span> <span class="n">loss_converge_maxiter</span><span class="p">,</span> <span class="n">verbose</span><span class="p">,</span>
                              <span class="n">init_near_query_instance</span><span class="p">,</span> <span class="n">tie_random</span><span class="p">,</span> <span class="n">stopping_threshold</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
-                             <span class="n">posthoc_sparsity_algorithm</span><span class="p">):</span>
+                             <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Finds counterfactuals by gradient-descent.&quot;&quot;&quot;</span>
 
-        <span class="c1"># Prepares user defined query_instance for DiCE.</span>
-        <span class="c1"># query_instance = self.data_interface.prepare_query_instance(query_instance=query_instance, encoding=&#39;one-hot&#39;)</span>
-        <span class="c1"># query_instance = np.array([query_instance.iloc[0].values])</span>
-        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">values</span>
+        <span class="n">query_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">()</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">x1</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
 
         <span class="c1"># find the predicted value of query_instance</span>
@@ -621,8 +621,7 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
             <span class="bp">self</span><span class="o">.</span><span class="n">max_iterations_run</span> <span class="o">=</span> <span class="n">iterations</span>
 
         <span class="bp">self</span><span class="o">.</span><span class="n">elapsed</span> <span class="o">=</span> <span class="n">timeit</span><span class="o">.</span><span class="n">default_timer</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span>
-
-        <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">cfs</span><span class="p">)</span> <span class="k">for</span> <span class="n">cfs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">]</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">predict_fn</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="n">cfs</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">))</span> <span class="k">for</span> <span class="n">cfs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">]</span>
 
         <span class="c1"># update final_cfs from backed up CFs if valid CFs are not found</span>
         <span class="k">if</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">any</span><span class="p">(</span><span class="n">i</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span><span class="p">))</span> <span class="ow">or</span>
@@ -635,20 +634,25 @@ <h1>Source code for dice_ml.explainer_interfaces.dice_tensorflow2</h1><div class
 
         <span class="c1"># do inverse transform of CFs to original user-fed format</span>
         <span class="n">cfs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">final_cfs</span><span class="p">))])</span>
-        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">)</span>
+        <span class="n">final_cfs_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+               <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">cfs</span><span class="p">))</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">preds</span><span class="o">.</span><span class="n">flatten</span><span class="p">()</span><span class="o">.</span><span class="n">tolist</span><span class="p">(),</span> <span class="mi">3</span><span class="p">)</span> <span class="k">for</span> <span class="n">preds</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cfs_preds</span><span class="p">]</span>
         <span class="n">cfs_preds</span> <span class="o">=</span> <span class="p">[</span><span class="n">item</span> <span class="k">for</span> <span class="n">sublist</span> <span class="ow">in</span> <span class="n">cfs_preds</span> <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">sublist</span><span class="p">]</span>
         <span class="n">final_cfs_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">cfs_preds</span><span class="p">)</span>
 
-        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
+        <span class="n">test_instance_df</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">inverse_transform</span><span class="p">(</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">get_decoded_data</span><span class="p">(</span><span class="n">query_instance</span><span class="p">))</span>
         <span class="n">test_instance_df</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">test_pred</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
 
         <span class="c1"># post-hoc operation on continuous features to enhance sparsity - only for public data</span>
         <span class="k">if</span> <span class="n">posthoc_sparsity_param</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">posthoc_sparsity_param</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> \
                 <span class="s1">&#39;data_df&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="n">final_cfs_df</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
-            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span>
-                <span class="n">final_cfs_df_sparse</span><span class="p">,</span> <span class="n">test_instance_df</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span> <span class="n">posthoc_sparsity_algorithm</span><span class="p">)</span>
+            <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="n">final_cfs_df_sparse</span><span class="p">,</span>
+                                                                       <span class="n">test_instance_df</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
+                                                                       <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span>
+                                                                       <span class="n">limit_steps_ls</span><span class="p">)</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="n">final_cfs_df_sparse</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="c1"># need to check the above code on posthoc sparsity</span>
diff --git a/docs/_modules/dice_ml/explainer_interfaces/explainer_base.html b/docs/_modules/dice_ml/explainer_interfaces/explainer_base.html
index 7659a780..5e810c26 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/explainer_base.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/explainer_base.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.explainer_base &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.explainer_base &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -239,7 +241,6 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
                 <span class="n">query_instances_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">query_instances</span><span class="p">[</span><span class="n">ix</span><span class="p">:(</span><span class="n">ix</span><span class="o">+</span><span class="mi">1</span><span class="p">)])</span>
         <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">query_instances</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">):</span>
             <span class="n">query_instances_list</span> <span class="o">=</span> <span class="n">query_instances</span>
-
         <span class="k">for</span> <span class="n">query_instance</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="p">(</span><span class="n">query_instances_list</span><span class="p">):</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">set_continuous_feature_indexes</span><span class="p">(</span><span class="n">query_instance</span><span class="p">)</span>
             <span class="n">res</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_generate_counterfactuals</span><span class="p">(</span>
@@ -254,7 +255,6 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
                 <span class="n">verbose</span><span class="o">=</span><span class="n">verbose</span><span class="p">,</span>
                 <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
             <span class="n">cf_examples_arr</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">res</span><span class="p">)</span>
-
         <span class="bp">self</span><span class="o">.</span><span class="n">_check_any_counterfactuals_computed</span><span class="p">(</span><span class="n">cf_examples_arr</span><span class="o">=</span><span class="n">cf_examples_arr</span><span class="p">)</span>
 
         <span class="k">return</span> <span class="n">CounterfactualExplanations</span><span class="p">(</span><span class="n">cf_examples_list</span><span class="o">=</span><span class="n">cf_examples_arr</span><span class="p">)</span></div>
@@ -310,9 +310,6 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 
         <span class="bp">self</span><span class="o">.</span><span class="n">check_query_instance_validity</span><span class="p">(</span><span class="n">features_to_vary</span><span class="p">,</span> <span class="n">permitted_range</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">feature_ranges_orig</span><span class="p">)</span>
 
-        <span class="c1"># check feature MAD validity and throw warnings</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">check_mad_validity</span><span class="p">(</span><span class="n">feature_weights</span><span class="p">)</span>
-
         <span class="k">return</span> <span class="n">features_to_vary</span></div>
 
 <div class="viewcode-block" id="ExplainerBase.check_query_instance_validity"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_query_instance_validity">[docs]</a>    <span class="k">def</span> <span class="nf">check_query_instance_validity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">features_to_vary</span><span class="p">,</span> <span class="n">permitted_range</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">feature_ranges_orig</span><span class="p">):</span>
@@ -322,7 +319,6 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 
             <span class="k">if</span> <span class="n">feature</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">:</span>
                 <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Feature&quot;</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="s2">&quot;not present in training data!&quot;</span><span class="p">)</span>
-
         <span class="k">for</span> <span class="n">feature</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">categorical_feature_names</span><span class="p">:</span>
             <span class="k">if</span> <span class="n">query_instance</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">feature_ranges_orig</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span> <span class="ow">and</span> \
                     <span class="nb">str</span><span class="p">(</span><span class="n">query_instance</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">feature_ranges_orig</span><span class="p">[</span><span class="n">feature</span><span class="p">]:</span>
@@ -569,14 +565,19 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 
 <div class="viewcode-block" id="ExplainerBase.predict_fn"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function&quot;&quot;&quot;</span>
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span></div>
+
+        <span class="n">preds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span>
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span> <span class="ow">and</span> \
+           <span class="nb">len</span><span class="p">(</span><span class="n">preds</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>  <span class="c1"># from deep learning predictors</span>
+            <span class="n">preds</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">column_stack</span><span class="p">([</span><span class="mi">1</span> <span class="o">-</span> <span class="n">preds</span><span class="p">,</span> <span class="n">preds</span><span class="p">])</span>
+        <span class="k">return</span> <span class="n">preds</span></div>
 
 <div class="viewcode-block" id="ExplainerBase.predict_fn_for_sparsity"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn_for_sparsity">[docs]</a>    <span class="k">def</span> <span class="nf">predict_fn_for_sparsity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;prediction function for sparsity correction&quot;&quot;&quot;</span>
         <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span></div>
 
 <div class="viewcode-block" id="ExplainerBase.do_posthoc_sparsity_enhancement"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement">[docs]</a>    <span class="k">def</span> <span class="nf">do_posthoc_sparsity_enhancement</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">posthoc_sparsity_param</span><span class="p">,</span>
-                                        <span class="n">posthoc_sparsity_algorithm</span><span class="p">):</span>
+                                        <span class="n">posthoc_sparsity_algorithm</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Post-hoc method to encourage sparsity in a generated counterfactuals.</span>
 
 <span class="sd">        :param final_cfs_sparse: Final CFs in original user-fed format, in a pandas dataframe.</span>
@@ -587,6 +588,8 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 <span class="sd">                                           large (for instance, income varying from 10k to 1000k)</span>
 <span class="sd">                                           and only if the features share a monotonic relationship</span>
 <span class="sd">                                           with predicted outcome in the model.</span>
+<span class="sd">        :param limit_steps_ls: Defines the limit of steps to be done in the linear search,</span>
+<span class="sd">                                necessary to avoid infinite loops</span>
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="k">if</span> <span class="n">final_cfs_sparse</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
             <span class="k">return</span> <span class="n">final_cfs_sparse</span>
@@ -618,28 +621,31 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
                 <span class="k">if</span><span class="p">(</span><span class="nb">abs</span><span class="p">(</span><span class="n">diff</span><span class="p">)</span> <span class="o">&lt;=</span> <span class="n">quantiles</span><span class="p">[</span><span class="n">feature</span><span class="p">]):</span>
                     <span class="k">if</span> <span class="n">posthoc_sparsity_algorithm</span> <span class="o">==</span> <span class="s2">&quot;linear&quot;</span><span class="p">:</span>
                         <span class="n">final_cfs_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_linear_search</span><span class="p">(</span><span class="n">diff</span><span class="p">,</span> <span class="n">decimal_prec</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">cf_ix</span><span class="p">,</span>
-                                                                 <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">current_pred</span><span class="p">)</span>
+                                                                 <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">current_pred</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">)</span>
 
                     <span class="k">elif</span> <span class="n">posthoc_sparsity_algorithm</span> <span class="o">==</span> <span class="s2">&quot;binary&quot;</span><span class="p">:</span>
                         <span class="n">final_cfs_sparse</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">do_binary_search</span><span class="p">(</span>
                             <span class="n">diff</span><span class="p">,</span> <span class="n">decimal_prec</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">current_pred</span><span class="p">)</span>
 
             <span class="n">temp_preds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn_for_sparsity</span><span class="p">(</span><span class="n">final_cfs_sparse</span><span class="o">.</span><span class="n">loc</span><span class="p">[[</span><span class="n">cf_ix</span><span class="p">]][</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span>
-            <span class="n">cfs_preds_sparse</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">temp_preds</span><span class="p">)</span>
-
+            <span class="n">cfs_preds_sparse</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">temp_preds</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
         <span class="n">final_cfs_sparse</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_model_output_from_scores</span><span class="p">(</span><span class="n">cfs_preds_sparse</span><span class="p">)</span>
         <span class="c1"># final_cfs_sparse[self.data_interface.outcome_name] = np.round(final_cfs_sparse[self.data_interface.outcome_name], 3)</span>
         <span class="k">return</span> <span class="n">final_cfs_sparse</span></div>
 
-<div class="viewcode-block" id="ExplainerBase.do_linear_search"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search">[docs]</a>    <span class="k">def</span> <span class="nf">do_linear_search</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">diff</span><span class="p">,</span> <span class="n">decimal_prec</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">current_pred_orig</span><span class="p">):</span>
+<div class="viewcode-block" id="ExplainerBase.do_linear_search"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search">[docs]</a>    <span class="k">def</span> <span class="nf">do_linear_search</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">diff</span><span class="p">,</span> <span class="n">decimal_prec</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span>
+                         <span class="n">current_pred_orig</span><span class="p">,</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;Performs a greedy linear search - moves the continuous features in CFs towards original values in</span>
-<span class="sd">           query_instance greedily until the prediction class changes.&quot;&quot;&quot;</span>
+<span class="sd">           query_instance greedily until the prediction class changes, or it reaches the maximum number of steps&quot;&quot;&quot;</span>
 
         <span class="n">old_diff</span> <span class="o">=</span> <span class="n">diff</span>
         <span class="n">change</span> <span class="o">=</span> <span class="p">(</span><span class="mi">10</span><span class="o">**-</span><span class="n">decimal_prec</span><span class="p">[</span><span class="n">feature</span><span class="p">])</span>  <span class="c1"># the minimal possible change for a feature</span>
         <span class="n">current_pred</span> <span class="o">=</span> <span class="n">current_pred_orig</span>
+        <span class="n">count_steps</span> <span class="o">=</span> <span class="mi">0</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
-            <span class="k">while</span><span class="p">((</span><span class="nb">abs</span><span class="p">(</span><span class="n">diff</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mf">10e-4</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">sign</span><span class="p">(</span><span class="n">diff</span><span class="o">*</span><span class="n">old_diff</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_cf_valid</span><span class="p">(</span><span class="n">current_pred</span><span class="p">)):</span>
+            <span class="k">while</span><span class="p">((</span><span class="nb">abs</span><span class="p">(</span><span class="n">diff</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mf">10e-4</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">sign</span><span class="p">(</span><span class="n">diff</span><span class="o">*</span><span class="n">old_diff</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span>
+                  <span class="bp">self</span><span class="o">.</span><span class="n">is_cf_valid</span><span class="p">(</span><span class="n">current_pred</span><span class="p">))</span> <span class="ow">and</span> <span class="p">(</span><span class="n">count_steps</span> <span class="o">&lt;</span> <span class="n">limit_steps_ls</span><span class="p">):</span>
+
                 <span class="n">old_val</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">final_cfs_sparse</span><span class="o">.</span><span class="n">at</span><span class="p">[</span><span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">])</span>
                 <span class="n">final_cfs_sparse</span><span class="o">.</span><span class="n">at</span><span class="p">[</span><span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">]</span> <span class="o">+=</span> <span class="n">np</span><span class="o">.</span><span class="n">sign</span><span class="p">(</span><span class="n">diff</span><span class="p">)</span><span class="o">*</span><span class="n">change</span>
                 <span class="n">current_pred</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict_fn_for_sparsity</span><span class="p">(</span><span class="n">final_cfs_sparse</span><span class="o">.</span><span class="n">loc</span><span class="p">[[</span><span class="n">cf_ix</span><span class="p">]][</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span>
@@ -652,6 +658,8 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 
                 <span class="n">diff</span> <span class="o">=</span> <span class="n">query_instance</span><span class="p">[</span><span class="n">feature</span><span class="p">]</span><span class="o">.</span><span class="n">iat</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">-</span> <span class="nb">int</span><span class="p">(</span><span class="n">final_cfs_sparse</span><span class="o">.</span><span class="n">at</span><span class="p">[</span><span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">])</span>
 
+                <span class="n">count_steps</span> <span class="o">+=</span> <span class="mi">1</span>
+
         <span class="k">return</span> <span class="n">final_cfs_sparse</span></div>
 
 <div class="viewcode-block" id="ExplainerBase.do_binary_search"><a class="viewcode-back" href="../../../dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_binary_search">[docs]</a>    <span class="k">def</span> <span class="nf">do_binary_search</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">diff</span><span class="p">,</span> <span class="n">decimal_prec</span><span class="p">,</span> <span class="n">query_instance</span><span class="p">,</span> <span class="n">cf_ix</span><span class="p">,</span> <span class="n">feature</span><span class="p">,</span> <span class="n">final_cfs_sparse</span><span class="p">,</span> <span class="n">current_pred</span><span class="p">):</span>
@@ -734,14 +742,30 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="k">if</span> <span class="n">desired_class_input</span> <span class="o">==</span> <span class="s2">&quot;opposite&quot;</span><span class="p">:</span>
             <span class="k">if</span> <span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
-                <span class="n">original_pred_1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">original_pred</span><span class="p">)</span>
+                <span class="c1"># &#39;original_pred&#39; needs to be converted to the proper class if &#39;original_pred&#39; comes from the</span>
+                <span class="c1"># &#39;predict_proba&#39; method (length is 2 and class is index with maximum value). Otherwise &#39;original_pred&#39;</span>
+                <span class="c1"># already contains the class.</span>
+                <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">original_pred</span><span class="p">,</span> <span class="s2">&quot;__len__&quot;</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">original_pred</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
+                    <span class="n">original_pred_1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">original_pred</span><span class="p">)</span>
+                <span class="k">else</span><span class="p">:</span>
+                    <span class="n">original_pred_1</span> <span class="o">=</span> <span class="n">original_pred</span>
                 <span class="n">target_class</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">original_pred_1</span><span class="p">)</span>
                 <span class="k">return</span> <span class="n">target_class</span>
+            <span class="k">elif</span> <span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>  <span class="c1"># only for pytorch DL model</span>
+                <span class="n">original_pred_1</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">original_pred</span><span class="p">)</span>
+                <span class="n">target_class</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mi">1</span><span class="o">-</span><span class="n">original_pred_1</span><span class="p">)</span>
+                <span class="k">return</span> <span class="n">target_class</span>
             <span class="k">elif</span> <span class="n">num_output_nodes</span> <span class="o">&gt;</span> <span class="mi">2</span><span class="p">:</span>
                 <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span>
                     <span class="s2">&quot;Desired class cannot be opposite if the number of classes is more than 2.&quot;</span><span class="p">)</span>
         <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">desired_class_input</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
-            <span class="k">if</span> <span class="n">desired_class_input</span> <span class="o">&gt;=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">desired_class_input</span> <span class="o">&lt;</span> <span class="n">num_output_nodes</span><span class="p">:</span>
+            <span class="k">if</span> <span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>   <span class="c1"># for DL models</span>
+                <span class="k">if</span> <span class="n">desired_class_input</span> <span class="ow">in</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">):</span>
+                    <span class="n">target_class</span> <span class="o">=</span> <span class="n">desired_class_input</span>
+                    <span class="k">return</span> <span class="n">target_class</span>
+                <span class="k">else</span><span class="p">:</span>
+                    <span class="k">raise</span> <span class="n">UserConfigValidationException</span><span class="p">(</span><span class="s2">&quot;Only 0, 1 are supported as desired class for binary classification!&quot;</span><span class="p">)</span>
+            <span class="k">elif</span> <span class="n">desired_class_input</span> <span class="o">&gt;=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">desired_class_input</span> <span class="o">&lt;</span> <span class="n">num_output_nodes</span><span class="p">:</span>
                 <span class="n">target_class</span> <span class="o">=</span> <span class="n">desired_class_input</span>
                 <span class="k">return</span> <span class="n">target_class</span>
             <span class="k">else</span><span class="p">:</span>
@@ -766,11 +790,15 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
         <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">model_outputs</span><span class="p">)):</span>
             <span class="n">pred</span> <span class="o">=</span> <span class="n">model_outputs</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
             <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
-                <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>  <span class="c1"># binary</span>
-                    <span class="n">pred_1</span> <span class="o">=</span> <span class="n">pred</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+                <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="ow">in</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">):</span>  <span class="c1"># binary</span>
+                    <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
+                        <span class="n">pred_1</span> <span class="o">=</span> <span class="n">pred</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+                    <span class="k">else</span><span class="p">:</span>
+                        <span class="n">pred_1</span> <span class="o">=</span> <span class="n">pred</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
                     <span class="n">validity</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span> <span class="k">if</span> \
                         <span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&lt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">)</span> <span class="ow">or</span>
                          <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">))</span> <span class="k">else</span> <span class="mi">0</span>
+
                 <span class="k">else</span><span class="p">:</span>  <span class="c1"># multiclass</span>
                     <span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">pred</span><span class="p">)</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span><span class="p">:</span>
                         <span class="n">validity</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span>
@@ -797,14 +825,14 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
                     <span class="n">target_cf_class</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_cf_class</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
             <span class="n">target_cf_class</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">target_cf_class</span><span class="p">)</span>
 
-            <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>  <span class="c1"># for tensorflow/pytorch models</span>
+            <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">model_score</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>  <span class="c1"># for tensorflow/pytorch models</span>
                 <span class="n">pred_1</span> <span class="o">=</span> <span class="n">model_score</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
                 <span class="n">validity</span> <span class="o">=</span> <span class="kc">True</span> <span class="k">if</span> \
                     <span class="p">((</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&lt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">)</span> <span class="ow">or</span>
                      <span class="p">(</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">))</span> <span class="k">else</span> <span class="kc">False</span>
                 <span class="k">return</span> <span class="n">validity</span>
-            <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>  <span class="c1"># binary</span>
-                <span class="n">pred_1</span> <span class="o">=</span> <span class="n">model_score</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">num_output_nodes</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+            <span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">model_score</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>  <span class="c1"># binary</span>
+                <span class="n">pred_1</span> <span class="o">=</span> <span class="n">model_score</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
                 <span class="n">validity</span> <span class="o">=</span> <span class="kc">True</span> <span class="k">if</span> \
                     <span class="p">((</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&lt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">)</span> <span class="ow">or</span>
                      <span class="p">(</span><span class="n">target_cf_class</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">pred_1</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">stopping_threshold</span><span class="p">))</span> <span class="k">else</span> <span class="kc">False</span>
@@ -822,7 +850,13 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
         <span class="n">model_output</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">model_scores</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">output_type</span><span class="p">)</span>
         <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">model_scores</span><span class="p">)):</span>
             <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
-                <span class="n">model_output</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
+                <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="s2">&quot;shape&quot;</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
+                    <span class="k">if</span> <span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
+                        <span class="n">model_output</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
+                    <span class="k">else</span><span class="p">:</span>
+                        <span class="n">model_output</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">])[</span><span class="mi">0</span><span class="p">]</span>
+                <span class="k">else</span><span class="p">:</span>  <span class="c1"># 1-D input</span>
+                    <span class="n">model_output</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
             <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Regressor</span><span class="p">:</span>
                 <span class="n">model_output</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">model_scores</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
         <span class="k">return</span> <span class="n">model_output</span></div>
@@ -853,7 +887,7 @@ <h1>Source code for dice_ml.explainer_interfaces.explainer_base</h1><div class="
         <span class="n">dataset_instance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">prepare_query_instance</span><span class="p">(</span>
             <span class="n">query_instance</span><span class="o">=</span><span class="n">data_df_copy</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">data_interface</span><span class="o">.</span><span class="n">feature_names</span><span class="p">])</span>
 
-        <span class="n">predictions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">dataset_instance</span><span class="p">)</span>
+        <span class="n">predictions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">dataset_instance</span><span class="p">,</span> <span class="n">model_score</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">flatten</span><span class="p">()</span>
         <span class="c1"># TODO: Is it okay to insert a column in the original dataframe with the predicted outcome? This is memory-efficient</span>
         <span class="n">data_df_copy</span><span class="p">[</span><span class="n">predicted_outcome_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">predictions</span>
 
diff --git a/docs/_modules/dice_ml/explainer_interfaces/feasible_base_vae.html b/docs/_modules/dice_ml/explainer_interfaces/feasible_base_vae.html
index 9d0202b8..476d8ab9 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/feasible_base_vae.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/feasible_base_vae.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.feasible_base_vae &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.feasible_base_vae &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/explainer_interfaces/feasible_model_approx.html b/docs/_modules/dice_ml/explainer_interfaces/feasible_model_approx.html
index 76a2bf64..a051bccd 100644
--- a/docs/_modules/dice_ml/explainer_interfaces/feasible_model_approx.html
+++ b/docs/_modules/dice_ml/explainer_interfaces/feasible_model_approx.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces.feasible_model_approx &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces.feasible_model_approx &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/model.html b/docs/_modules/dice_ml/model.html
index 0e616719..c05b3a03 100644
--- a/docs/_modules/dice_ml/model.html
+++ b/docs/_modules/dice_ml/model.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.model &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
         <script src="../../_static/jquery.js"></script>
         <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../_static/doctools.js"></script>
+        <script src="../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/model_interfaces/base_model.html b/docs/_modules/dice_ml/model_interfaces/base_model.html
index 091d017f..6d8be717 100644
--- a/docs/_modules/dice_ml/model_interfaces/base_model.html
+++ b/docs/_modules/dice_ml/model_interfaces/base_model.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.model_interfaces.base_model &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.model_interfaces.base_model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/model_interfaces/keras_tensorflow_model.html b/docs/_modules/dice_ml/model_interfaces/keras_tensorflow_model.html
index 2947e256..52987a71 100644
--- a/docs/_modules/dice_ml/model_interfaces/keras_tensorflow_model.html
+++ b/docs/_modules/dice_ml/model_interfaces/keras_tensorflow_model.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.model_interfaces.keras_tensorflow_model &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.model_interfaces.keras_tensorflow_model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -102,7 +104,7 @@ <h1>Source code for dice_ml.model_interfaces.keras_tensorflow_model</h1><div cla
 <span class="sd">                        dictionary of kw_args, by default.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
 
-        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_path</span><span class="p">,</span> <span class="n">backend</span><span class="p">)</span>
+        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_path</span><span class="p">,</span> <span class="n">backend</span><span class="p">,</span> <span class="n">func</span><span class="p">,</span> <span class="n">kw_args</span><span class="p">)</span>
 
 <div class="viewcode-block" id="KerasTensorFlowModel.load_model"><a class="viewcode-back" href="../../../dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.load_model">[docs]</a>    <span class="k">def</span> <span class="nf">load_model</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_path</span> <span class="o">!=</span> <span class="s1">&#39;&#39;</span><span class="p">:</span>
@@ -115,9 +117,8 @@ <h1>Source code for dice_ml.model_interfaces.keras_tensorflow_model</h1><div cla
 <span class="sd">        :param training: to determine training mode in TF2.</span>
 <span class="sd">        :param transform_data: boolean to indicate if data transformation is required.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
-        <span class="k">if</span> <span class="n">transform_data</span><span class="p">:</span>
-            <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
-
+        <span class="k">if</span> <span class="n">transform_data</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">tf</span><span class="o">.</span><span class="n">is_tensor</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">):</span>
+            <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">tf</span><span class="o">.</span><span class="n">constant</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">(),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">tf</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">backend</span> <span class="o">==</span> <span class="s1">&#39;TF2&#39;</span><span class="p">:</span>
             <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">,</span> <span class="n">training</span><span class="o">=</span><span class="n">training</span><span class="p">)</span>
         <span class="k">else</span><span class="p">:</span>
diff --git a/docs/_modules/dice_ml/model_interfaces/pytorch_model.html b/docs/_modules/dice_ml/model_interfaces/pytorch_model.html
index d5669ed7..368791f4 100644
--- a/docs/_modules/dice_ml/model_interfaces/pytorch_model.html
+++ b/docs/_modules/dice_ml/model_interfaces/pytorch_model.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.model_interfaces.pytorch_model &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.model_interfaces.pytorch_model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -83,8 +85,10 @@
   <h1>Source code for dice_ml.model_interfaces.pytorch_model</h1><div class="highlight"><pre>
 <span></span><span class="sd">&quot;&quot;&quot;Module containing an interface to trained PyTorch model.&quot;&quot;&quot;</span>
 
+<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">torch</span>
 
+<span class="kn">from</span> <span class="nn">dice_ml.constants</span> <span class="kn">import</span> <span class="n">ModelTypes</span>
 <span class="kn">from</span> <span class="nn">dice_ml.model_interfaces.base_model</span> <span class="kn">import</span> <span class="n">BaseModel</span>
 
 
@@ -101,22 +105,30 @@ <h1>Source code for dice_ml.model_interfaces.pytorch_model</h1><div class="highl
 <span class="sd">                        dictionary of kw_args, by default.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
 
-        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_path</span><span class="p">,</span> <span class="n">backend</span><span class="p">)</span>
+        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_path</span><span class="p">,</span> <span class="n">backend</span><span class="p">,</span> <span class="n">func</span><span class="p">,</span> <span class="n">kw_args</span><span class="p">)</span>
 
 <div class="viewcode-block" id="PyTorchModel.load_model"><a class="viewcode-back" href="../../../dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.load_model">[docs]</a>    <span class="k">def</span> <span class="nf">load_model</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_path</span> <span class="o">!=</span> <span class="s1">&#39;&#39;</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model_path</span><span class="p">)</span></div>
 
-<div class="viewcode-block" id="PyTorchModel.get_output"><a class="viewcode-back" href="../../../dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output">[docs]</a>    <span class="k">def</span> <span class="nf">get_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_tensor</span><span class="p">,</span> <span class="n">transform_data</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
+<div class="viewcode-block" id="PyTorchModel.get_output"><a class="viewcode-back" href="../../../dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output">[docs]</a>    <span class="k">def</span> <span class="nf">get_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_instance</span><span class="p">,</span> <span class="n">model_score</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+                   <span class="n">transform_data</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">out_tensor</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
         <span class="sd">&quot;&quot;&quot;returns prediction probabilities</span>
 
 <span class="sd">        :param input_tensor: test input.</span>
 <span class="sd">        :param transform_data: boolean to indicate if data transformation is required.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
+        <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">input_instance</span>
         <span class="k">if</span> <span class="n">transform_data</span><span class="p">:</span>
-            <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">))</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
-
-        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span></div>
+            <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">())</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
+        <span class="k">if</span> <span class="ow">not</span> <span class="n">torch</span><span class="o">.</span><span class="n">is_tensor</span><span class="p">(</span><span class="n">input_instance</span><span class="p">):</span>
+            <span class="n">input_tensor</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">tensor</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">input_instance</span><span class="p">)</span><span class="o">.</span><span class="n">to_numpy</span><span class="p">())</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
+        <span class="n">out</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">input_tensor</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
+        <span class="k">if</span> <span class="ow">not</span> <span class="n">out_tensor</span><span class="p">:</span>
+            <span class="n">out</span> <span class="o">=</span> <span class="n">out</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
+        <span class="k">if</span> <span class="n">model_score</span> <span class="ow">is</span> <span class="kc">False</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_type</span> <span class="o">==</span> <span class="n">ModelTypes</span><span class="o">.</span><span class="n">Classifier</span><span class="p">:</span>
+            <span class="n">out</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">round</span><span class="p">(</span><span class="n">out</span><span class="p">)</span>  <span class="c1"># TODO need to generalize for n-class classifier</span>
+        <span class="k">return</span> <span class="n">out</span></div>
 
 <div class="viewcode-block" id="PyTorchModel.set_eval_mode"><a class="viewcode-back" href="../../../dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.set_eval_mode">[docs]</a>    <span class="k">def</span> <span class="nf">set_eval_mode</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span></div>
diff --git a/docs/_modules/dice_ml/utils/exception.html b/docs/_modules/dice_ml/utils/exception.html
index a73c0fbf..01ed4d08 100644
--- a/docs/_modules/dice_ml/utils/exception.html
+++ b/docs/_modules/dice_ml/utils/exception.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils.exception &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils.exception &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/utils/helpers.html b/docs/_modules/dice_ml/utils/helpers.html
index b8eb5a7f..b513effc 100644
--- a/docs/_modules/dice_ml/utils/helpers.html
+++ b/docs/_modules/dice_ml/utils/helpers.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils.helpers &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils.helpers &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -85,12 +87,16 @@ <h1>Source code for dice_ml.utils.helpers</h1><div class="highlight"><pre>
 <span class="sd">This module containts helper functions to load data and get meta deta.</span>
 <span class="sd">&quot;&quot;&quot;</span>
 <span class="kn">import</span> <span class="nn">os</span>
+<span class="kn">import</span> <span class="nn">pickle</span>
 <span class="kn">import</span> <span class="nn">shutil</span>
 
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
+<span class="kn">from</span> <span class="nn">sklearn.compose</span> <span class="kn">import</span> <span class="n">ColumnTransformer</span>
+<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <span class="n">RandomForestClassifier</span>
 <span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">train_test_split</span>
-<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">FunctionTransformer</span>
+<span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <span class="n">Pipeline</span>
+<span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">FunctionTransformer</span><span class="p">,</span> <span class="n">OneHotEncoder</span>
 
 <span class="kn">import</span> <span class="nn">dice_ml</span>
 
@@ -167,6 +173,31 @@ <h1>Source code for dice_ml.utils.helpers</h1><div class="highlight"><pre>
     <span class="k">return</span> <span class="n">adult_data</span></div>
 
 
+<div class="viewcode-block" id="save_adult_income_model"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.save_adult_income_model">[docs]</a><span class="k">def</span> <span class="nf">save_adult_income_model</span><span class="p">(</span><span class="n">modelpath</span><span class="p">,</span> <span class="n">test_fraction</span><span class="o">=</span><span class="mf">0.2</span><span class="p">,</span> <span class="n">random_state</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
+    <span class="n">dataset</span> <span class="o">=</span> <span class="n">load_adult_income_dataset</span><span class="p">()</span>
+    <span class="n">target</span> <span class="o">=</span> <span class="n">dataset</span><span class="p">[</span><span class="s2">&quot;income&quot;</span><span class="p">]</span>
+    <span class="n">train_dataset</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span>
+                                                    <span class="n">target</span><span class="p">,</span>
+                                                    <span class="n">test_size</span><span class="o">=</span><span class="n">test_fraction</span><span class="p">,</span>
+                                                    <span class="n">random_state</span><span class="o">=</span><span class="n">random_state</span><span class="p">,</span>
+                                                    <span class="n">stratify</span><span class="o">=</span><span class="n">target</span><span class="p">)</span>
+    <span class="n">x_train</span> <span class="o">=</span> <span class="n">train_dataset</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="s1">&#39;income&#39;</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
+    <span class="n">numerical</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;age&quot;</span><span class="p">,</span> <span class="s2">&quot;hours_per_week&quot;</span><span class="p">]</span>
+    <span class="n">categorical</span> <span class="o">=</span> <span class="n">x_train</span><span class="o">.</span><span class="n">columns</span><span class="o">.</span><span class="n">difference</span><span class="p">(</span><span class="n">numerical</span><span class="p">)</span>
+
+    <span class="n">categorical_transformer</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">(</span><span class="n">steps</span><span class="o">=</span><span class="p">[</span>
+        <span class="p">(</span><span class="s1">&#39;onehot&#39;</span><span class="p">,</span> <span class="n">OneHotEncoder</span><span class="p">(</span><span class="n">handle_unknown</span><span class="o">=</span><span class="s1">&#39;ignore&#39;</span><span class="p">))])</span>
+
+    <span class="n">transformations</span> <span class="o">=</span> <span class="n">ColumnTransformer</span><span class="p">(</span>
+        <span class="n">transformers</span><span class="o">=</span><span class="p">[</span>
+            <span class="p">(</span><span class="s1">&#39;cat&#39;</span><span class="p">,</span> <span class="n">categorical_transformer</span><span class="p">,</span> <span class="n">categorical</span><span class="p">)])</span>
+
+    <span class="n">clf</span> <span class="o">=</span> <span class="n">Pipeline</span><span class="p">(</span><span class="n">steps</span><span class="o">=</span><span class="p">[(</span><span class="s1">&#39;preprocessor&#39;</span><span class="p">,</span> <span class="n">transformations</span><span class="p">),</span>
+                          <span class="p">(</span><span class="s1">&#39;classifier&#39;</span><span class="p">,</span> <span class="n">RandomForestClassifier</span><span class="p">())])</span>
+    <span class="n">model</span> <span class="o">=</span> <span class="n">clf</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">x_train</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
+    <span class="n">pickle</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="nb">open</span><span class="p">(</span><span class="n">modelpath</span><span class="p">,</span> <span class="s1">&#39;wb&#39;</span><span class="p">))</span></div>
+
+
 <div class="viewcode-block" id="load_custom_testing_dataset"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.load_custom_testing_dataset">[docs]</a><span class="k">def</span> <span class="nf">load_custom_testing_dataset</span><span class="p">():</span>
     <span class="n">data</span> <span class="o">=</span> <span class="p">[[</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="s1">&#39;b&#39;</span><span class="p">,</span> <span class="mi">10000</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="s1">&#39;c&#39;</span><span class="p">,</span> <span class="mi">14</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="s1">&#39;a&#39;</span><span class="p">,</span> <span class="mi">88</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="s1">&#39;c&#39;</span><span class="p">,</span> <span class="mi">14</span><span class="p">,</span> <span class="mi">0</span><span class="p">]]</span>
     <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">columns</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;Categorical&#39;</span><span class="p">,</span> <span class="s1">&#39;Numerical&#39;</span><span class="p">,</span> <span class="s1">&#39;Outcome&#39;</span><span class="p">])</span></div>
@@ -199,7 +230,7 @@ <h1>Source code for dice_ml.utils.helpers</h1><div class="highlight"><pre>
 
 <div class="viewcode-block" id="get_adult_income_modelpath"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.get_adult_income_modelpath">[docs]</a><span class="k">def</span> <span class="nf">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="s1">&#39;TF1&#39;</span><span class="p">):</span>
     <span class="n">pkg_path</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">__path__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
-    <span class="n">model_ext</span> <span class="o">=</span> <span class="s1">&#39;.h5&#39;</span> <span class="k">if</span> <span class="s1">&#39;TF&#39;</span> <span class="ow">in</span> <span class="n">backend</span> <span class="k">else</span> <span class="s1">&#39;.pth&#39;</span>
+    <span class="n">model_ext</span> <span class="o">=</span> <span class="s1">&#39;.h5&#39;</span> <span class="k">if</span> <span class="s1">&#39;TF&#39;</span> <span class="ow">in</span> <span class="n">backend</span> <span class="k">else</span> <span class="p">(</span><span class="s1">&#39;.pth&#39;</span> <span class="k">if</span> <span class="n">backend</span> <span class="o">==</span> <span class="s1">&#39;PYT&#39;</span> <span class="k">else</span> <span class="s1">&#39;.pkl&#39;</span><span class="p">)</span>
     <span class="n">modelpath</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">pkg_path</span><span class="p">,</span> <span class="s1">&#39;utils&#39;</span><span class="p">,</span> <span class="s1">&#39;sample_trained_models&#39;</span><span class="p">,</span> <span class="s1">&#39;adult&#39;</span><span class="o">+</span><span class="n">model_ext</span><span class="p">)</span>
     <span class="k">return</span> <span class="n">modelpath</span></div>
 
@@ -302,7 +333,11 @@ <h1>Source code for dice_ml.utils.helpers</h1><div class="highlight"><pre>
 
 <div class="viewcode-block" id="ohe_min_max_transformation"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.ohe_min_max_transformation">[docs]</a><span class="k">def</span> <span class="nf">ohe_min_max_transformation</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">data_interface</span><span class="p">):</span>
     <span class="sd">&quot;&quot;&quot;the data is one-hot-encoded and min-max normalized and fed to the ML model&quot;&quot;&quot;</span>
-    <span class="k">return</span> <span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="o">.</span><span class="n">values</span></div>
+    <span class="k">return</span> <span class="n">data_interface</span><span class="o">.</span><span class="n">get_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">data</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="inverse_ohe_min_max_transformation"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.inverse_ohe_min_max_transformation">[docs]</a><span class="k">def</span> <span class="nf">inverse_ohe_min_max_transformation</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">data_interface</span><span class="p">):</span>
+    <span class="k">return</span> <span class="n">data_interface</span><span class="o">.</span><span class="n">get_inverse_ohe_min_max_normalized_data</span><span class="p">(</span><span class="n">data</span><span class="p">)</span></div>
 
 
 <div class="viewcode-block" id="DataTransfomer"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer">[docs]</a><span class="k">class</span> <span class="nc">DataTransfomer</span><span class="p">:</span>
@@ -322,7 +357,13 @@ <h1>Source code for dice_ml.utils.helpers</h1><div class="highlight"><pre>
 
 <div class="viewcode-block" id="DataTransfomer.initialize_transform_func"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.initialize_transform_func">[docs]</a>    <span class="k">def</span> <span class="nf">initialize_transform_func</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">func</span> <span class="o">==</span> <span class="s1">&#39;ohe-min-max&#39;</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">data_transformer</span> <span class="o">=</span> <span class="n">FunctionTransformer</span><span class="p">(</span><span class="n">func</span><span class="o">=</span><span class="n">ohe_min_max_transformation</span><span class="p">,</span> <span class="n">kw_args</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">kw_args</span><span class="p">,</span> <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">data_transformer</span> <span class="o">=</span> <span class="n">FunctionTransformer</span><span class="p">(</span>
+                    <span class="n">func</span><span class="o">=</span><span class="n">ohe_min_max_transformation</span><span class="p">,</span>
+                    <span class="n">inverse_func</span><span class="o">=</span><span class="n">inverse_ohe_min_max_transformation</span><span class="p">,</span>
+                    <span class="n">check_inverse</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+                    <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+                    <span class="n">kw_args</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">kw_args</span><span class="p">,</span>
+                    <span class="n">inv_kw_args</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">kw_args</span><span class="p">)</span>
         <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">func</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
             <span class="c1"># identity transformation</span>
             <span class="c1"># add more ready-to-use transformers (such as label-encoding) in elif loops.</span>
diff --git a/docs/_modules/dice_ml/utils/sample_architecture/vae_model.html b/docs/_modules/dice_ml/utils/sample_architecture/vae_model.html
index ecb8f0c0..5aa7be77 100644
--- a/docs/_modules/dice_ml/utils/sample_architecture/vae_model.html
+++ b/docs/_modules/dice_ml/utils/sample_architecture/vae_model.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils.sample_architecture.vae_model &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils.sample_architecture.vae_model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../../" id="documentation_options" src="../../../../_static/documentation_options.js"></script>
         <script src="../../../../_static/jquery.js"></script>
         <script src="../../../../_static/underscore.js"></script>
+        <script src="../../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../../_static/doctools.js"></script>
+        <script src="../../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/_modules/dice_ml/utils/serialize.html b/docs/_modules/dice_ml/utils/serialize.html
index 94acd05d..fd132f05 100644
--- a/docs/_modules/dice_ml/utils/serialize.html
+++ b/docs/_modules/dice_ml/utils/serialize.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils.serialize &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils.serialize &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
         <script src="../../../_static/jquery.js"></script>
         <script src="../../../_static/underscore.js"></script>
+        <script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../../../_static/doctools.js"></script>
+        <script src="../../../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../../../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../../../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -84,6 +86,7 @@ <h1>Source code for dice_ml.utils.serialize</h1><div class="highlight"><pre>
 <div class="viewcode-block" id="DummyDataInterface"><a class="viewcode-back" href="../../../dice_ml.utils.html#dice_ml.utils.serialize.DummyDataInterface">[docs]</a><span></span><span class="k">class</span> <span class="nc">DummyDataInterface</span><span class="p">:</span>
     <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">outcome_name</span><span class="p">,</span> <span class="n">data_df</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">outcome_name</span> <span class="o">=</span> <span class="n">outcome_name</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">data_df</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="k">if</span> <span class="n">data_df</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">data_df</span> <span class="o">=</span> <span class="n">data_df</span>
 
diff --git a/docs/_modules/index.html b/docs/_modules/index.html
index 6ab59f55..4fa69913 100644
--- a/docs/_modules/index.html
+++ b/docs/_modules/index.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Overview: module code &mdash; DiCE 0.8 documentation</title>
+  <title>Overview: module code &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../genindex.html" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -102,6 +104,7 @@ <h1>All modules for which code is available</h1>
 <li><a href="dice_ml/model_interfaces/pytorch_model.html">dice_ml.model_interfaces.pytorch_model</a></li>
 <li><a href="dice_ml/utils/exception.html">dice_ml.utils.exception</a></li>
 <li><a href="dice_ml/utils/helpers.html">dice_ml.utils.helpers</a></li>
+<li><a href="dice_ml/utils/neuralnetworks.html">dice_ml.utils.neuralnetworks</a></li>
 <li><a href="dice_ml/utils/sample_architecture/vae_model.html">dice_ml.utils.sample_architecture.vae_model</a></li>
 <li><a href="dice_ml/utils/serialize.html">dice_ml.utils.serialize</a></li>
 </ul>
diff --git a/docs/_static/basic.css b/docs/_static/basic.css
index bf18350b..eeb0519a 100644
--- a/docs/_static/basic.css
+++ b/docs/_static/basic.css
@@ -222,7 +222,7 @@ table.modindextable td {
 /* -- general body styles --------------------------------------------------- */
 
 div.body {
-    min-width: 450px;
+    min-width: 360px;
     max-width: 800px;
 }
 
@@ -236,7 +236,6 @@ div.body p, div.body dd, div.body li, div.body blockquote {
 a.headerlink {
     visibility: hidden;
 }
-
 a.brackets:before,
 span.brackets > a:before{
     content: "[";
@@ -247,6 +246,7 @@ span.brackets > a:after {
     content: "]";
 }
 
+
 h1:hover > a.headerlink,
 h2:hover > a.headerlink,
 h3:hover > a.headerlink,
@@ -334,13 +334,11 @@ aside.sidebar {
 p.sidebar-title {
     font-weight: bold;
 }
-
 div.admonition, div.topic, blockquote {
     clear: left;
 }
 
 /* -- topics ---------------------------------------------------------------- */
-
 div.topic {
     border: 1px solid #ccc;
     padding: 7px;
@@ -428,10 +426,6 @@ table.docutils td, table.docutils th {
     border-bottom: 1px solid #aaa;
 }
 
-table.footnote td, table.footnote th {
-    border: 0 !important;
-}
-
 th {
     text-align: left;
     padding-right: 5px;
@@ -614,7 +608,6 @@ ol.simple p,
 ul.simple p {
     margin-bottom: 0;
 }
-
 dl.footnote > dt,
 dl.citation > dt {
     float: left;
@@ -643,11 +636,11 @@ dl.field-list > dt {
     padding-left: 0.5em;
     padding-right: 5px;
 }
-
 dl.field-list > dt:after {
     content: ":";
 }
 
+
 dl.field-list > dd {
     padding-left: 0.5em;
     margin-top: 0em;
diff --git a/docs/_static/doctools.js b/docs/_static/doctools.js
index e509e483..527b876c 100644
--- a/docs/_static/doctools.js
+++ b/docs/_static/doctools.js
@@ -2,325 +2,155 @@
  * doctools.js
  * ~~~~~~~~~~~
  *
- * Sphinx JavaScript utilities for all documentation.
+ * Base JavaScript utilities for all Sphinx HTML documentation.
  *
  * :copyright: Copyright 2007-2022 by the Sphinx team, see AUTHORS.
  * :license: BSD, see LICENSE for details.
  *
  */
-
-/**
- * select a different prefix for underscore
- */
-$u = _.noConflict();
-
-/**
- * make the code below compatible with browsers without
- * an installed firebug like debugger
-if (!window.console || !console.firebug) {
-  var names = ["log", "debug", "info", "warn", "error", "assert", "dir",
-    "dirxml", "group", "groupEnd", "time", "timeEnd", "count", "trace",
-    "profile", "profileEnd"];
-  window.console = {};
-  for (var i = 0; i < names.length; ++i)
-    window.console[names[i]] = function() {};
-}
- */
-
-/**
- * small helper function to urldecode strings
- *
- * See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/decodeURIComponent#Decoding_query_parameters_from_a_URL
- */
-jQuery.urldecode = function(x) {
-  if (!x) {
-    return x
-  }
-  return decodeURIComponent(x.replace(/\+/g, ' '));
-};
-
-/**
- * small helper function to urlencode strings
- */
-jQuery.urlencode = encodeURIComponent;
-
-/**
- * This function returns the parsed url parameters of the
- * current request. Multiple values per key are supported,
- * it will always return arrays of strings for the value parts.
- */
-jQuery.getQueryParameters = function(s) {
-  if (typeof s === 'undefined')
-    s = document.location.search;
-  var parts = s.substr(s.indexOf('?') + 1).split('&');
-  var result = {};
-  for (var i = 0; i < parts.length; i++) {
-    var tmp = parts[i].split('=', 2);
-    var key = jQuery.urldecode(tmp[0]);
-    var value = jQuery.urldecode(tmp[1]);
-    if (key in result)
-      result[key].push(value);
-    else
-      result[key] = [value];
+"use strict";
+
+const BLACKLISTED_KEY_CONTROL_ELEMENTS = new Set([
+  "TEXTAREA",
+  "INPUT",
+  "SELECT",
+  "BUTTON",
+]);
+
+const _ready = (callback) => {
+  if (document.readyState !== "loading") {
+    callback();
+  } else {
+    document.addEventListener("DOMContentLoaded", callback);
   }
-  return result;
 };
 
-/**
- * highlight a given string on a jquery object by wrapping it in
- * span elements with the given class name.
- */
-jQuery.fn.highlightText = function(text, className) {
-  function highlight(node, addItems) {
-    if (node.nodeType === 3) {
-      var val = node.nodeValue;
-      var pos = val.toLowerCase().indexOf(text);
-      if (pos >= 0 &&
-          !jQuery(node.parentNode).hasClass(className) &&
-          !jQuery(node.parentNode).hasClass("nohighlight")) {
-        var span;
-        var isInSVG = jQuery(node).closest("body, svg, foreignObject").is("svg");
-        if (isInSVG) {
-          span = document.createElementNS("http://www.w3.org/2000/svg", "tspan");
-        } else {
-          span = document.createElement("span");
-          span.className = className;
-        }
-        span.appendChild(document.createTextNode(val.substr(pos, text.length)));
-        node.parentNode.insertBefore(span, node.parentNode.insertBefore(
-          document.createTextNode(val.substr(pos + text.length)),
-          node.nextSibling));
-        node.nodeValue = val.substr(0, pos);
-        if (isInSVG) {
-          var rect = document.createElementNS("http://www.w3.org/2000/svg", "rect");
-          var bbox = node.parentElement.getBBox();
-          rect.x.baseVal.value = bbox.x;
-          rect.y.baseVal.value = bbox.y;
-          rect.width.baseVal.value = bbox.width;
-          rect.height.baseVal.value = bbox.height;
-          rect.setAttribute('class', className);
-          addItems.push({
-              "parent": node.parentNode,
-              "target": rect});
-        }
-      }
-    }
-    else if (!jQuery(node).is("button, select, textarea")) {
-      jQuery.each(node.childNodes, function() {
-        highlight(this, addItems);
-      });
-    }
-  }
-  var addItems = [];
-  var result = this.each(function() {
-    highlight(this, addItems);
-  });
-  for (var i = 0; i < addItems.length; ++i) {
-    jQuery(addItems[i].parent).before(addItems[i].target);
-  }
-  return result;
-};
-
-/*
- * backward compatibility for jQuery.browser
- * This will be supported until firefox bug is fixed.
- */
-if (!jQuery.browser) {
-  jQuery.uaMatch = function(ua) {
-    ua = ua.toLowerCase();
-
-    var match = /(chrome)[ \/]([\w.]+)/.exec(ua) ||
-      /(webkit)[ \/]([\w.]+)/.exec(ua) ||
-      /(opera)(?:.*version|)[ \/]([\w.]+)/.exec(ua) ||
-      /(msie) ([\w.]+)/.exec(ua) ||
-      ua.indexOf("compatible") < 0 && /(mozilla)(?:.*? rv:([\w.]+)|)/.exec(ua) ||
-      [];
-
-    return {
-      browser: match[ 1 ] || "",
-      version: match[ 2 ] || "0"
-    };
-  };
-  jQuery.browser = {};
-  jQuery.browser[jQuery.uaMatch(navigator.userAgent).browser] = true;
-}
-
 /**
  * Small JavaScript module for the documentation.
  */
-var Documentation = {
-
-  init : function() {
-    this.fixFirefoxAnchorBug();
-    this.highlightSearchWords();
-    this.initIndexTable();
-    if (DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) {
-      this.initOnKeyListeners();
-    }
+const Documentation = {
+  init: () => {
+    Documentation.initDomainIndexTable();
+    Documentation.initOnKeyListeners();
   },
 
   /**
    * i18n support
    */
-  TRANSLATIONS : {},
-  PLURAL_EXPR : function(n) { return n === 1 ? 0 : 1; },
-  LOCALE : 'unknown',
+  TRANSLATIONS: {},
+  PLURAL_EXPR: (n) => (n === 1 ? 0 : 1),
+  LOCALE: "unknown",
 
   // gettext and ngettext don't access this so that the functions
   // can safely bound to a different name (_ = Documentation.gettext)
-  gettext : function(string) {
-    var translated = Documentation.TRANSLATIONS[string];
-    if (typeof translated === 'undefined')
-      return string;
-    return (typeof translated === 'string') ? translated : translated[0];
+  gettext: (string) => {
+    const translated = Documentation.TRANSLATIONS[string];
+    switch (typeof translated) {
+      case "undefined":
+        return string; // no translation
+      case "string":
+        return translated; // translation exists
+      default:
+        return translated[0]; // (singular, plural) translation tuple exists
+    }
   },
 
-  ngettext : function(singular, plural, n) {
-    var translated = Documentation.TRANSLATIONS[singular];
-    if (typeof translated === 'undefined')
-      return (n == 1) ? singular : plural;
-    return translated[Documentation.PLURALEXPR(n)];
+  ngettext: (singular, plural, n) => {
+    const translated = Documentation.TRANSLATIONS[singular];
+    if (typeof translated !== "undefined")
+      return translated[Documentation.PLURAL_EXPR(n)];
+    return n === 1 ? singular : plural;
   },
 
-  addTranslations : function(catalog) {
-    for (var key in catalog.messages)
-      this.TRANSLATIONS[key] = catalog.messages[key];
-    this.PLURAL_EXPR = new Function('n', 'return +(' + catalog.plural_expr + ')');
-    this.LOCALE = catalog.locale;
+  addTranslations: (catalog) => {
+    Object.assign(Documentation.TRANSLATIONS, catalog.messages);
+    Documentation.PLURAL_EXPR = new Function(
+      "n",
+      `return (${catalog.plural_expr})`
+    );
+    Documentation.LOCALE = catalog.locale;
   },
 
   /**
-   * add context elements like header anchor links
+   * helper function to focus on search bar
    */
-  addContextElements : function() {
-    $('div[id] > :header:first').each(function() {
-      $('<a class="headerlink">\u00B6</a>').
-      attr('href', '#' + this.id).
-      attr('title', _('Permalink to this headline')).
-      appendTo(this);
-    });
-    $('dt[id]').each(function() {
-      $('<a class="headerlink">\u00B6</a>').
-      attr('href', '#' + this.id).
-      attr('title', _('Permalink to this definition')).
-      appendTo(this);
-    });
+  focusSearchBar: () => {
+    document.querySelectorAll("input[name=q]")[0]?.focus();
   },
 
   /**
-   * workaround a firefox stupidity
-   * see: https://bugzilla.mozilla.org/show_bug.cgi?id=645075
+   * Initialise the domain index toggle buttons
    */
-  fixFirefoxAnchorBug : function() {
-    if (document.location.hash && $.browser.mozilla)
-      window.setTimeout(function() {
-        document.location.href += '';
-      }, 10);
-  },
-
-  /**
-   * highlight the search words provided in the url in the text
-   */
-  highlightSearchWords : function() {
-    var params = $.getQueryParameters();
-    var terms = (params.highlight) ? params.highlight[0].split(/\s+/) : [];
-    if (terms.length) {
-      var body = $('div.body');
-      if (!body.length) {
-        body = $('body');
+  initDomainIndexTable: () => {
+    const toggler = (el) => {
+      const idNumber = el.id.substr(7);
+      const toggledRows = document.querySelectorAll(`tr.cg-${idNumber}`);
+      if (el.src.substr(-9) === "minus.png") {
+        el.src = `${el.src.substr(0, el.src.length - 9)}plus.png`;
+        toggledRows.forEach((el) => (el.style.display = "none"));
+      } else {
+        el.src = `${el.src.substr(0, el.src.length - 8)}minus.png`;
+        toggledRows.forEach((el) => (el.style.display = ""));
       }
-      window.setTimeout(function() {
-        $.each(terms, function() {
-          body.highlightText(this.toLowerCase(), 'highlighted');
-        });
-      }, 10);
-      $('<p class="highlight-link"><a href="javascript:Documentation.' +
-        'hideSearchWords()">' + _('Hide Search Matches') + '</a></p>')
-          .appendTo($('#searchbox'));
-    }
-  },
-
-  /**
-   * init the domain index toggle buttons
-   */
-  initIndexTable : function() {
-    var togglers = $('img.toggler').click(function() {
-      var src = $(this).attr('src');
-      var idnum = $(this).attr('id').substr(7);
-      $('tr.cg-' + idnum).toggle();
-      if (src.substr(-9) === 'minus.png')
-        $(this).attr('src', src.substr(0, src.length-9) + 'plus.png');
-      else
-        $(this).attr('src', src.substr(0, src.length-8) + 'minus.png');
-    }).css('display', '');
-    if (DOCUMENTATION_OPTIONS.COLLAPSE_INDEX) {
-        togglers.click();
-    }
-  },
+    };
 
-  /**
-   * helper function to hide the search marks again
-   */
-  hideSearchWords : function() {
-    $('#searchbox .highlight-link').fadeOut(300);
-    $('span.highlighted').removeClass('highlighted');
-    var url = new URL(window.location);
-    url.searchParams.delete('highlight');
-    window.history.replaceState({}, '', url);
+    const togglerElements = document.querySelectorAll("img.toggler");
+    togglerElements.forEach((el) =>
+      el.addEventListener("click", (event) => toggler(event.currentTarget))
+    );
+    togglerElements.forEach((el) => (el.style.display = ""));
+    if (DOCUMENTATION_OPTIONS.COLLAPSE_INDEX) togglerElements.forEach(toggler);
   },
 
-  /**
-   * make the url absolute
-   */
-  makeURL : function(relativeURL) {
-    return DOCUMENTATION_OPTIONS.URL_ROOT + '/' + relativeURL;
-  },
-
-  /**
-   * get the current relative url
-   */
-  getCurrentURL : function() {
-    var path = document.location.pathname;
-    var parts = path.split(/\//);
-    $.each(DOCUMENTATION_OPTIONS.URL_ROOT.split(/\//), function() {
-      if (this === '..')
-        parts.pop();
-    });
-    var url = parts.join('/');
-    return path.substring(url.lastIndexOf('/') + 1, path.length - 1);
-  },
-
-  initOnKeyListeners: function() {
-    $(document).keydown(function(event) {
-      var activeElementType = document.activeElement.tagName;
-      // don't navigate when in search box, textarea, dropdown or button
-      if (activeElementType !== 'TEXTAREA' && activeElementType !== 'INPUT' && activeElementType !== 'SELECT'
-          && activeElementType !== 'BUTTON' && !event.altKey && !event.ctrlKey && !event.metaKey
-          && !event.shiftKey) {
-        switch (event.keyCode) {
-          case 37: // left
-            var prevHref = $('link[rel="prev"]').prop('href');
-            if (prevHref) {
-              window.location.href = prevHref;
-              return false;
+  initOnKeyListeners: () => {
+    // only install a listener if it is really needed
+    if (
+      !DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS &&
+      !DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS
+    )
+      return;
+
+    document.addEventListener("keydown", (event) => {
+      // bail for input elements
+      if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return;
+      // bail with special keys
+      if (event.altKey || event.ctrlKey || event.metaKey) return;
+
+      if (!event.shiftKey) {
+        switch (event.key) {
+          case "ArrowLeft":
+            if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
+
+            const prevLink = document.querySelector('link[rel="prev"]');
+            if (prevLink && prevLink.href) {
+              window.location.href = prevLink.href;
+              event.preventDefault();
             }
             break;
-          case 39: // right
-            var nextHref = $('link[rel="next"]').prop('href');
-            if (nextHref) {
-              window.location.href = nextHref;
-              return false;
+          case "ArrowRight":
+            if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
+
+            const nextLink = document.querySelector('link[rel="next"]');
+            if (nextLink && nextLink.href) {
+              window.location.href = nextLink.href;
+              event.preventDefault();
             }
             break;
         }
       }
+
+      // some keyboard layouts may need Shift to get /
+      switch (event.key) {
+        case "/":
+          if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) break;
+          Documentation.focusSearchBar();
+          event.preventDefault();
+      }
     });
-  }
+  },
 };
 
 // quick alias for translations
-_ = Documentation.gettext;
+const _ = Documentation.gettext;
 
-$(document).ready(function() {
-  Documentation.init();
-});
+_ready(Documentation.init);
diff --git a/docs/_static/documentation_options.js b/docs/_static/documentation_options.js
index f788b8b0..2088af8d 100644
--- a/docs/_static/documentation_options.js
+++ b/docs/_static/documentation_options.js
@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '0.8',
+    VERSION: '0.9',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',
@@ -8,5 +8,7 @@ var DOCUMENTATION_OPTIONS = {
     LINK_SUFFIX: '.html',
     HAS_SOURCE: true,
     SOURCELINK_SUFFIX: '.txt',
-    NAVIGATION_WITH_KEYS: false
+    NAVIGATION_WITH_KEYS: false,
+    SHOW_SEARCH_SUMMARY: true,
+    ENABLE_SEARCH_SHORTCUTS: true,
 };
\ No newline at end of file
diff --git a/docs/_static/jquery.js b/docs/_static/jquery.js
index b0614034..c4c6022f 100644
--- a/docs/_static/jquery.js
+++ b/docs/_static/jquery.js
@@ -1,2 +1,2 @@
-/*! jQuery v3.5.1 | (c) JS Foundation and other contributors | jquery.org/license */
-!function(e,t){"use strict";"object"==typeof module&&"object"==typeof module.exports?module.exports=e.document?t(e,!0):function(e){if(!e.document)throw new Error("jQuery requires a window with a document");return t(e)}:t(e)}("undefined"!=typeof window?window:this,function(C,e){"use strict";var t=[],r=Object.getPrototypeOf,s=t.slice,g=t.flat?function(e){return t.flat.call(e)}:function(e){return t.concat.apply([],e)},u=t.push,i=t.indexOf,n={},o=n.toString,v=n.hasOwnProperty,a=v.toString,l=a.call(Object),y={},m=function(e){return"function"==typeof e&&"number"!=typeof e.nodeType},x=function(e){return null!=e&&e===e.window},E=C.document,c={type:!0,src:!0,nonce:!0,noModule:!0};function b(e,t,n){var r,i,o=(n=n||E).createElement("script");if(o.text=e,t)for(r in c)(i=t[r]||t.getAttribute&&t.getAttribute(r))&&o.setAttribute(r,i);n.head.appendChild(o).parentNode.removeChild(o)}function w(e){return null==e?e+"":"object"==typeof e||"function"==typeof e?n[o.call(e)]||"object":typeof e}var f="3.5.1",S=function(e,t){return new S.fn.init(e,t)};function p(e){var t=!!e&&"length"in e&&e.length,n=w(e);return!m(e)&&!x(e)&&("array"===n||0===t||"number"==typeof t&&0<t&&t-1 in e)}S.fn=S.prototype={jquery:f,constructor:S,length:0,toArray:function(){return s.call(this)},get:function(e){return null==e?s.call(this):e<0?this[e+this.length]:this[e]},pushStack:function(e){var t=S.merge(this.constructor(),e);return t.prevObject=this,t},each:function(e){return S.each(this,e)},map:function(n){return this.pushStack(S.map(this,function(e,t){return n.call(e,t,e)}))},slice:function(){return this.pushStack(s.apply(this,arguments))},first:function(){return this.eq(0)},last:function(){return this.eq(-1)},even:function(){return this.pushStack(S.grep(this,function(e,t){return(t+1)%2}))},odd:function(){return this.pushStack(S.grep(this,function(e,t){return t%2}))},eq:function(e){var t=this.length,n=+e+(e<0?t:0);return this.pushStack(0<=n&&n<t?[this[n]]:[])},end:function(){return this.prevObject||this.constructor()},push:u,sort:t.sort,splice:t.splice},S.extend=S.fn.extend=function(){var e,t,n,r,i,o,a=arguments[0]||{},s=1,u=arguments.length,l=!1;for("boolean"==typeof a&&(l=a,a=arguments[s]||{},s++),"object"==typeof a||m(a)||(a={}),s===u&&(a=this,s--);s<u;s++)if(null!=(e=arguments[s]))for(t in e)r=e[t],"__proto__"!==t&&a!==r&&(l&&r&&(S.isPlainObject(r)||(i=Array.isArray(r)))?(n=a[t],o=i&&!Array.isArray(n)?[]:i||S.isPlainObject(n)?n:{},i=!1,a[t]=S.extend(l,o,r)):void 0!==r&&(a[t]=r));return a},S.extend({expando:"jQuery"+(f+Math.random()).replace(/\D/g,""),isReady:!0,error:function(e){throw new Error(e)},noop:function(){},isPlainObject:function(e){var t,n;return!(!e||"[object Object]"!==o.call(e))&&(!(t=r(e))||"function"==typeof(n=v.call(t,"constructor")&&t.constructor)&&a.call(n)===l)},isEmptyObject:function(e){var t;for(t in e)return!1;return!0},globalEval:function(e,t,n){b(e,{nonce:t&&t.nonce},n)},each:function(e,t){var n,r=0;if(p(e)){for(n=e.length;r<n;r++)if(!1===t.call(e[r],r,e[r]))break}else for(r in e)if(!1===t.call(e[r],r,e[r]))break;return e},makeArray:function(e,t){var n=t||[];return null!=e&&(p(Object(e))?S.merge(n,"string"==typeof e?[e]:e):u.call(n,e)),n},inArray:function(e,t,n){return null==t?-1:i.call(t,e,n)},merge:function(e,t){for(var n=+t.length,r=0,i=e.length;r<n;r++)e[i++]=t[r];return e.length=i,e},grep:function(e,t,n){for(var r=[],i=0,o=e.length,a=!n;i<o;i++)!t(e[i],i)!==a&&r.push(e[i]);return r},map:function(e,t,n){var r,i,o=0,a=[];if(p(e))for(r=e.length;o<r;o++)null!=(i=t(e[o],o,n))&&a.push(i);else for(o in e)null!=(i=t(e[o],o,n))&&a.push(i);return g(a)},guid:1,support:y}),"function"==typeof Symbol&&(S.fn[Symbol.iterator]=t[Symbol.iterator]),S.each("Boolean Number String Function Array Date RegExp Object Error Symbol".split(" "),function(e,t){n["[object "+t+"]"]=t.toLowerCase()});var d=function(n){var e,d,b,o,i,h,f,g,w,u,l,T,C,a,E,v,s,c,y,S="sizzle"+1*new Date,p=n.document,k=0,r=0,m=ue(),x=ue(),A=ue(),N=ue(),D=function(e,t){return e===t&&(l=!0),0},j={}.hasOwnProperty,t=[],q=t.pop,L=t.push,H=t.push,O=t.slice,P=function(e,t){for(var n=0,r=e.length;n<r;n++)if(e[n]===t)return n;return-1},R="checked|selected|async|autofocus|autoplay|controls|defer|disabled|hidden|ismap|loop|multiple|open|readonly|required|scoped",M="[\\x20\\t\\r\\n\\f]",I="(?:\\\\[\\da-fA-F]{1,6}"+M+"?|\\\\[^\\r\\n\\f]|[\\w-]|[^\0-\\x7f])+",W="\\["+M+"*("+I+")(?:"+M+"*([*^$|!~]?=)"+M+"*(?:'((?:\\\\.|[^\\\\'])*)'|\"((?:\\\\.|[^\\\\\"])*)\"|("+I+"))|)"+M+"*\\]",F=":("+I+")(?:\\((('((?:\\\\.|[^\\\\'])*)'|\"((?:\\\\.|[^\\\\\"])*)\")|((?:\\\\.|[^\\\\()[\\]]|"+W+")*)|.*)\\)|)",B=new RegExp(M+"+","g"),$=new RegExp("^"+M+"+|((?:^|[^\\\\])(?:\\\\.)*)"+M+"+$","g"),_=new RegExp("^"+M+"*,"+M+"*"),z=new RegExp("^"+M+"*([>+~]|"+M+")"+M+"*"),U=new RegExp(M+"|>"),X=new RegExp(F),V=new RegExp("^"+I+"$"),G={ID:new RegExp("^#("+I+")"),CLASS:new RegExp("^\\.("+I+")"),TAG:new RegExp("^("+I+"|[*])"),ATTR:new RegExp("^"+W),PSEUDO:new RegExp("^"+F),CHILD:new RegExp("^:(only|first|last|nth|nth-last)-(child|of-type)(?:\\("+M+"*(even|odd|(([+-]|)(\\d*)n|)"+M+"*(?:([+-]|)"+M+"*(\\d+)|))"+M+"*\\)|)","i"),bool:new RegExp("^(?:"+R+")$","i"),needsContext:new RegExp("^"+M+"*[>+~]|:(even|odd|eq|gt|lt|nth|first|last)(?:\\("+M+"*((?:-\\d)?\\d*)"+M+"*\\)|)(?=[^-]|$)","i")},Y=/HTML$/i,Q=/^(?:input|select|textarea|button)$/i,J=/^h\d$/i,K=/^[^{]+\{\s*\[native \w/,Z=/^(?:#([\w-]+)|(\w+)|\.([\w-]+))$/,ee=/[+~]/,te=new RegExp("\\\\[\\da-fA-F]{1,6}"+M+"?|\\\\([^\\r\\n\\f])","g"),ne=function(e,t){var n="0x"+e.slice(1)-65536;return t||(n<0?String.fromCharCode(n+65536):String.fromCharCode(n>>10|55296,1023&n|56320))},re=/([\0-\x1f\x7f]|^-?\d)|^-$|[^\0-\x1f\x7f-\uFFFF\w-]/g,ie=function(e,t){return t?"\0"===e?"\ufffd":e.slice(0,-1)+"\\"+e.charCodeAt(e.length-1).toString(16)+" ":"\\"+e},oe=function(){T()},ae=be(function(e){return!0===e.disabled&&"fieldset"===e.nodeName.toLowerCase()},{dir:"parentNode",next:"legend"});try{H.apply(t=O.call(p.childNodes),p.childNodes),t[p.childNodes.length].nodeType}catch(e){H={apply:t.length?function(e,t){L.apply(e,O.call(t))}:function(e,t){var n=e.length,r=0;while(e[n++]=t[r++]);e.length=n-1}}}function se(t,e,n,r){var i,o,a,s,u,l,c,f=e&&e.ownerDocument,p=e?e.nodeType:9;if(n=n||[],"string"!=typeof t||!t||1!==p&&9!==p&&11!==p)return n;if(!r&&(T(e),e=e||C,E)){if(11!==p&&(u=Z.exec(t)))if(i=u[1]){if(9===p){if(!(a=e.getElementById(i)))return n;if(a.id===i)return n.push(a),n}else if(f&&(a=f.getElementById(i))&&y(e,a)&&a.id===i)return n.push(a),n}else{if(u[2])return H.apply(n,e.getElementsByTagName(t)),n;if((i=u[3])&&d.getElementsByClassName&&e.getElementsByClassName)return H.apply(n,e.getElementsByClassName(i)),n}if(d.qsa&&!N[t+" "]&&(!v||!v.test(t))&&(1!==p||"object"!==e.nodeName.toLowerCase())){if(c=t,f=e,1===p&&(U.test(t)||z.test(t))){(f=ee.test(t)&&ye(e.parentNode)||e)===e&&d.scope||((s=e.getAttribute("id"))?s=s.replace(re,ie):e.setAttribute("id",s=S)),o=(l=h(t)).length;while(o--)l[o]=(s?"#"+s:":scope")+" "+xe(l[o]);c=l.join(",")}try{return H.apply(n,f.querySelectorAll(c)),n}catch(e){N(t,!0)}finally{s===S&&e.removeAttribute("id")}}}return g(t.replace($,"$1"),e,n,r)}function ue(){var r=[];return function e(t,n){return r.push(t+" ")>b.cacheLength&&delete e[r.shift()],e[t+" "]=n}}function le(e){return e[S]=!0,e}function ce(e){var t=C.createElement("fieldset");try{return!!e(t)}catch(e){return!1}finally{t.parentNode&&t.parentNode.removeChild(t),t=null}}function fe(e,t){var n=e.split("|"),r=n.length;while(r--)b.attrHandle[n[r]]=t}function pe(e,t){var n=t&&e,r=n&&1===e.nodeType&&1===t.nodeType&&e.sourceIndex-t.sourceIndex;if(r)return r;if(n)while(n=n.nextSibling)if(n===t)return-1;return e?1:-1}function de(t){return function(e){return"input"===e.nodeName.toLowerCase()&&e.type===t}}function he(n){return function(e){var t=e.nodeName.toLowerCase();return("input"===t||"button"===t)&&e.type===n}}function ge(t){return function(e){return"form"in e?e.parentNode&&!1===e.disabled?"label"in e?"label"in e.parentNode?e.parentNode.disabled===t:e.disabled===t:e.isDisabled===t||e.isDisabled!==!t&&ae(e)===t:e.disabled===t:"label"in e&&e.disabled===t}}function ve(a){return le(function(o){return o=+o,le(function(e,t){var n,r=a([],e.length,o),i=r.length;while(i--)e[n=r[i]]&&(e[n]=!(t[n]=e[n]))})})}function ye(e){return e&&"undefined"!=typeof e.getElementsByTagName&&e}for(e in d=se.support={},i=se.isXML=function(e){var t=e.namespaceURI,n=(e.ownerDocument||e).documentElement;return!Y.test(t||n&&n.nodeName||"HTML")},T=se.setDocument=function(e){var t,n,r=e?e.ownerDocument||e:p;return r!=C&&9===r.nodeType&&r.documentElement&&(a=(C=r).documentElement,E=!i(C),p!=C&&(n=C.defaultView)&&n.top!==n&&(n.addEventListener?n.addEventListener("unload",oe,!1):n.attachEvent&&n.attachEvent("onunload",oe)),d.scope=ce(function(e){return a.appendChild(e).appendChild(C.createElement("div")),"undefined"!=typeof e.querySelectorAll&&!e.querySelectorAll(":scope fieldset div").length}),d.attributes=ce(function(e){return e.className="i",!e.getAttribute("className")}),d.getElementsByTagName=ce(function(e){return e.appendChild(C.createComment("")),!e.getElementsByTagName("*").length}),d.getElementsByClassName=K.test(C.getElementsByClassName),d.getById=ce(function(e){return a.appendChild(e).id=S,!C.getElementsByName||!C.getElementsByName(S).length}),d.getById?(b.filter.ID=function(e){var t=e.replace(te,ne);return function(e){return e.getAttribute("id")===t}},b.find.ID=function(e,t){if("undefined"!=typeof t.getElementById&&E){var n=t.getElementById(e);return n?[n]:[]}}):(b.filter.ID=function(e){var n=e.replace(te,ne);return function(e){var t="undefined"!=typeof e.getAttributeNode&&e.getAttributeNode("id");return t&&t.value===n}},b.find.ID=function(e,t){if("undefined"!=typeof t.getElementById&&E){var n,r,i,o=t.getElementById(e);if(o){if((n=o.getAttributeNode("id"))&&n.value===e)return[o];i=t.getElementsByName(e),r=0;while(o=i[r++])if((n=o.getAttributeNode("id"))&&n.value===e)return[o]}return[]}}),b.find.TAG=d.getElementsByTagName?function(e,t){return"undefined"!=typeof t.getElementsByTagName?t.getElementsByTagName(e):d.qsa?t.querySelectorAll(e):void 0}:function(e,t){var n,r=[],i=0,o=t.getElementsByTagName(e);if("*"===e){while(n=o[i++])1===n.nodeType&&r.push(n);return r}return o},b.find.CLASS=d.getElementsByClassName&&function(e,t){if("undefined"!=typeof t.getElementsByClassName&&E)return t.getElementsByClassName(e)},s=[],v=[],(d.qsa=K.test(C.querySelectorAll))&&(ce(function(e){var t;a.appendChild(e).innerHTML="<a id='"+S+"'></a><select id='"+S+"-\r\\' msallowcapture=''><option selected=''></option></select>",e.querySelectorAll("[msallowcapture^='']").length&&v.push("[*^$]="+M+"*(?:''|\"\")"),e.querySelectorAll("[selected]").length||v.push("\\["+M+"*(?:value|"+R+")"),e.querySelectorAll("[id~="+S+"-]").length||v.push("~="),(t=C.createElement("input")).setAttribute("name",""),e.appendChild(t),e.querySelectorAll("[name='']").length||v.push("\\["+M+"*name"+M+"*="+M+"*(?:''|\"\")"),e.querySelectorAll(":checked").length||v.push(":checked"),e.querySelectorAll("a#"+S+"+*").length||v.push(".#.+[+~]"),e.querySelectorAll("\\\f"),v.push("[\\r\\n\\f]")}),ce(function(e){e.innerHTML="<a href='' disabled='disabled'></a><select disabled='disabled'><option/></select>";var t=C.createElement("input");t.setAttribute("type","hidden"),e.appendChild(t).setAttribute("name","D"),e.querySelectorAll("[name=d]").length&&v.push("name"+M+"*[*^$|!~]?="),2!==e.querySelectorAll(":enabled").length&&v.push(":enabled",":disabled"),a.appendChild(e).disabled=!0,2!==e.querySelectorAll(":disabled").length&&v.push(":enabled",":disabled"),e.querySelectorAll("*,:x"),v.push(",.*:")})),(d.matchesSelector=K.test(c=a.matches||a.webkitMatchesSelector||a.mozMatchesSelector||a.oMatchesSelector||a.msMatchesSelector))&&ce(function(e){d.disconnectedMatch=c.call(e,"*"),c.call(e,"[s!='']:x"),s.push("!=",F)}),v=v.length&&new RegExp(v.join("|")),s=s.length&&new RegExp(s.join("|")),t=K.test(a.compareDocumentPosition),y=t||K.test(a.contains)?function(e,t){var n=9===e.nodeType?e.documentElement:e,r=t&&t.parentNode;return e===r||!(!r||1!==r.nodeType||!(n.contains?n.contains(r):e.compareDocumentPosition&&16&e.compareDocumentPosition(r)))}:function(e,t){if(t)while(t=t.parentNode)if(t===e)return!0;return!1},D=t?function(e,t){if(e===t)return l=!0,0;var n=!e.compareDocumentPosition-!t.compareDocumentPosition;return n||(1&(n=(e.ownerDocument||e)==(t.ownerDocument||t)?e.compareDocumentPosition(t):1)||!d.sortDetached&&t.compareDocumentPosition(e)===n?e==C||e.ownerDocument==p&&y(p,e)?-1:t==C||t.ownerDocument==p&&y(p,t)?1:u?P(u,e)-P(u,t):0:4&n?-1:1)}:function(e,t){if(e===t)return l=!0,0;var n,r=0,i=e.parentNode,o=t.parentNode,a=[e],s=[t];if(!i||!o)return e==C?-1:t==C?1:i?-1:o?1:u?P(u,e)-P(u,t):0;if(i===o)return pe(e,t);n=e;while(n=n.parentNode)a.unshift(n);n=t;while(n=n.parentNode)s.unshift(n);while(a[r]===s[r])r++;return r?pe(a[r],s[r]):a[r]==p?-1:s[r]==p?1:0}),C},se.matches=function(e,t){return se(e,null,null,t)},se.matchesSelector=function(e,t){if(T(e),d.matchesSelector&&E&&!N[t+" "]&&(!s||!s.test(t))&&(!v||!v.test(t)))try{var n=c.call(e,t);if(n||d.disconnectedMatch||e.document&&11!==e.document.nodeType)return n}catch(e){N(t,!0)}return 0<se(t,C,null,[e]).length},se.contains=function(e,t){return(e.ownerDocument||e)!=C&&T(e),y(e,t)},se.attr=function(e,t){(e.ownerDocument||e)!=C&&T(e);var n=b.attrHandle[t.toLowerCase()],r=n&&j.call(b.attrHandle,t.toLowerCase())?n(e,t,!E):void 0;return void 0!==r?r:d.attributes||!E?e.getAttribute(t):(r=e.getAttributeNode(t))&&r.specified?r.value:null},se.escape=function(e){return(e+"").replace(re,ie)},se.error=function(e){throw new Error("Syntax error, unrecognized expression: "+e)},se.uniqueSort=function(e){var t,n=[],r=0,i=0;if(l=!d.detectDuplicates,u=!d.sortStable&&e.slice(0),e.sort(D),l){while(t=e[i++])t===e[i]&&(r=n.push(i));while(r--)e.splice(n[r],1)}return u=null,e},o=se.getText=function(e){var t,n="",r=0,i=e.nodeType;if(i){if(1===i||9===i||11===i){if("string"==typeof e.textContent)return e.textContent;for(e=e.firstChild;e;e=e.nextSibling)n+=o(e)}else if(3===i||4===i)return e.nodeValue}else while(t=e[r++])n+=o(t);return n},(b=se.selectors={cacheLength:50,createPseudo:le,match:G,attrHandle:{},find:{},relative:{">":{dir:"parentNode",first:!0}," ":{dir:"parentNode"},"+":{dir:"previousSibling",first:!0},"~":{dir:"previousSibling"}},preFilter:{ATTR:function(e){return e[1]=e[1].replace(te,ne),e[3]=(e[3]||e[4]||e[5]||"").replace(te,ne),"~="===e[2]&&(e[3]=" "+e[3]+" "),e.slice(0,4)},CHILD:function(e){return e[1]=e[1].toLowerCase(),"nth"===e[1].slice(0,3)?(e[3]||se.error(e[0]),e[4]=+(e[4]?e[5]+(e[6]||1):2*("even"===e[3]||"odd"===e[3])),e[5]=+(e[7]+e[8]||"odd"===e[3])):e[3]&&se.error(e[0]),e},PSEUDO:function(e){var t,n=!e[6]&&e[2];return G.CHILD.test(e[0])?null:(e[3]?e[2]=e[4]||e[5]||"":n&&X.test(n)&&(t=h(n,!0))&&(t=n.indexOf(")",n.length-t)-n.length)&&(e[0]=e[0].slice(0,t),e[2]=n.slice(0,t)),e.slice(0,3))}},filter:{TAG:function(e){var t=e.replace(te,ne).toLowerCase();return"*"===e?function(){return!0}:function(e){return e.nodeName&&e.nodeName.toLowerCase()===t}},CLASS:function(e){var t=m[e+" "];return t||(t=new RegExp("(^|"+M+")"+e+"("+M+"|$)"))&&m(e,function(e){return t.test("string"==typeof e.className&&e.className||"undefined"!=typeof e.getAttribute&&e.getAttribute("class")||"")})},ATTR:function(n,r,i){return function(e){var t=se.attr(e,n);return null==t?"!="===r:!r||(t+="","="===r?t===i:"!="===r?t!==i:"^="===r?i&&0===t.indexOf(i):"*="===r?i&&-1<t.indexOf(i):"$="===r?i&&t.slice(-i.length)===i:"~="===r?-1<(" "+t.replace(B," ")+" ").indexOf(i):"|="===r&&(t===i||t.slice(0,i.length+1)===i+"-"))}},CHILD:function(h,e,t,g,v){var y="nth"!==h.slice(0,3),m="last"!==h.slice(-4),x="of-type"===e;return 1===g&&0===v?function(e){return!!e.parentNode}:function(e,t,n){var r,i,o,a,s,u,l=y!==m?"nextSibling":"previousSibling",c=e.parentNode,f=x&&e.nodeName.toLowerCase(),p=!n&&!x,d=!1;if(c){if(y){while(l){a=e;while(a=a[l])if(x?a.nodeName.toLowerCase()===f:1===a.nodeType)return!1;u=l="only"===h&&!u&&"nextSibling"}return!0}if(u=[m?c.firstChild:c.lastChild],m&&p){d=(s=(r=(i=(o=(a=c)[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]||[])[0]===k&&r[1])&&r[2],a=s&&c.childNodes[s];while(a=++s&&a&&a[l]||(d=s=0)||u.pop())if(1===a.nodeType&&++d&&a===e){i[h]=[k,s,d];break}}else if(p&&(d=s=(r=(i=(o=(a=e)[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]||[])[0]===k&&r[1]),!1===d)while(a=++s&&a&&a[l]||(d=s=0)||u.pop())if((x?a.nodeName.toLowerCase()===f:1===a.nodeType)&&++d&&(p&&((i=(o=a[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]=[k,d]),a===e))break;return(d-=v)===g||d%g==0&&0<=d/g}}},PSEUDO:function(e,o){var t,a=b.pseudos[e]||b.setFilters[e.toLowerCase()]||se.error("unsupported pseudo: "+e);return a[S]?a(o):1<a.length?(t=[e,e,"",o],b.setFilters.hasOwnProperty(e.toLowerCase())?le(function(e,t){var n,r=a(e,o),i=r.length;while(i--)e[n=P(e,r[i])]=!(t[n]=r[i])}):function(e){return a(e,0,t)}):a}},pseudos:{not:le(function(e){var r=[],i=[],s=f(e.replace($,"$1"));return s[S]?le(function(e,t,n,r){var i,o=s(e,null,r,[]),a=e.length;while(a--)(i=o[a])&&(e[a]=!(t[a]=i))}):function(e,t,n){return r[0]=e,s(r,null,n,i),r[0]=null,!i.pop()}}),has:le(function(t){return function(e){return 0<se(t,e).length}}),contains:le(function(t){return t=t.replace(te,ne),function(e){return-1<(e.textContent||o(e)).indexOf(t)}}),lang:le(function(n){return V.test(n||"")||se.error("unsupported lang: "+n),n=n.replace(te,ne).toLowerCase(),function(e){var t;do{if(t=E?e.lang:e.getAttribute("xml:lang")||e.getAttribute("lang"))return(t=t.toLowerCase())===n||0===t.indexOf(n+"-")}while((e=e.parentNode)&&1===e.nodeType);return!1}}),target:function(e){var t=n.location&&n.location.hash;return t&&t.slice(1)===e.id},root:function(e){return e===a},focus:function(e){return e===C.activeElement&&(!C.hasFocus||C.hasFocus())&&!!(e.type||e.href||~e.tabIndex)},enabled:ge(!1),disabled:ge(!0),checked:function(e){var t=e.nodeName.toLowerCase();return"input"===t&&!!e.checked||"option"===t&&!!e.selected},selected:function(e){return e.parentNode&&e.parentNode.selectedIndex,!0===e.selected},empty:function(e){for(e=e.firstChild;e;e=e.nextSibling)if(e.nodeType<6)return!1;return!0},parent:function(e){return!b.pseudos.empty(e)},header:function(e){return J.test(e.nodeName)},input:function(e){return Q.test(e.nodeName)},button:function(e){var t=e.nodeName.toLowerCase();return"input"===t&&"button"===e.type||"button"===t},text:function(e){var t;return"input"===e.nodeName.toLowerCase()&&"text"===e.type&&(null==(t=e.getAttribute("type"))||"text"===t.toLowerCase())},first:ve(function(){return[0]}),last:ve(function(e,t){return[t-1]}),eq:ve(function(e,t,n){return[n<0?n+t:n]}),even:ve(function(e,t){for(var n=0;n<t;n+=2)e.push(n);return e}),odd:ve(function(e,t){for(var n=1;n<t;n+=2)e.push(n);return e}),lt:ve(function(e,t,n){for(var r=n<0?n+t:t<n?t:n;0<=--r;)e.push(r);return e}),gt:ve(function(e,t,n){for(var r=n<0?n+t:n;++r<t;)e.push(r);return e})}}).pseudos.nth=b.pseudos.eq,{radio:!0,checkbox:!0,file:!0,password:!0,image:!0})b.pseudos[e]=de(e);for(e in{submit:!0,reset:!0})b.pseudos[e]=he(e);function me(){}function xe(e){for(var t=0,n=e.length,r="";t<n;t++)r+=e[t].value;return r}function be(s,e,t){var u=e.dir,l=e.next,c=l||u,f=t&&"parentNode"===c,p=r++;return e.first?function(e,t,n){while(e=e[u])if(1===e.nodeType||f)return s(e,t,n);return!1}:function(e,t,n){var r,i,o,a=[k,p];if(n){while(e=e[u])if((1===e.nodeType||f)&&s(e,t,n))return!0}else while(e=e[u])if(1===e.nodeType||f)if(i=(o=e[S]||(e[S]={}))[e.uniqueID]||(o[e.uniqueID]={}),l&&l===e.nodeName.toLowerCase())e=e[u]||e;else{if((r=i[c])&&r[0]===k&&r[1]===p)return a[2]=r[2];if((i[c]=a)[2]=s(e,t,n))return!0}return!1}}function we(i){return 1<i.length?function(e,t,n){var r=i.length;while(r--)if(!i[r](e,t,n))return!1;return!0}:i[0]}function Te(e,t,n,r,i){for(var o,a=[],s=0,u=e.length,l=null!=t;s<u;s++)(o=e[s])&&(n&&!n(o,r,i)||(a.push(o),l&&t.push(s)));return a}function Ce(d,h,g,v,y,e){return v&&!v[S]&&(v=Ce(v)),y&&!y[S]&&(y=Ce(y,e)),le(function(e,t,n,r){var i,o,a,s=[],u=[],l=t.length,c=e||function(e,t,n){for(var r=0,i=t.length;r<i;r++)se(e,t[r],n);return n}(h||"*",n.nodeType?[n]:n,[]),f=!d||!e&&h?c:Te(c,s,d,n,r),p=g?y||(e?d:l||v)?[]:t:f;if(g&&g(f,p,n,r),v){i=Te(p,u),v(i,[],n,r),o=i.length;while(o--)(a=i[o])&&(p[u[o]]=!(f[u[o]]=a))}if(e){if(y||d){if(y){i=[],o=p.length;while(o--)(a=p[o])&&i.push(f[o]=a);y(null,p=[],i,r)}o=p.length;while(o--)(a=p[o])&&-1<(i=y?P(e,a):s[o])&&(e[i]=!(t[i]=a))}}else p=Te(p===t?p.splice(l,p.length):p),y?y(null,t,p,r):H.apply(t,p)})}function Ee(e){for(var i,t,n,r=e.length,o=b.relative[e[0].type],a=o||b.relative[" "],s=o?1:0,u=be(function(e){return e===i},a,!0),l=be(function(e){return-1<P(i,e)},a,!0),c=[function(e,t,n){var r=!o&&(n||t!==w)||((i=t).nodeType?u(e,t,n):l(e,t,n));return i=null,r}];s<r;s++)if(t=b.relative[e[s].type])c=[be(we(c),t)];else{if((t=b.filter[e[s].type].apply(null,e[s].matches))[S]){for(n=++s;n<r;n++)if(b.relative[e[n].type])break;return Ce(1<s&&we(c),1<s&&xe(e.slice(0,s-1).concat({value:" "===e[s-2].type?"*":""})).replace($,"$1"),t,s<n&&Ee(e.slice(s,n)),n<r&&Ee(e=e.slice(n)),n<r&&xe(e))}c.push(t)}return we(c)}return me.prototype=b.filters=b.pseudos,b.setFilters=new me,h=se.tokenize=function(e,t){var n,r,i,o,a,s,u,l=x[e+" "];if(l)return t?0:l.slice(0);a=e,s=[],u=b.preFilter;while(a){for(o in n&&!(r=_.exec(a))||(r&&(a=a.slice(r[0].length)||a),s.push(i=[])),n=!1,(r=z.exec(a))&&(n=r.shift(),i.push({value:n,type:r[0].replace($," ")}),a=a.slice(n.length)),b.filter)!(r=G[o].exec(a))||u[o]&&!(r=u[o](r))||(n=r.shift(),i.push({value:n,type:o,matches:r}),a=a.slice(n.length));if(!n)break}return t?a.length:a?se.error(e):x(e,s).slice(0)},f=se.compile=function(e,t){var n,v,y,m,x,r,i=[],o=[],a=A[e+" "];if(!a){t||(t=h(e)),n=t.length;while(n--)(a=Ee(t[n]))[S]?i.push(a):o.push(a);(a=A(e,(v=o,m=0<(y=i).length,x=0<v.length,r=function(e,t,n,r,i){var o,a,s,u=0,l="0",c=e&&[],f=[],p=w,d=e||x&&b.find.TAG("*",i),h=k+=null==p?1:Math.random()||.1,g=d.length;for(i&&(w=t==C||t||i);l!==g&&null!=(o=d[l]);l++){if(x&&o){a=0,t||o.ownerDocument==C||(T(o),n=!E);while(s=v[a++])if(s(o,t||C,n)){r.push(o);break}i&&(k=h)}m&&((o=!s&&o)&&u--,e&&c.push(o))}if(u+=l,m&&l!==u){a=0;while(s=y[a++])s(c,f,t,n);if(e){if(0<u)while(l--)c[l]||f[l]||(f[l]=q.call(r));f=Te(f)}H.apply(r,f),i&&!e&&0<f.length&&1<u+y.length&&se.uniqueSort(r)}return i&&(k=h,w=p),c},m?le(r):r))).selector=e}return a},g=se.select=function(e,t,n,r){var i,o,a,s,u,l="function"==typeof e&&e,c=!r&&h(e=l.selector||e);if(n=n||[],1===c.length){if(2<(o=c[0]=c[0].slice(0)).length&&"ID"===(a=o[0]).type&&9===t.nodeType&&E&&b.relative[o[1].type]){if(!(t=(b.find.ID(a.matches[0].replace(te,ne),t)||[])[0]))return n;l&&(t=t.parentNode),e=e.slice(o.shift().value.length)}i=G.needsContext.test(e)?0:o.length;while(i--){if(a=o[i],b.relative[s=a.type])break;if((u=b.find[s])&&(r=u(a.matches[0].replace(te,ne),ee.test(o[0].type)&&ye(t.parentNode)||t))){if(o.splice(i,1),!(e=r.length&&xe(o)))return H.apply(n,r),n;break}}}return(l||f(e,c))(r,t,!E,n,!t||ee.test(e)&&ye(t.parentNode)||t),n},d.sortStable=S.split("").sort(D).join("")===S,d.detectDuplicates=!!l,T(),d.sortDetached=ce(function(e){return 1&e.compareDocumentPosition(C.createElement("fieldset"))}),ce(function(e){return e.innerHTML="<a href='#'></a>","#"===e.firstChild.getAttribute("href")})||fe("type|href|height|width",function(e,t,n){if(!n)return e.getAttribute(t,"type"===t.toLowerCase()?1:2)}),d.attributes&&ce(function(e){return e.innerHTML="<input/>",e.firstChild.setAttribute("value",""),""===e.firstChild.getAttribute("value")})||fe("value",function(e,t,n){if(!n&&"input"===e.nodeName.toLowerCase())return e.defaultValue}),ce(function(e){return null==e.getAttribute("disabled")})||fe(R,function(e,t,n){var r;if(!n)return!0===e[t]?t.toLowerCase():(r=e.getAttributeNode(t))&&r.specified?r.value:null}),se}(C);S.find=d,S.expr=d.selectors,S.expr[":"]=S.expr.pseudos,S.uniqueSort=S.unique=d.uniqueSort,S.text=d.getText,S.isXMLDoc=d.isXML,S.contains=d.contains,S.escapeSelector=d.escape;var h=function(e,t,n){var r=[],i=void 0!==n;while((e=e[t])&&9!==e.nodeType)if(1===e.nodeType){if(i&&S(e).is(n))break;r.push(e)}return r},T=function(e,t){for(var n=[];e;e=e.nextSibling)1===e.nodeType&&e!==t&&n.push(e);return n},k=S.expr.match.needsContext;function A(e,t){return e.nodeName&&e.nodeName.toLowerCase()===t.toLowerCase()}var N=/^<([a-z][^\/\0>:\x20\t\r\n\f]*)[\x20\t\r\n\f]*\/?>(?:<\/\1>|)$/i;function D(e,n,r){return m(n)?S.grep(e,function(e,t){return!!n.call(e,t,e)!==r}):n.nodeType?S.grep(e,function(e){return e===n!==r}):"string"!=typeof n?S.grep(e,function(e){return-1<i.call(n,e)!==r}):S.filter(n,e,r)}S.filter=function(e,t,n){var r=t[0];return n&&(e=":not("+e+")"),1===t.length&&1===r.nodeType?S.find.matchesSelector(r,e)?[r]:[]:S.find.matches(e,S.grep(t,function(e){return 1===e.nodeType}))},S.fn.extend({find:function(e){var t,n,r=this.length,i=this;if("string"!=typeof e)return this.pushStack(S(e).filter(function(){for(t=0;t<r;t++)if(S.contains(i[t],this))return!0}));for(n=this.pushStack([]),t=0;t<r;t++)S.find(e,i[t],n);return 1<r?S.uniqueSort(n):n},filter:function(e){return this.pushStack(D(this,e||[],!1))},not:function(e){return this.pushStack(D(this,e||[],!0))},is:function(e){return!!D(this,"string"==typeof e&&k.test(e)?S(e):e||[],!1).length}});var j,q=/^(?:\s*(<[\w\W]+>)[^>]*|#([\w-]+))$/;(S.fn.init=function(e,t,n){var r,i;if(!e)return this;if(n=n||j,"string"==typeof e){if(!(r="<"===e[0]&&">"===e[e.length-1]&&3<=e.length?[null,e,null]:q.exec(e))||!r[1]&&t)return!t||t.jquery?(t||n).find(e):this.constructor(t).find(e);if(r[1]){if(t=t instanceof S?t[0]:t,S.merge(this,S.parseHTML(r[1],t&&t.nodeType?t.ownerDocument||t:E,!0)),N.test(r[1])&&S.isPlainObject(t))for(r in t)m(this[r])?this[r](t[r]):this.attr(r,t[r]);return this}return(i=E.getElementById(r[2]))&&(this[0]=i,this.length=1),this}return e.nodeType?(this[0]=e,this.length=1,this):m(e)?void 0!==n.ready?n.ready(e):e(S):S.makeArray(e,this)}).prototype=S.fn,j=S(E);var L=/^(?:parents|prev(?:Until|All))/,H={children:!0,contents:!0,next:!0,prev:!0};function O(e,t){while((e=e[t])&&1!==e.nodeType);return e}S.fn.extend({has:function(e){var t=S(e,this),n=t.length;return this.filter(function(){for(var e=0;e<n;e++)if(S.contains(this,t[e]))return!0})},closest:function(e,t){var n,r=0,i=this.length,o=[],a="string"!=typeof e&&S(e);if(!k.test(e))for(;r<i;r++)for(n=this[r];n&&n!==t;n=n.parentNode)if(n.nodeType<11&&(a?-1<a.index(n):1===n.nodeType&&S.find.matchesSelector(n,e))){o.push(n);break}return this.pushStack(1<o.length?S.uniqueSort(o):o)},index:function(e){return e?"string"==typeof e?i.call(S(e),this[0]):i.call(this,e.jquery?e[0]:e):this[0]&&this[0].parentNode?this.first().prevAll().length:-1},add:function(e,t){return this.pushStack(S.uniqueSort(S.merge(this.get(),S(e,t))))},addBack:function(e){return this.add(null==e?this.prevObject:this.prevObject.filter(e))}}),S.each({parent:function(e){var t=e.parentNode;return t&&11!==t.nodeType?t:null},parents:function(e){return h(e,"parentNode")},parentsUntil:function(e,t,n){return h(e,"parentNode",n)},next:function(e){return O(e,"nextSibling")},prev:function(e){return O(e,"previousSibling")},nextAll:function(e){return h(e,"nextSibling")},prevAll:function(e){return h(e,"previousSibling")},nextUntil:function(e,t,n){return h(e,"nextSibling",n)},prevUntil:function(e,t,n){return h(e,"previousSibling",n)},siblings:function(e){return T((e.parentNode||{}).firstChild,e)},children:function(e){return T(e.firstChild)},contents:function(e){return null!=e.contentDocument&&r(e.contentDocument)?e.contentDocument:(A(e,"template")&&(e=e.content||e),S.merge([],e.childNodes))}},function(r,i){S.fn[r]=function(e,t){var n=S.map(this,i,e);return"Until"!==r.slice(-5)&&(t=e),t&&"string"==typeof t&&(n=S.filter(t,n)),1<this.length&&(H[r]||S.uniqueSort(n),L.test(r)&&n.reverse()),this.pushStack(n)}});var P=/[^\x20\t\r\n\f]+/g;function R(e){return e}function M(e){throw e}function I(e,t,n,r){var i;try{e&&m(i=e.promise)?i.call(e).done(t).fail(n):e&&m(i=e.then)?i.call(e,t,n):t.apply(void 0,[e].slice(r))}catch(e){n.apply(void 0,[e])}}S.Callbacks=function(r){var e,n;r="string"==typeof r?(e=r,n={},S.each(e.match(P)||[],function(e,t){n[t]=!0}),n):S.extend({},r);var i,t,o,a,s=[],u=[],l=-1,c=function(){for(a=a||r.once,o=i=!0;u.length;l=-1){t=u.shift();while(++l<s.length)!1===s[l].apply(t[0],t[1])&&r.stopOnFalse&&(l=s.length,t=!1)}r.memory||(t=!1),i=!1,a&&(s=t?[]:"")},f={add:function(){return s&&(t&&!i&&(l=s.length-1,u.push(t)),function n(e){S.each(e,function(e,t){m(t)?r.unique&&f.has(t)||s.push(t):t&&t.length&&"string"!==w(t)&&n(t)})}(arguments),t&&!i&&c()),this},remove:function(){return S.each(arguments,function(e,t){var n;while(-1<(n=S.inArray(t,s,n)))s.splice(n,1),n<=l&&l--}),this},has:function(e){return e?-1<S.inArray(e,s):0<s.length},empty:function(){return s&&(s=[]),this},disable:function(){return a=u=[],s=t="",this},disabled:function(){return!s},lock:function(){return a=u=[],t||i||(s=t=""),this},locked:function(){return!!a},fireWith:function(e,t){return a||(t=[e,(t=t||[]).slice?t.slice():t],u.push(t),i||c()),this},fire:function(){return f.fireWith(this,arguments),this},fired:function(){return!!o}};return f},S.extend({Deferred:function(e){var o=[["notify","progress",S.Callbacks("memory"),S.Callbacks("memory"),2],["resolve","done",S.Callbacks("once memory"),S.Callbacks("once memory"),0,"resolved"],["reject","fail",S.Callbacks("once memory"),S.Callbacks("once memory"),1,"rejected"]],i="pending",a={state:function(){return i},always:function(){return s.done(arguments).fail(arguments),this},"catch":function(e){return a.then(null,e)},pipe:function(){var i=arguments;return S.Deferred(function(r){S.each(o,function(e,t){var n=m(i[t[4]])&&i[t[4]];s[t[1]](function(){var e=n&&n.apply(this,arguments);e&&m(e.promise)?e.promise().progress(r.notify).done(r.resolve).fail(r.reject):r[t[0]+"With"](this,n?[e]:arguments)})}),i=null}).promise()},then:function(t,n,r){var u=0;function l(i,o,a,s){return function(){var n=this,r=arguments,e=function(){var e,t;if(!(i<u)){if((e=a.apply(n,r))===o.promise())throw new TypeError("Thenable self-resolution");t=e&&("object"==typeof e||"function"==typeof e)&&e.then,m(t)?s?t.call(e,l(u,o,R,s),l(u,o,M,s)):(u++,t.call(e,l(u,o,R,s),l(u,o,M,s),l(u,o,R,o.notifyWith))):(a!==R&&(n=void 0,r=[e]),(s||o.resolveWith)(n,r))}},t=s?e:function(){try{e()}catch(e){S.Deferred.exceptionHook&&S.Deferred.exceptionHook(e,t.stackTrace),u<=i+1&&(a!==M&&(n=void 0,r=[e]),o.rejectWith(n,r))}};i?t():(S.Deferred.getStackHook&&(t.stackTrace=S.Deferred.getStackHook()),C.setTimeout(t))}}return S.Deferred(function(e){o[0][3].add(l(0,e,m(r)?r:R,e.notifyWith)),o[1][3].add(l(0,e,m(t)?t:R)),o[2][3].add(l(0,e,m(n)?n:M))}).promise()},promise:function(e){return null!=e?S.extend(e,a):a}},s={};return S.each(o,function(e,t){var n=t[2],r=t[5];a[t[1]]=n.add,r&&n.add(function(){i=r},o[3-e][2].disable,o[3-e][3].disable,o[0][2].lock,o[0][3].lock),n.add(t[3].fire),s[t[0]]=function(){return s[t[0]+"With"](this===s?void 0:this,arguments),this},s[t[0]+"With"]=n.fireWith}),a.promise(s),e&&e.call(s,s),s},when:function(e){var n=arguments.length,t=n,r=Array(t),i=s.call(arguments),o=S.Deferred(),a=function(t){return function(e){r[t]=this,i[t]=1<arguments.length?s.call(arguments):e,--n||o.resolveWith(r,i)}};if(n<=1&&(I(e,o.done(a(t)).resolve,o.reject,!n),"pending"===o.state()||m(i[t]&&i[t].then)))return o.then();while(t--)I(i[t],a(t),o.reject);return o.promise()}});var W=/^(Eval|Internal|Range|Reference|Syntax|Type|URI)Error$/;S.Deferred.exceptionHook=function(e,t){C.console&&C.console.warn&&e&&W.test(e.name)&&C.console.warn("jQuery.Deferred exception: "+e.message,e.stack,t)},S.readyException=function(e){C.setTimeout(function(){throw e})};var F=S.Deferred();function B(){E.removeEventListener("DOMContentLoaded",B),C.removeEventListener("load",B),S.ready()}S.fn.ready=function(e){return F.then(e)["catch"](function(e){S.readyException(e)}),this},S.extend({isReady:!1,readyWait:1,ready:function(e){(!0===e?--S.readyWait:S.isReady)||(S.isReady=!0)!==e&&0<--S.readyWait||F.resolveWith(E,[S])}}),S.ready.then=F.then,"complete"===E.readyState||"loading"!==E.readyState&&!E.documentElement.doScroll?C.setTimeout(S.ready):(E.addEventListener("DOMContentLoaded",B),C.addEventListener("load",B));var $=function(e,t,n,r,i,o,a){var s=0,u=e.length,l=null==n;if("object"===w(n))for(s in i=!0,n)$(e,t,s,n[s],!0,o,a);else if(void 0!==r&&(i=!0,m(r)||(a=!0),l&&(a?(t.call(e,r),t=null):(l=t,t=function(e,t,n){return l.call(S(e),n)})),t))for(;s<u;s++)t(e[s],n,a?r:r.call(e[s],s,t(e[s],n)));return i?e:l?t.call(e):u?t(e[0],n):o},_=/^-ms-/,z=/-([a-z])/g;function U(e,t){return t.toUpperCase()}function X(e){return e.replace(_,"ms-").replace(z,U)}var V=function(e){return 1===e.nodeType||9===e.nodeType||!+e.nodeType};function G(){this.expando=S.expando+G.uid++}G.uid=1,G.prototype={cache:function(e){var t=e[this.expando];return t||(t={},V(e)&&(e.nodeType?e[this.expando]=t:Object.defineProperty(e,this.expando,{value:t,configurable:!0}))),t},set:function(e,t,n){var r,i=this.cache(e);if("string"==typeof t)i[X(t)]=n;else for(r in t)i[X(r)]=t[r];return i},get:function(e,t){return void 0===t?this.cache(e):e[this.expando]&&e[this.expando][X(t)]},access:function(e,t,n){return void 0===t||t&&"string"==typeof t&&void 0===n?this.get(e,t):(this.set(e,t,n),void 0!==n?n:t)},remove:function(e,t){var n,r=e[this.expando];if(void 0!==r){if(void 0!==t){n=(t=Array.isArray(t)?t.map(X):(t=X(t))in r?[t]:t.match(P)||[]).length;while(n--)delete r[t[n]]}(void 0===t||S.isEmptyObject(r))&&(e.nodeType?e[this.expando]=void 0:delete e[this.expando])}},hasData:function(e){var t=e[this.expando];return void 0!==t&&!S.isEmptyObject(t)}};var Y=new G,Q=new G,J=/^(?:\{[\w\W]*\}|\[[\w\W]*\])$/,K=/[A-Z]/g;function Z(e,t,n){var r,i;if(void 0===n&&1===e.nodeType)if(r="data-"+t.replace(K,"-$&").toLowerCase(),"string"==typeof(n=e.getAttribute(r))){try{n="true"===(i=n)||"false"!==i&&("null"===i?null:i===+i+""?+i:J.test(i)?JSON.parse(i):i)}catch(e){}Q.set(e,t,n)}else n=void 0;return n}S.extend({hasData:function(e){return Q.hasData(e)||Y.hasData(e)},data:function(e,t,n){return Q.access(e,t,n)},removeData:function(e,t){Q.remove(e,t)},_data:function(e,t,n){return Y.access(e,t,n)},_removeData:function(e,t){Y.remove(e,t)}}),S.fn.extend({data:function(n,e){var t,r,i,o=this[0],a=o&&o.attributes;if(void 0===n){if(this.length&&(i=Q.get(o),1===o.nodeType&&!Y.get(o,"hasDataAttrs"))){t=a.length;while(t--)a[t]&&0===(r=a[t].name).indexOf("data-")&&(r=X(r.slice(5)),Z(o,r,i[r]));Y.set(o,"hasDataAttrs",!0)}return i}return"object"==typeof n?this.each(function(){Q.set(this,n)}):$(this,function(e){var t;if(o&&void 0===e)return void 0!==(t=Q.get(o,n))?t:void 0!==(t=Z(o,n))?t:void 0;this.each(function(){Q.set(this,n,e)})},null,e,1<arguments.length,null,!0)},removeData:function(e){return this.each(function(){Q.remove(this,e)})}}),S.extend({queue:function(e,t,n){var r;if(e)return t=(t||"fx")+"queue",r=Y.get(e,t),n&&(!r||Array.isArray(n)?r=Y.access(e,t,S.makeArray(n)):r.push(n)),r||[]},dequeue:function(e,t){t=t||"fx";var n=S.queue(e,t),r=n.length,i=n.shift(),o=S._queueHooks(e,t);"inprogress"===i&&(i=n.shift(),r--),i&&("fx"===t&&n.unshift("inprogress"),delete o.stop,i.call(e,function(){S.dequeue(e,t)},o)),!r&&o&&o.empty.fire()},_queueHooks:function(e,t){var n=t+"queueHooks";return Y.get(e,n)||Y.access(e,n,{empty:S.Callbacks("once memory").add(function(){Y.remove(e,[t+"queue",n])})})}}),S.fn.extend({queue:function(t,n){var e=2;return"string"!=typeof t&&(n=t,t="fx",e--),arguments.length<e?S.queue(this[0],t):void 0===n?this:this.each(function(){var e=S.queue(this,t,n);S._queueHooks(this,t),"fx"===t&&"inprogress"!==e[0]&&S.dequeue(this,t)})},dequeue:function(e){return this.each(function(){S.dequeue(this,e)})},clearQueue:function(e){return this.queue(e||"fx",[])},promise:function(e,t){var n,r=1,i=S.Deferred(),o=this,a=this.length,s=function(){--r||i.resolveWith(o,[o])};"string"!=typeof e&&(t=e,e=void 0),e=e||"fx";while(a--)(n=Y.get(o[a],e+"queueHooks"))&&n.empty&&(r++,n.empty.add(s));return s(),i.promise(t)}});var ee=/[+-]?(?:\d*\.|)\d+(?:[eE][+-]?\d+|)/.source,te=new RegExp("^(?:([+-])=|)("+ee+")([a-z%]*)$","i"),ne=["Top","Right","Bottom","Left"],re=E.documentElement,ie=function(e){return S.contains(e.ownerDocument,e)},oe={composed:!0};re.getRootNode&&(ie=function(e){return S.contains(e.ownerDocument,e)||e.getRootNode(oe)===e.ownerDocument});var ae=function(e,t){return"none"===(e=t||e).style.display||""===e.style.display&&ie(e)&&"none"===S.css(e,"display")};function se(e,t,n,r){var i,o,a=20,s=r?function(){return r.cur()}:function(){return S.css(e,t,"")},u=s(),l=n&&n[3]||(S.cssNumber[t]?"":"px"),c=e.nodeType&&(S.cssNumber[t]||"px"!==l&&+u)&&te.exec(S.css(e,t));if(c&&c[3]!==l){u/=2,l=l||c[3],c=+u||1;while(a--)S.style(e,t,c+l),(1-o)*(1-(o=s()/u||.5))<=0&&(a=0),c/=o;c*=2,S.style(e,t,c+l),n=n||[]}return n&&(c=+c||+u||0,i=n[1]?c+(n[1]+1)*n[2]:+n[2],r&&(r.unit=l,r.start=c,r.end=i)),i}var ue={};function le(e,t){for(var n,r,i,o,a,s,u,l=[],c=0,f=e.length;c<f;c++)(r=e[c]).style&&(n=r.style.display,t?("none"===n&&(l[c]=Y.get(r,"display")||null,l[c]||(r.style.display="")),""===r.style.display&&ae(r)&&(l[c]=(u=a=o=void 0,a=(i=r).ownerDocument,s=i.nodeName,(u=ue[s])||(o=a.body.appendChild(a.createElement(s)),u=S.css(o,"display"),o.parentNode.removeChild(o),"none"===u&&(u="block"),ue[s]=u)))):"none"!==n&&(l[c]="none",Y.set(r,"display",n)));for(c=0;c<f;c++)null!=l[c]&&(e[c].style.display=l[c]);return e}S.fn.extend({show:function(){return le(this,!0)},hide:function(){return le(this)},toggle:function(e){return"boolean"==typeof e?e?this.show():this.hide():this.each(function(){ae(this)?S(this).show():S(this).hide()})}});var ce,fe,pe=/^(?:checkbox|radio)$/i,de=/<([a-z][^\/\0>\x20\t\r\n\f]*)/i,he=/^$|^module$|\/(?:java|ecma)script/i;ce=E.createDocumentFragment().appendChild(E.createElement("div")),(fe=E.createElement("input")).setAttribute("type","radio"),fe.setAttribute("checked","checked"),fe.setAttribute("name","t"),ce.appendChild(fe),y.checkClone=ce.cloneNode(!0).cloneNode(!0).lastChild.checked,ce.innerHTML="<textarea>x</textarea>",y.noCloneChecked=!!ce.cloneNode(!0).lastChild.defaultValue,ce.innerHTML="<option></option>",y.option=!!ce.lastChild;var ge={thead:[1,"<table>","</table>"],col:[2,"<table><colgroup>","</colgroup></table>"],tr:[2,"<table><tbody>","</tbody></table>"],td:[3,"<table><tbody><tr>","</tr></tbody></table>"],_default:[0,"",""]};function ve(e,t){var n;return n="undefined"!=typeof e.getElementsByTagName?e.getElementsByTagName(t||"*"):"undefined"!=typeof e.querySelectorAll?e.querySelectorAll(t||"*"):[],void 0===t||t&&A(e,t)?S.merge([e],n):n}function ye(e,t){for(var n=0,r=e.length;n<r;n++)Y.set(e[n],"globalEval",!t||Y.get(t[n],"globalEval"))}ge.tbody=ge.tfoot=ge.colgroup=ge.caption=ge.thead,ge.th=ge.td,y.option||(ge.optgroup=ge.option=[1,"<select multiple='multiple'>","</select>"]);var me=/<|&#?\w+;/;function xe(e,t,n,r,i){for(var o,a,s,u,l,c,f=t.createDocumentFragment(),p=[],d=0,h=e.length;d<h;d++)if((o=e[d])||0===o)if("object"===w(o))S.merge(p,o.nodeType?[o]:o);else if(me.test(o)){a=a||f.appendChild(t.createElement("div")),s=(de.exec(o)||["",""])[1].toLowerCase(),u=ge[s]||ge._default,a.innerHTML=u[1]+S.htmlPrefilter(o)+u[2],c=u[0];while(c--)a=a.lastChild;S.merge(p,a.childNodes),(a=f.firstChild).textContent=""}else p.push(t.createTextNode(o));f.textContent="",d=0;while(o=p[d++])if(r&&-1<S.inArray(o,r))i&&i.push(o);else if(l=ie(o),a=ve(f.appendChild(o),"script"),l&&ye(a),n){c=0;while(o=a[c++])he.test(o.type||"")&&n.push(o)}return f}var be=/^key/,we=/^(?:mouse|pointer|contextmenu|drag|drop)|click/,Te=/^([^.]*)(?:\.(.+)|)/;function Ce(){return!0}function Ee(){return!1}function Se(e,t){return e===function(){try{return E.activeElement}catch(e){}}()==("focus"===t)}function ke(e,t,n,r,i,o){var a,s;if("object"==typeof t){for(s in"string"!=typeof n&&(r=r||n,n=void 0),t)ke(e,s,n,r,t[s],o);return e}if(null==r&&null==i?(i=n,r=n=void 0):null==i&&("string"==typeof n?(i=r,r=void 0):(i=r,r=n,n=void 0)),!1===i)i=Ee;else if(!i)return e;return 1===o&&(a=i,(i=function(e){return S().off(e),a.apply(this,arguments)}).guid=a.guid||(a.guid=S.guid++)),e.each(function(){S.event.add(this,t,i,r,n)})}function Ae(e,i,o){o?(Y.set(e,i,!1),S.event.add(e,i,{namespace:!1,handler:function(e){var t,n,r=Y.get(this,i);if(1&e.isTrigger&&this[i]){if(r.length)(S.event.special[i]||{}).delegateType&&e.stopPropagation();else if(r=s.call(arguments),Y.set(this,i,r),t=o(this,i),this[i](),r!==(n=Y.get(this,i))||t?Y.set(this,i,!1):n={},r!==n)return e.stopImmediatePropagation(),e.preventDefault(),n.value}else r.length&&(Y.set(this,i,{value:S.event.trigger(S.extend(r[0],S.Event.prototype),r.slice(1),this)}),e.stopImmediatePropagation())}})):void 0===Y.get(e,i)&&S.event.add(e,i,Ce)}S.event={global:{},add:function(t,e,n,r,i){var o,a,s,u,l,c,f,p,d,h,g,v=Y.get(t);if(V(t)){n.handler&&(n=(o=n).handler,i=o.selector),i&&S.find.matchesSelector(re,i),n.guid||(n.guid=S.guid++),(u=v.events)||(u=v.events=Object.create(null)),(a=v.handle)||(a=v.handle=function(e){return"undefined"!=typeof S&&S.event.triggered!==e.type?S.event.dispatch.apply(t,arguments):void 0}),l=(e=(e||"").match(P)||[""]).length;while(l--)d=g=(s=Te.exec(e[l])||[])[1],h=(s[2]||"").split(".").sort(),d&&(f=S.event.special[d]||{},d=(i?f.delegateType:f.bindType)||d,f=S.event.special[d]||{},c=S.extend({type:d,origType:g,data:r,handler:n,guid:n.guid,selector:i,needsContext:i&&S.expr.match.needsContext.test(i),namespace:h.join(".")},o),(p=u[d])||((p=u[d]=[]).delegateCount=0,f.setup&&!1!==f.setup.call(t,r,h,a)||t.addEventListener&&t.addEventListener(d,a)),f.add&&(f.add.call(t,c),c.handler.guid||(c.handler.guid=n.guid)),i?p.splice(p.delegateCount++,0,c):p.push(c),S.event.global[d]=!0)}},remove:function(e,t,n,r,i){var o,a,s,u,l,c,f,p,d,h,g,v=Y.hasData(e)&&Y.get(e);if(v&&(u=v.events)){l=(t=(t||"").match(P)||[""]).length;while(l--)if(d=g=(s=Te.exec(t[l])||[])[1],h=(s[2]||"").split(".").sort(),d){f=S.event.special[d]||{},p=u[d=(r?f.delegateType:f.bindType)||d]||[],s=s[2]&&new RegExp("(^|\\.)"+h.join("\\.(?:.*\\.|)")+"(\\.|$)"),a=o=p.length;while(o--)c=p[o],!i&&g!==c.origType||n&&n.guid!==c.guid||s&&!s.test(c.namespace)||r&&r!==c.selector&&("**"!==r||!c.selector)||(p.splice(o,1),c.selector&&p.delegateCount--,f.remove&&f.remove.call(e,c));a&&!p.length&&(f.teardown&&!1!==f.teardown.call(e,h,v.handle)||S.removeEvent(e,d,v.handle),delete u[d])}else for(d in u)S.event.remove(e,d+t[l],n,r,!0);S.isEmptyObject(u)&&Y.remove(e,"handle events")}},dispatch:function(e){var t,n,r,i,o,a,s=new Array(arguments.length),u=S.event.fix(e),l=(Y.get(this,"events")||Object.create(null))[u.type]||[],c=S.event.special[u.type]||{};for(s[0]=u,t=1;t<arguments.length;t++)s[t]=arguments[t];if(u.delegateTarget=this,!c.preDispatch||!1!==c.preDispatch.call(this,u)){a=S.event.handlers.call(this,u,l),t=0;while((i=a[t++])&&!u.isPropagationStopped()){u.currentTarget=i.elem,n=0;while((o=i.handlers[n++])&&!u.isImmediatePropagationStopped())u.rnamespace&&!1!==o.namespace&&!u.rnamespace.test(o.namespace)||(u.handleObj=o,u.data=o.data,void 0!==(r=((S.event.special[o.origType]||{}).handle||o.handler).apply(i.elem,s))&&!1===(u.result=r)&&(u.preventDefault(),u.stopPropagation()))}return c.postDispatch&&c.postDispatch.call(this,u),u.result}},handlers:function(e,t){var n,r,i,o,a,s=[],u=t.delegateCount,l=e.target;if(u&&l.nodeType&&!("click"===e.type&&1<=e.button))for(;l!==this;l=l.parentNode||this)if(1===l.nodeType&&("click"!==e.type||!0!==l.disabled)){for(o=[],a={},n=0;n<u;n++)void 0===a[i=(r=t[n]).selector+" "]&&(a[i]=r.needsContext?-1<S(i,this).index(l):S.find(i,this,null,[l]).length),a[i]&&o.push(r);o.length&&s.push({elem:l,handlers:o})}return l=this,u<t.length&&s.push({elem:l,handlers:t.slice(u)}),s},addProp:function(t,e){Object.defineProperty(S.Event.prototype,t,{enumerable:!0,configurable:!0,get:m(e)?function(){if(this.originalEvent)return e(this.originalEvent)}:function(){if(this.originalEvent)return this.originalEvent[t]},set:function(e){Object.defineProperty(this,t,{enumerable:!0,configurable:!0,writable:!0,value:e})}})},fix:function(e){return e[S.expando]?e:new S.Event(e)},special:{load:{noBubble:!0},click:{setup:function(e){var t=this||e;return pe.test(t.type)&&t.click&&A(t,"input")&&Ae(t,"click",Ce),!1},trigger:function(e){var t=this||e;return pe.test(t.type)&&t.click&&A(t,"input")&&Ae(t,"click"),!0},_default:function(e){var t=e.target;return pe.test(t.type)&&t.click&&A(t,"input")&&Y.get(t,"click")||A(t,"a")}},beforeunload:{postDispatch:function(e){void 0!==e.result&&e.originalEvent&&(e.originalEvent.returnValue=e.result)}}}},S.removeEvent=function(e,t,n){e.removeEventListener&&e.removeEventListener(t,n)},S.Event=function(e,t){if(!(this instanceof S.Event))return new S.Event(e,t);e&&e.type?(this.originalEvent=e,this.type=e.type,this.isDefaultPrevented=e.defaultPrevented||void 0===e.defaultPrevented&&!1===e.returnValue?Ce:Ee,this.target=e.target&&3===e.target.nodeType?e.target.parentNode:e.target,this.currentTarget=e.currentTarget,this.relatedTarget=e.relatedTarget):this.type=e,t&&S.extend(this,t),this.timeStamp=e&&e.timeStamp||Date.now(),this[S.expando]=!0},S.Event.prototype={constructor:S.Event,isDefaultPrevented:Ee,isPropagationStopped:Ee,isImmediatePropagationStopped:Ee,isSimulated:!1,preventDefault:function(){var e=this.originalEvent;this.isDefaultPrevented=Ce,e&&!this.isSimulated&&e.preventDefault()},stopPropagation:function(){var e=this.originalEvent;this.isPropagationStopped=Ce,e&&!this.isSimulated&&e.stopPropagation()},stopImmediatePropagation:function(){var e=this.originalEvent;this.isImmediatePropagationStopped=Ce,e&&!this.isSimulated&&e.stopImmediatePropagation(),this.stopPropagation()}},S.each({altKey:!0,bubbles:!0,cancelable:!0,changedTouches:!0,ctrlKey:!0,detail:!0,eventPhase:!0,metaKey:!0,pageX:!0,pageY:!0,shiftKey:!0,view:!0,"char":!0,code:!0,charCode:!0,key:!0,keyCode:!0,button:!0,buttons:!0,clientX:!0,clientY:!0,offsetX:!0,offsetY:!0,pointerId:!0,pointerType:!0,screenX:!0,screenY:!0,targetTouches:!0,toElement:!0,touches:!0,which:function(e){var t=e.button;return null==e.which&&be.test(e.type)?null!=e.charCode?e.charCode:e.keyCode:!e.which&&void 0!==t&&we.test(e.type)?1&t?1:2&t?3:4&t?2:0:e.which}},S.event.addProp),S.each({focus:"focusin",blur:"focusout"},function(e,t){S.event.special[e]={setup:function(){return Ae(this,e,Se),!1},trigger:function(){return Ae(this,e),!0},delegateType:t}}),S.each({mouseenter:"mouseover",mouseleave:"mouseout",pointerenter:"pointerover",pointerleave:"pointerout"},function(e,i){S.event.special[e]={delegateType:i,bindType:i,handle:function(e){var t,n=e.relatedTarget,r=e.handleObj;return n&&(n===this||S.contains(this,n))||(e.type=r.origType,t=r.handler.apply(this,arguments),e.type=i),t}}}),S.fn.extend({on:function(e,t,n,r){return ke(this,e,t,n,r)},one:function(e,t,n,r){return ke(this,e,t,n,r,1)},off:function(e,t,n){var r,i;if(e&&e.preventDefault&&e.handleObj)return r=e.handleObj,S(e.delegateTarget).off(r.namespace?r.origType+"."+r.namespace:r.origType,r.selector,r.handler),this;if("object"==typeof e){for(i in e)this.off(i,t,e[i]);return this}return!1!==t&&"function"!=typeof t||(n=t,t=void 0),!1===n&&(n=Ee),this.each(function(){S.event.remove(this,e,n,t)})}});var Ne=/<script|<style|<link/i,De=/checked\s*(?:[^=]|=\s*.checked.)/i,je=/^\s*<!(?:\[CDATA\[|--)|(?:\]\]|--)>\s*$/g;function qe(e,t){return A(e,"table")&&A(11!==t.nodeType?t:t.firstChild,"tr")&&S(e).children("tbody")[0]||e}function Le(e){return e.type=(null!==e.getAttribute("type"))+"/"+e.type,e}function He(e){return"true/"===(e.type||"").slice(0,5)?e.type=e.type.slice(5):e.removeAttribute("type"),e}function Oe(e,t){var n,r,i,o,a,s;if(1===t.nodeType){if(Y.hasData(e)&&(s=Y.get(e).events))for(i in Y.remove(t,"handle events"),s)for(n=0,r=s[i].length;n<r;n++)S.event.add(t,i,s[i][n]);Q.hasData(e)&&(o=Q.access(e),a=S.extend({},o),Q.set(t,a))}}function Pe(n,r,i,o){r=g(r);var e,t,a,s,u,l,c=0,f=n.length,p=f-1,d=r[0],h=m(d);if(h||1<f&&"string"==typeof d&&!y.checkClone&&De.test(d))return n.each(function(e){var t=n.eq(e);h&&(r[0]=d.call(this,e,t.html())),Pe(t,r,i,o)});if(f&&(t=(e=xe(r,n[0].ownerDocument,!1,n,o)).firstChild,1===e.childNodes.length&&(e=t),t||o)){for(s=(a=S.map(ve(e,"script"),Le)).length;c<f;c++)u=e,c!==p&&(u=S.clone(u,!0,!0),s&&S.merge(a,ve(u,"script"))),i.call(n[c],u,c);if(s)for(l=a[a.length-1].ownerDocument,S.map(a,He),c=0;c<s;c++)u=a[c],he.test(u.type||"")&&!Y.access(u,"globalEval")&&S.contains(l,u)&&(u.src&&"module"!==(u.type||"").toLowerCase()?S._evalUrl&&!u.noModule&&S._evalUrl(u.src,{nonce:u.nonce||u.getAttribute("nonce")},l):b(u.textContent.replace(je,""),u,l))}return n}function Re(e,t,n){for(var r,i=t?S.filter(t,e):e,o=0;null!=(r=i[o]);o++)n||1!==r.nodeType||S.cleanData(ve(r)),r.parentNode&&(n&&ie(r)&&ye(ve(r,"script")),r.parentNode.removeChild(r));return e}S.extend({htmlPrefilter:function(e){return e},clone:function(e,t,n){var r,i,o,a,s,u,l,c=e.cloneNode(!0),f=ie(e);if(!(y.noCloneChecked||1!==e.nodeType&&11!==e.nodeType||S.isXMLDoc(e)))for(a=ve(c),r=0,i=(o=ve(e)).length;r<i;r++)s=o[r],u=a[r],void 0,"input"===(l=u.nodeName.toLowerCase())&&pe.test(s.type)?u.checked=s.checked:"input"!==l&&"textarea"!==l||(u.defaultValue=s.defaultValue);if(t)if(n)for(o=o||ve(e),a=a||ve(c),r=0,i=o.length;r<i;r++)Oe(o[r],a[r]);else Oe(e,c);return 0<(a=ve(c,"script")).length&&ye(a,!f&&ve(e,"script")),c},cleanData:function(e){for(var t,n,r,i=S.event.special,o=0;void 0!==(n=e[o]);o++)if(V(n)){if(t=n[Y.expando]){if(t.events)for(r in t.events)i[r]?S.event.remove(n,r):S.removeEvent(n,r,t.handle);n[Y.expando]=void 0}n[Q.expando]&&(n[Q.expando]=void 0)}}}),S.fn.extend({detach:function(e){return Re(this,e,!0)},remove:function(e){return Re(this,e)},text:function(e){return $(this,function(e){return void 0===e?S.text(this):this.empty().each(function(){1!==this.nodeType&&11!==this.nodeType&&9!==this.nodeType||(this.textContent=e)})},null,e,arguments.length)},append:function(){return Pe(this,arguments,function(e){1!==this.nodeType&&11!==this.nodeType&&9!==this.nodeType||qe(this,e).appendChild(e)})},prepend:function(){return Pe(this,arguments,function(e){if(1===this.nodeType||11===this.nodeType||9===this.nodeType){var t=qe(this,e);t.insertBefore(e,t.firstChild)}})},before:function(){return Pe(this,arguments,function(e){this.parentNode&&this.parentNode.insertBefore(e,this)})},after:function(){return Pe(this,arguments,function(e){this.parentNode&&this.parentNode.insertBefore(e,this.nextSibling)})},empty:function(){for(var e,t=0;null!=(e=this[t]);t++)1===e.nodeType&&(S.cleanData(ve(e,!1)),e.textContent="");return this},clone:function(e,t){return e=null!=e&&e,t=null==t?e:t,this.map(function(){return S.clone(this,e,t)})},html:function(e){return $(this,function(e){var t=this[0]||{},n=0,r=this.length;if(void 0===e&&1===t.nodeType)return t.innerHTML;if("string"==typeof e&&!Ne.test(e)&&!ge[(de.exec(e)||["",""])[1].toLowerCase()]){e=S.htmlPrefilter(e);try{for(;n<r;n++)1===(t=this[n]||{}).nodeType&&(S.cleanData(ve(t,!1)),t.innerHTML=e);t=0}catch(e){}}t&&this.empty().append(e)},null,e,arguments.length)},replaceWith:function(){var n=[];return Pe(this,arguments,function(e){var t=this.parentNode;S.inArray(this,n)<0&&(S.cleanData(ve(this)),t&&t.replaceChild(e,this))},n)}}),S.each({appendTo:"append",prependTo:"prepend",insertBefore:"before",insertAfter:"after",replaceAll:"replaceWith"},function(e,a){S.fn[e]=function(e){for(var t,n=[],r=S(e),i=r.length-1,o=0;o<=i;o++)t=o===i?this:this.clone(!0),S(r[o])[a](t),u.apply(n,t.get());return this.pushStack(n)}});var Me=new RegExp("^("+ee+")(?!px)[a-z%]+$","i"),Ie=function(e){var t=e.ownerDocument.defaultView;return t&&t.opener||(t=C),t.getComputedStyle(e)},We=function(e,t,n){var r,i,o={};for(i in t)o[i]=e.style[i],e.style[i]=t[i];for(i in r=n.call(e),t)e.style[i]=o[i];return r},Fe=new RegExp(ne.join("|"),"i");function Be(e,t,n){var r,i,o,a,s=e.style;return(n=n||Ie(e))&&(""!==(a=n.getPropertyValue(t)||n[t])||ie(e)||(a=S.style(e,t)),!y.pixelBoxStyles()&&Me.test(a)&&Fe.test(t)&&(r=s.width,i=s.minWidth,o=s.maxWidth,s.minWidth=s.maxWidth=s.width=a,a=n.width,s.width=r,s.minWidth=i,s.maxWidth=o)),void 0!==a?a+"":a}function $e(e,t){return{get:function(){if(!e())return(this.get=t).apply(this,arguments);delete this.get}}}!function(){function e(){if(l){u.style.cssText="position:absolute;left:-11111px;width:60px;margin-top:1px;padding:0;border:0",l.style.cssText="position:relative;display:block;box-sizing:border-box;overflow:scroll;margin:auto;border:1px;padding:1px;width:60%;top:1%",re.appendChild(u).appendChild(l);var e=C.getComputedStyle(l);n="1%"!==e.top,s=12===t(e.marginLeft),l.style.right="60%",o=36===t(e.right),r=36===t(e.width),l.style.position="absolute",i=12===t(l.offsetWidth/3),re.removeChild(u),l=null}}function t(e){return Math.round(parseFloat(e))}var n,r,i,o,a,s,u=E.createElement("div"),l=E.createElement("div");l.style&&(l.style.backgroundClip="content-box",l.cloneNode(!0).style.backgroundClip="",y.clearCloneStyle="content-box"===l.style.backgroundClip,S.extend(y,{boxSizingReliable:function(){return e(),r},pixelBoxStyles:function(){return e(),o},pixelPosition:function(){return e(),n},reliableMarginLeft:function(){return e(),s},scrollboxSize:function(){return e(),i},reliableTrDimensions:function(){var e,t,n,r;return null==a&&(e=E.createElement("table"),t=E.createElement("tr"),n=E.createElement("div"),e.style.cssText="position:absolute;left:-11111px",t.style.height="1px",n.style.height="9px",re.appendChild(e).appendChild(t).appendChild(n),r=C.getComputedStyle(t),a=3<parseInt(r.height),re.removeChild(e)),a}}))}();var _e=["Webkit","Moz","ms"],ze=E.createElement("div").style,Ue={};function Xe(e){var t=S.cssProps[e]||Ue[e];return t||(e in ze?e:Ue[e]=function(e){var t=e[0].toUpperCase()+e.slice(1),n=_e.length;while(n--)if((e=_e[n]+t)in ze)return e}(e)||e)}var Ve=/^(none|table(?!-c[ea]).+)/,Ge=/^--/,Ye={position:"absolute",visibility:"hidden",display:"block"},Qe={letterSpacing:"0",fontWeight:"400"};function Je(e,t,n){var r=te.exec(t);return r?Math.max(0,r[2]-(n||0))+(r[3]||"px"):t}function Ke(e,t,n,r,i,o){var a="width"===t?1:0,s=0,u=0;if(n===(r?"border":"content"))return 0;for(;a<4;a+=2)"margin"===n&&(u+=S.css(e,n+ne[a],!0,i)),r?("content"===n&&(u-=S.css(e,"padding"+ne[a],!0,i)),"margin"!==n&&(u-=S.css(e,"border"+ne[a]+"Width",!0,i))):(u+=S.css(e,"padding"+ne[a],!0,i),"padding"!==n?u+=S.css(e,"border"+ne[a]+"Width",!0,i):s+=S.css(e,"border"+ne[a]+"Width",!0,i));return!r&&0<=o&&(u+=Math.max(0,Math.ceil(e["offset"+t[0].toUpperCase()+t.slice(1)]-o-u-s-.5))||0),u}function Ze(e,t,n){var r=Ie(e),i=(!y.boxSizingReliable()||n)&&"border-box"===S.css(e,"boxSizing",!1,r),o=i,a=Be(e,t,r),s="offset"+t[0].toUpperCase()+t.slice(1);if(Me.test(a)){if(!n)return a;a="auto"}return(!y.boxSizingReliable()&&i||!y.reliableTrDimensions()&&A(e,"tr")||"auto"===a||!parseFloat(a)&&"inline"===S.css(e,"display",!1,r))&&e.getClientRects().length&&(i="border-box"===S.css(e,"boxSizing",!1,r),(o=s in e)&&(a=e[s])),(a=parseFloat(a)||0)+Ke(e,t,n||(i?"border":"content"),o,r,a)+"px"}function et(e,t,n,r,i){return new et.prototype.init(e,t,n,r,i)}S.extend({cssHooks:{opacity:{get:function(e,t){if(t){var n=Be(e,"opacity");return""===n?"1":n}}}},cssNumber:{animationIterationCount:!0,columnCount:!0,fillOpacity:!0,flexGrow:!0,flexShrink:!0,fontWeight:!0,gridArea:!0,gridColumn:!0,gridColumnEnd:!0,gridColumnStart:!0,gridRow:!0,gridRowEnd:!0,gridRowStart:!0,lineHeight:!0,opacity:!0,order:!0,orphans:!0,widows:!0,zIndex:!0,zoom:!0},cssProps:{},style:function(e,t,n,r){if(e&&3!==e.nodeType&&8!==e.nodeType&&e.style){var i,o,a,s=X(t),u=Ge.test(t),l=e.style;if(u||(t=Xe(s)),a=S.cssHooks[t]||S.cssHooks[s],void 0===n)return a&&"get"in a&&void 0!==(i=a.get(e,!1,r))?i:l[t];"string"===(o=typeof n)&&(i=te.exec(n))&&i[1]&&(n=se(e,t,i),o="number"),null!=n&&n==n&&("number"!==o||u||(n+=i&&i[3]||(S.cssNumber[s]?"":"px")),y.clearCloneStyle||""!==n||0!==t.indexOf("background")||(l[t]="inherit"),a&&"set"in a&&void 0===(n=a.set(e,n,r))||(u?l.setProperty(t,n):l[t]=n))}},css:function(e,t,n,r){var i,o,a,s=X(t);return Ge.test(t)||(t=Xe(s)),(a=S.cssHooks[t]||S.cssHooks[s])&&"get"in a&&(i=a.get(e,!0,n)),void 0===i&&(i=Be(e,t,r)),"normal"===i&&t in Qe&&(i=Qe[t]),""===n||n?(o=parseFloat(i),!0===n||isFinite(o)?o||0:i):i}}),S.each(["height","width"],function(e,u){S.cssHooks[u]={get:function(e,t,n){if(t)return!Ve.test(S.css(e,"display"))||e.getClientRects().length&&e.getBoundingClientRect().width?Ze(e,u,n):We(e,Ye,function(){return Ze(e,u,n)})},set:function(e,t,n){var r,i=Ie(e),o=!y.scrollboxSize()&&"absolute"===i.position,a=(o||n)&&"border-box"===S.css(e,"boxSizing",!1,i),s=n?Ke(e,u,n,a,i):0;return a&&o&&(s-=Math.ceil(e["offset"+u[0].toUpperCase()+u.slice(1)]-parseFloat(i[u])-Ke(e,u,"border",!1,i)-.5)),s&&(r=te.exec(t))&&"px"!==(r[3]||"px")&&(e.style[u]=t,t=S.css(e,u)),Je(0,t,s)}}}),S.cssHooks.marginLeft=$e(y.reliableMarginLeft,function(e,t){if(t)return(parseFloat(Be(e,"marginLeft"))||e.getBoundingClientRect().left-We(e,{marginLeft:0},function(){return e.getBoundingClientRect().left}))+"px"}),S.each({margin:"",padding:"",border:"Width"},function(i,o){S.cssHooks[i+o]={expand:function(e){for(var t=0,n={},r="string"==typeof e?e.split(" "):[e];t<4;t++)n[i+ne[t]+o]=r[t]||r[t-2]||r[0];return n}},"margin"!==i&&(S.cssHooks[i+o].set=Je)}),S.fn.extend({css:function(e,t){return $(this,function(e,t,n){var r,i,o={},a=0;if(Array.isArray(t)){for(r=Ie(e),i=t.length;a<i;a++)o[t[a]]=S.css(e,t[a],!1,r);return o}return void 0!==n?S.style(e,t,n):S.css(e,t)},e,t,1<arguments.length)}}),((S.Tween=et).prototype={constructor:et,init:function(e,t,n,r,i,o){this.elem=e,this.prop=n,this.easing=i||S.easing._default,this.options=t,this.start=this.now=this.cur(),this.end=r,this.unit=o||(S.cssNumber[n]?"":"px")},cur:function(){var e=et.propHooks[this.prop];return e&&e.get?e.get(this):et.propHooks._default.get(this)},run:function(e){var t,n=et.propHooks[this.prop];return this.options.duration?this.pos=t=S.easing[this.easing](e,this.options.duration*e,0,1,this.options.duration):this.pos=t=e,this.now=(this.end-this.start)*t+this.start,this.options.step&&this.options.step.call(this.elem,this.now,this),n&&n.set?n.set(this):et.propHooks._default.set(this),this}}).init.prototype=et.prototype,(et.propHooks={_default:{get:function(e){var t;return 1!==e.elem.nodeType||null!=e.elem[e.prop]&&null==e.elem.style[e.prop]?e.elem[e.prop]:(t=S.css(e.elem,e.prop,""))&&"auto"!==t?t:0},set:function(e){S.fx.step[e.prop]?S.fx.step[e.prop](e):1!==e.elem.nodeType||!S.cssHooks[e.prop]&&null==e.elem.style[Xe(e.prop)]?e.elem[e.prop]=e.now:S.style(e.elem,e.prop,e.now+e.unit)}}}).scrollTop=et.propHooks.scrollLeft={set:function(e){e.elem.nodeType&&e.elem.parentNode&&(e.elem[e.prop]=e.now)}},S.easing={linear:function(e){return e},swing:function(e){return.5-Math.cos(e*Math.PI)/2},_default:"swing"},S.fx=et.prototype.init,S.fx.step={};var tt,nt,rt,it,ot=/^(?:toggle|show|hide)$/,at=/queueHooks$/;function st(){nt&&(!1===E.hidden&&C.requestAnimationFrame?C.requestAnimationFrame(st):C.setTimeout(st,S.fx.interval),S.fx.tick())}function ut(){return C.setTimeout(function(){tt=void 0}),tt=Date.now()}function lt(e,t){var n,r=0,i={height:e};for(t=t?1:0;r<4;r+=2-t)i["margin"+(n=ne[r])]=i["padding"+n]=e;return t&&(i.opacity=i.width=e),i}function ct(e,t,n){for(var r,i=(ft.tweeners[t]||[]).concat(ft.tweeners["*"]),o=0,a=i.length;o<a;o++)if(r=i[o].call(n,t,e))return r}function ft(o,e,t){var n,a,r=0,i=ft.prefilters.length,s=S.Deferred().always(function(){delete u.elem}),u=function(){if(a)return!1;for(var e=tt||ut(),t=Math.max(0,l.startTime+l.duration-e),n=1-(t/l.duration||0),r=0,i=l.tweens.length;r<i;r++)l.tweens[r].run(n);return s.notifyWith(o,[l,n,t]),n<1&&i?t:(i||s.notifyWith(o,[l,1,0]),s.resolveWith(o,[l]),!1)},l=s.promise({elem:o,props:S.extend({},e),opts:S.extend(!0,{specialEasing:{},easing:S.easing._default},t),originalProperties:e,originalOptions:t,startTime:tt||ut(),duration:t.duration,tweens:[],createTween:function(e,t){var n=S.Tween(o,l.opts,e,t,l.opts.specialEasing[e]||l.opts.easing);return l.tweens.push(n),n},stop:function(e){var t=0,n=e?l.tweens.length:0;if(a)return this;for(a=!0;t<n;t++)l.tweens[t].run(1);return e?(s.notifyWith(o,[l,1,0]),s.resolveWith(o,[l,e])):s.rejectWith(o,[l,e]),this}}),c=l.props;for(!function(e,t){var n,r,i,o,a;for(n in e)if(i=t[r=X(n)],o=e[n],Array.isArray(o)&&(i=o[1],o=e[n]=o[0]),n!==r&&(e[r]=o,delete e[n]),(a=S.cssHooks[r])&&"expand"in a)for(n in o=a.expand(o),delete e[r],o)n in e||(e[n]=o[n],t[n]=i);else t[r]=i}(c,l.opts.specialEasing);r<i;r++)if(n=ft.prefilters[r].call(l,o,c,l.opts))return m(n.stop)&&(S._queueHooks(l.elem,l.opts.queue).stop=n.stop.bind(n)),n;return S.map(c,ct,l),m(l.opts.start)&&l.opts.start.call(o,l),l.progress(l.opts.progress).done(l.opts.done,l.opts.complete).fail(l.opts.fail).always(l.opts.always),S.fx.timer(S.extend(u,{elem:o,anim:l,queue:l.opts.queue})),l}S.Animation=S.extend(ft,{tweeners:{"*":[function(e,t){var n=this.createTween(e,t);return se(n.elem,e,te.exec(t),n),n}]},tweener:function(e,t){m(e)?(t=e,e=["*"]):e=e.match(P);for(var n,r=0,i=e.length;r<i;r++)n=e[r],ft.tweeners[n]=ft.tweeners[n]||[],ft.tweeners[n].unshift(t)},prefilters:[function(e,t,n){var r,i,o,a,s,u,l,c,f="width"in t||"height"in t,p=this,d={},h=e.style,g=e.nodeType&&ae(e),v=Y.get(e,"fxshow");for(r in n.queue||(null==(a=S._queueHooks(e,"fx")).unqueued&&(a.unqueued=0,s=a.empty.fire,a.empty.fire=function(){a.unqueued||s()}),a.unqueued++,p.always(function(){p.always(function(){a.unqueued--,S.queue(e,"fx").length||a.empty.fire()})})),t)if(i=t[r],ot.test(i)){if(delete t[r],o=o||"toggle"===i,i===(g?"hide":"show")){if("show"!==i||!v||void 0===v[r])continue;g=!0}d[r]=v&&v[r]||S.style(e,r)}if((u=!S.isEmptyObject(t))||!S.isEmptyObject(d))for(r in f&&1===e.nodeType&&(n.overflow=[h.overflow,h.overflowX,h.overflowY],null==(l=v&&v.display)&&(l=Y.get(e,"display")),"none"===(c=S.css(e,"display"))&&(l?c=l:(le([e],!0),l=e.style.display||l,c=S.css(e,"display"),le([e]))),("inline"===c||"inline-block"===c&&null!=l)&&"none"===S.css(e,"float")&&(u||(p.done(function(){h.display=l}),null==l&&(c=h.display,l="none"===c?"":c)),h.display="inline-block")),n.overflow&&(h.overflow="hidden",p.always(function(){h.overflow=n.overflow[0],h.overflowX=n.overflow[1],h.overflowY=n.overflow[2]})),u=!1,d)u||(v?"hidden"in v&&(g=v.hidden):v=Y.access(e,"fxshow",{display:l}),o&&(v.hidden=!g),g&&le([e],!0),p.done(function(){for(r in g||le([e]),Y.remove(e,"fxshow"),d)S.style(e,r,d[r])})),u=ct(g?v[r]:0,r,p),r in v||(v[r]=u.start,g&&(u.end=u.start,u.start=0))}],prefilter:function(e,t){t?ft.prefilters.unshift(e):ft.prefilters.push(e)}}),S.speed=function(e,t,n){var r=e&&"object"==typeof e?S.extend({},e):{complete:n||!n&&t||m(e)&&e,duration:e,easing:n&&t||t&&!m(t)&&t};return S.fx.off?r.duration=0:"number"!=typeof r.duration&&(r.duration in S.fx.speeds?r.duration=S.fx.speeds[r.duration]:r.duration=S.fx.speeds._default),null!=r.queue&&!0!==r.queue||(r.queue="fx"),r.old=r.complete,r.complete=function(){m(r.old)&&r.old.call(this),r.queue&&S.dequeue(this,r.queue)},r},S.fn.extend({fadeTo:function(e,t,n,r){return this.filter(ae).css("opacity",0).show().end().animate({opacity:t},e,n,r)},animate:function(t,e,n,r){var i=S.isEmptyObject(t),o=S.speed(e,n,r),a=function(){var e=ft(this,S.extend({},t),o);(i||Y.get(this,"finish"))&&e.stop(!0)};return a.finish=a,i||!1===o.queue?this.each(a):this.queue(o.queue,a)},stop:function(i,e,o){var a=function(e){var t=e.stop;delete e.stop,t(o)};return"string"!=typeof i&&(o=e,e=i,i=void 0),e&&this.queue(i||"fx",[]),this.each(function(){var e=!0,t=null!=i&&i+"queueHooks",n=S.timers,r=Y.get(this);if(t)r[t]&&r[t].stop&&a(r[t]);else for(t in r)r[t]&&r[t].stop&&at.test(t)&&a(r[t]);for(t=n.length;t--;)n[t].elem!==this||null!=i&&n[t].queue!==i||(n[t].anim.stop(o),e=!1,n.splice(t,1));!e&&o||S.dequeue(this,i)})},finish:function(a){return!1!==a&&(a=a||"fx"),this.each(function(){var e,t=Y.get(this),n=t[a+"queue"],r=t[a+"queueHooks"],i=S.timers,o=n?n.length:0;for(t.finish=!0,S.queue(this,a,[]),r&&r.stop&&r.stop.call(this,!0),e=i.length;e--;)i[e].elem===this&&i[e].queue===a&&(i[e].anim.stop(!0),i.splice(e,1));for(e=0;e<o;e++)n[e]&&n[e].finish&&n[e].finish.call(this);delete t.finish})}}),S.each(["toggle","show","hide"],function(e,r){var i=S.fn[r];S.fn[r]=function(e,t,n){return null==e||"boolean"==typeof e?i.apply(this,arguments):this.animate(lt(r,!0),e,t,n)}}),S.each({slideDown:lt("show"),slideUp:lt("hide"),slideToggle:lt("toggle"),fadeIn:{opacity:"show"},fadeOut:{opacity:"hide"},fadeToggle:{opacity:"toggle"}},function(e,r){S.fn[e]=function(e,t,n){return this.animate(r,e,t,n)}}),S.timers=[],S.fx.tick=function(){var e,t=0,n=S.timers;for(tt=Date.now();t<n.length;t++)(e=n[t])()||n[t]!==e||n.splice(t--,1);n.length||S.fx.stop(),tt=void 0},S.fx.timer=function(e){S.timers.push(e),S.fx.start()},S.fx.interval=13,S.fx.start=function(){nt||(nt=!0,st())},S.fx.stop=function(){nt=null},S.fx.speeds={slow:600,fast:200,_default:400},S.fn.delay=function(r,e){return r=S.fx&&S.fx.speeds[r]||r,e=e||"fx",this.queue(e,function(e,t){var n=C.setTimeout(e,r);t.stop=function(){C.clearTimeout(n)}})},rt=E.createElement("input"),it=E.createElement("select").appendChild(E.createElement("option")),rt.type="checkbox",y.checkOn=""!==rt.value,y.optSelected=it.selected,(rt=E.createElement("input")).value="t",rt.type="radio",y.radioValue="t"===rt.value;var pt,dt=S.expr.attrHandle;S.fn.extend({attr:function(e,t){return $(this,S.attr,e,t,1<arguments.length)},removeAttr:function(e){return this.each(function(){S.removeAttr(this,e)})}}),S.extend({attr:function(e,t,n){var r,i,o=e.nodeType;if(3!==o&&8!==o&&2!==o)return"undefined"==typeof e.getAttribute?S.prop(e,t,n):(1===o&&S.isXMLDoc(e)||(i=S.attrHooks[t.toLowerCase()]||(S.expr.match.bool.test(t)?pt:void 0)),void 0!==n?null===n?void S.removeAttr(e,t):i&&"set"in i&&void 0!==(r=i.set(e,n,t))?r:(e.setAttribute(t,n+""),n):i&&"get"in i&&null!==(r=i.get(e,t))?r:null==(r=S.find.attr(e,t))?void 0:r)},attrHooks:{type:{set:function(e,t){if(!y.radioValue&&"radio"===t&&A(e,"input")){var n=e.value;return e.setAttribute("type",t),n&&(e.value=n),t}}}},removeAttr:function(e,t){var n,r=0,i=t&&t.match(P);if(i&&1===e.nodeType)while(n=i[r++])e.removeAttribute(n)}}),pt={set:function(e,t,n){return!1===t?S.removeAttr(e,n):e.setAttribute(n,n),n}},S.each(S.expr.match.bool.source.match(/\w+/g),function(e,t){var a=dt[t]||S.find.attr;dt[t]=function(e,t,n){var r,i,o=t.toLowerCase();return n||(i=dt[o],dt[o]=r,r=null!=a(e,t,n)?o:null,dt[o]=i),r}});var ht=/^(?:input|select|textarea|button)$/i,gt=/^(?:a|area)$/i;function vt(e){return(e.match(P)||[]).join(" ")}function yt(e){return e.getAttribute&&e.getAttribute("class")||""}function mt(e){return Array.isArray(e)?e:"string"==typeof e&&e.match(P)||[]}S.fn.extend({prop:function(e,t){return $(this,S.prop,e,t,1<arguments.length)},removeProp:function(e){return this.each(function(){delete this[S.propFix[e]||e]})}}),S.extend({prop:function(e,t,n){var r,i,o=e.nodeType;if(3!==o&&8!==o&&2!==o)return 1===o&&S.isXMLDoc(e)||(t=S.propFix[t]||t,i=S.propHooks[t]),void 0!==n?i&&"set"in i&&void 0!==(r=i.set(e,n,t))?r:e[t]=n:i&&"get"in i&&null!==(r=i.get(e,t))?r:e[t]},propHooks:{tabIndex:{get:function(e){var t=S.find.attr(e,"tabindex");return t?parseInt(t,10):ht.test(e.nodeName)||gt.test(e.nodeName)&&e.href?0:-1}}},propFix:{"for":"htmlFor","class":"className"}}),y.optSelected||(S.propHooks.selected={get:function(e){var t=e.parentNode;return t&&t.parentNode&&t.parentNode.selectedIndex,null},set:function(e){var t=e.parentNode;t&&(t.selectedIndex,t.parentNode&&t.parentNode.selectedIndex)}}),S.each(["tabIndex","readOnly","maxLength","cellSpacing","cellPadding","rowSpan","colSpan","useMap","frameBorder","contentEditable"],function(){S.propFix[this.toLowerCase()]=this}),S.fn.extend({addClass:function(t){var e,n,r,i,o,a,s,u=0;if(m(t))return this.each(function(e){S(this).addClass(t.call(this,e,yt(this)))});if((e=mt(t)).length)while(n=this[u++])if(i=yt(n),r=1===n.nodeType&&" "+vt(i)+" "){a=0;while(o=e[a++])r.indexOf(" "+o+" ")<0&&(r+=o+" ");i!==(s=vt(r))&&n.setAttribute("class",s)}return this},removeClass:function(t){var e,n,r,i,o,a,s,u=0;if(m(t))return this.each(function(e){S(this).removeClass(t.call(this,e,yt(this)))});if(!arguments.length)return this.attr("class","");if((e=mt(t)).length)while(n=this[u++])if(i=yt(n),r=1===n.nodeType&&" "+vt(i)+" "){a=0;while(o=e[a++])while(-1<r.indexOf(" "+o+" "))r=r.replace(" "+o+" "," ");i!==(s=vt(r))&&n.setAttribute("class",s)}return this},toggleClass:function(i,t){var o=typeof i,a="string"===o||Array.isArray(i);return"boolean"==typeof t&&a?t?this.addClass(i):this.removeClass(i):m(i)?this.each(function(e){S(this).toggleClass(i.call(this,e,yt(this),t),t)}):this.each(function(){var e,t,n,r;if(a){t=0,n=S(this),r=mt(i);while(e=r[t++])n.hasClass(e)?n.removeClass(e):n.addClass(e)}else void 0!==i&&"boolean"!==o||((e=yt(this))&&Y.set(this,"__className__",e),this.setAttribute&&this.setAttribute("class",e||!1===i?"":Y.get(this,"__className__")||""))})},hasClass:function(e){var t,n,r=0;t=" "+e+" ";while(n=this[r++])if(1===n.nodeType&&-1<(" "+vt(yt(n))+" ").indexOf(t))return!0;return!1}});var xt=/\r/g;S.fn.extend({val:function(n){var r,e,i,t=this[0];return arguments.length?(i=m(n),this.each(function(e){var t;1===this.nodeType&&(null==(t=i?n.call(this,e,S(this).val()):n)?t="":"number"==typeof t?t+="":Array.isArray(t)&&(t=S.map(t,function(e){return null==e?"":e+""})),(r=S.valHooks[this.type]||S.valHooks[this.nodeName.toLowerCase()])&&"set"in r&&void 0!==r.set(this,t,"value")||(this.value=t))})):t?(r=S.valHooks[t.type]||S.valHooks[t.nodeName.toLowerCase()])&&"get"in r&&void 0!==(e=r.get(t,"value"))?e:"string"==typeof(e=t.value)?e.replace(xt,""):null==e?"":e:void 0}}),S.extend({valHooks:{option:{get:function(e){var t=S.find.attr(e,"value");return null!=t?t:vt(S.text(e))}},select:{get:function(e){var t,n,r,i=e.options,o=e.selectedIndex,a="select-one"===e.type,s=a?null:[],u=a?o+1:i.length;for(r=o<0?u:a?o:0;r<u;r++)if(((n=i[r]).selected||r===o)&&!n.disabled&&(!n.parentNode.disabled||!A(n.parentNode,"optgroup"))){if(t=S(n).val(),a)return t;s.push(t)}return s},set:function(e,t){var n,r,i=e.options,o=S.makeArray(t),a=i.length;while(a--)((r=i[a]).selected=-1<S.inArray(S.valHooks.option.get(r),o))&&(n=!0);return n||(e.selectedIndex=-1),o}}}}),S.each(["radio","checkbox"],function(){S.valHooks[this]={set:function(e,t){if(Array.isArray(t))return e.checked=-1<S.inArray(S(e).val(),t)}},y.checkOn||(S.valHooks[this].get=function(e){return null===e.getAttribute("value")?"on":e.value})}),y.focusin="onfocusin"in C;var bt=/^(?:focusinfocus|focusoutblur)$/,wt=function(e){e.stopPropagation()};S.extend(S.event,{trigger:function(e,t,n,r){var i,o,a,s,u,l,c,f,p=[n||E],d=v.call(e,"type")?e.type:e,h=v.call(e,"namespace")?e.namespace.split("."):[];if(o=f=a=n=n||E,3!==n.nodeType&&8!==n.nodeType&&!bt.test(d+S.event.triggered)&&(-1<d.indexOf(".")&&(d=(h=d.split(".")).shift(),h.sort()),u=d.indexOf(":")<0&&"on"+d,(e=e[S.expando]?e:new S.Event(d,"object"==typeof e&&e)).isTrigger=r?2:3,e.namespace=h.join("."),e.rnamespace=e.namespace?new RegExp("(^|\\.)"+h.join("\\.(?:.*\\.|)")+"(\\.|$)"):null,e.result=void 0,e.target||(e.target=n),t=null==t?[e]:S.makeArray(t,[e]),c=S.event.special[d]||{},r||!c.trigger||!1!==c.trigger.apply(n,t))){if(!r&&!c.noBubble&&!x(n)){for(s=c.delegateType||d,bt.test(s+d)||(o=o.parentNode);o;o=o.parentNode)p.push(o),a=o;a===(n.ownerDocument||E)&&p.push(a.defaultView||a.parentWindow||C)}i=0;while((o=p[i++])&&!e.isPropagationStopped())f=o,e.type=1<i?s:c.bindType||d,(l=(Y.get(o,"events")||Object.create(null))[e.type]&&Y.get(o,"handle"))&&l.apply(o,t),(l=u&&o[u])&&l.apply&&V(o)&&(e.result=l.apply(o,t),!1===e.result&&e.preventDefault());return e.type=d,r||e.isDefaultPrevented()||c._default&&!1!==c._default.apply(p.pop(),t)||!V(n)||u&&m(n[d])&&!x(n)&&((a=n[u])&&(n[u]=null),S.event.triggered=d,e.isPropagationStopped()&&f.addEventListener(d,wt),n[d](),e.isPropagationStopped()&&f.removeEventListener(d,wt),S.event.triggered=void 0,a&&(n[u]=a)),e.result}},simulate:function(e,t,n){var r=S.extend(new S.Event,n,{type:e,isSimulated:!0});S.event.trigger(r,null,t)}}),S.fn.extend({trigger:function(e,t){return this.each(function(){S.event.trigger(e,t,this)})},triggerHandler:function(e,t){var n=this[0];if(n)return S.event.trigger(e,t,n,!0)}}),y.focusin||S.each({focus:"focusin",blur:"focusout"},function(n,r){var i=function(e){S.event.simulate(r,e.target,S.event.fix(e))};S.event.special[r]={setup:function(){var e=this.ownerDocument||this.document||this,t=Y.access(e,r);t||e.addEventListener(n,i,!0),Y.access(e,r,(t||0)+1)},teardown:function(){var e=this.ownerDocument||this.document||this,t=Y.access(e,r)-1;t?Y.access(e,r,t):(e.removeEventListener(n,i,!0),Y.remove(e,r))}}});var Tt=C.location,Ct={guid:Date.now()},Et=/\?/;S.parseXML=function(e){var t;if(!e||"string"!=typeof e)return null;try{t=(new C.DOMParser).parseFromString(e,"text/xml")}catch(e){t=void 0}return t&&!t.getElementsByTagName("parsererror").length||S.error("Invalid XML: "+e),t};var St=/\[\]$/,kt=/\r?\n/g,At=/^(?:submit|button|image|reset|file)$/i,Nt=/^(?:input|select|textarea|keygen)/i;function Dt(n,e,r,i){var t;if(Array.isArray(e))S.each(e,function(e,t){r||St.test(n)?i(n,t):Dt(n+"["+("object"==typeof t&&null!=t?e:"")+"]",t,r,i)});else if(r||"object"!==w(e))i(n,e);else for(t in e)Dt(n+"["+t+"]",e[t],r,i)}S.param=function(e,t){var n,r=[],i=function(e,t){var n=m(t)?t():t;r[r.length]=encodeURIComponent(e)+"="+encodeURIComponent(null==n?"":n)};if(null==e)return"";if(Array.isArray(e)||e.jquery&&!S.isPlainObject(e))S.each(e,function(){i(this.name,this.value)});else for(n in e)Dt(n,e[n],t,i);return r.join("&")},S.fn.extend({serialize:function(){return S.param(this.serializeArray())},serializeArray:function(){return this.map(function(){var e=S.prop(this,"elements");return e?S.makeArray(e):this}).filter(function(){var e=this.type;return this.name&&!S(this).is(":disabled")&&Nt.test(this.nodeName)&&!At.test(e)&&(this.checked||!pe.test(e))}).map(function(e,t){var n=S(this).val();return null==n?null:Array.isArray(n)?S.map(n,function(e){return{name:t.name,value:e.replace(kt,"\r\n")}}):{name:t.name,value:n.replace(kt,"\r\n")}}).get()}});var jt=/%20/g,qt=/#.*$/,Lt=/([?&])_=[^&]*/,Ht=/^(.*?):[ \t]*([^\r\n]*)$/gm,Ot=/^(?:GET|HEAD)$/,Pt=/^\/\//,Rt={},Mt={},It="*/".concat("*"),Wt=E.createElement("a");function Ft(o){return function(e,t){"string"!=typeof e&&(t=e,e="*");var n,r=0,i=e.toLowerCase().match(P)||[];if(m(t))while(n=i[r++])"+"===n[0]?(n=n.slice(1)||"*",(o[n]=o[n]||[]).unshift(t)):(o[n]=o[n]||[]).push(t)}}function Bt(t,i,o,a){var s={},u=t===Mt;function l(e){var r;return s[e]=!0,S.each(t[e]||[],function(e,t){var n=t(i,o,a);return"string"!=typeof n||u||s[n]?u?!(r=n):void 0:(i.dataTypes.unshift(n),l(n),!1)}),r}return l(i.dataTypes[0])||!s["*"]&&l("*")}function $t(e,t){var n,r,i=S.ajaxSettings.flatOptions||{};for(n in t)void 0!==t[n]&&((i[n]?e:r||(r={}))[n]=t[n]);return r&&S.extend(!0,e,r),e}Wt.href=Tt.href,S.extend({active:0,lastModified:{},etag:{},ajaxSettings:{url:Tt.href,type:"GET",isLocal:/^(?:about|app|app-storage|.+-extension|file|res|widget):$/.test(Tt.protocol),global:!0,processData:!0,async:!0,contentType:"application/x-www-form-urlencoded; charset=UTF-8",accepts:{"*":It,text:"text/plain",html:"text/html",xml:"application/xml, text/xml",json:"application/json, text/javascript"},contents:{xml:/\bxml\b/,html:/\bhtml/,json:/\bjson\b/},responseFields:{xml:"responseXML",text:"responseText",json:"responseJSON"},converters:{"* text":String,"text html":!0,"text json":JSON.parse,"text xml":S.parseXML},flatOptions:{url:!0,context:!0}},ajaxSetup:function(e,t){return t?$t($t(e,S.ajaxSettings),t):$t(S.ajaxSettings,e)},ajaxPrefilter:Ft(Rt),ajaxTransport:Ft(Mt),ajax:function(e,t){"object"==typeof e&&(t=e,e=void 0),t=t||{};var c,f,p,n,d,r,h,g,i,o,v=S.ajaxSetup({},t),y=v.context||v,m=v.context&&(y.nodeType||y.jquery)?S(y):S.event,x=S.Deferred(),b=S.Callbacks("once memory"),w=v.statusCode||{},a={},s={},u="canceled",T={readyState:0,getResponseHeader:function(e){var t;if(h){if(!n){n={};while(t=Ht.exec(p))n[t[1].toLowerCase()+" "]=(n[t[1].toLowerCase()+" "]||[]).concat(t[2])}t=n[e.toLowerCase()+" "]}return null==t?null:t.join(", ")},getAllResponseHeaders:function(){return h?p:null},setRequestHeader:function(e,t){return null==h&&(e=s[e.toLowerCase()]=s[e.toLowerCase()]||e,a[e]=t),this},overrideMimeType:function(e){return null==h&&(v.mimeType=e),this},statusCode:function(e){var t;if(e)if(h)T.always(e[T.status]);else for(t in e)w[t]=[w[t],e[t]];return this},abort:function(e){var t=e||u;return c&&c.abort(t),l(0,t),this}};if(x.promise(T),v.url=((e||v.url||Tt.href)+"").replace(Pt,Tt.protocol+"//"),v.type=t.method||t.type||v.method||v.type,v.dataTypes=(v.dataType||"*").toLowerCase().match(P)||[""],null==v.crossDomain){r=E.createElement("a");try{r.href=v.url,r.href=r.href,v.crossDomain=Wt.protocol+"//"+Wt.host!=r.protocol+"//"+r.host}catch(e){v.crossDomain=!0}}if(v.data&&v.processData&&"string"!=typeof v.data&&(v.data=S.param(v.data,v.traditional)),Bt(Rt,v,t,T),h)return T;for(i in(g=S.event&&v.global)&&0==S.active++&&S.event.trigger("ajaxStart"),v.type=v.type.toUpperCase(),v.hasContent=!Ot.test(v.type),f=v.url.replace(qt,""),v.hasContent?v.data&&v.processData&&0===(v.contentType||"").indexOf("application/x-www-form-urlencoded")&&(v.data=v.data.replace(jt,"+")):(o=v.url.slice(f.length),v.data&&(v.processData||"string"==typeof v.data)&&(f+=(Et.test(f)?"&":"?")+v.data,delete v.data),!1===v.cache&&(f=f.replace(Lt,"$1"),o=(Et.test(f)?"&":"?")+"_="+Ct.guid+++o),v.url=f+o),v.ifModified&&(S.lastModified[f]&&T.setRequestHeader("If-Modified-Since",S.lastModified[f]),S.etag[f]&&T.setRequestHeader("If-None-Match",S.etag[f])),(v.data&&v.hasContent&&!1!==v.contentType||t.contentType)&&T.setRequestHeader("Content-Type",v.contentType),T.setRequestHeader("Accept",v.dataTypes[0]&&v.accepts[v.dataTypes[0]]?v.accepts[v.dataTypes[0]]+("*"!==v.dataTypes[0]?", "+It+"; q=0.01":""):v.accepts["*"]),v.headers)T.setRequestHeader(i,v.headers[i]);if(v.beforeSend&&(!1===v.beforeSend.call(y,T,v)||h))return T.abort();if(u="abort",b.add(v.complete),T.done(v.success),T.fail(v.error),c=Bt(Mt,v,t,T)){if(T.readyState=1,g&&m.trigger("ajaxSend",[T,v]),h)return T;v.async&&0<v.timeout&&(d=C.setTimeout(function(){T.abort("timeout")},v.timeout));try{h=!1,c.send(a,l)}catch(e){if(h)throw e;l(-1,e)}}else l(-1,"No Transport");function l(e,t,n,r){var i,o,a,s,u,l=t;h||(h=!0,d&&C.clearTimeout(d),c=void 0,p=r||"",T.readyState=0<e?4:0,i=200<=e&&e<300||304===e,n&&(s=function(e,t,n){var r,i,o,a,s=e.contents,u=e.dataTypes;while("*"===u[0])u.shift(),void 0===r&&(r=e.mimeType||t.getResponseHeader("Content-Type"));if(r)for(i in s)if(s[i]&&s[i].test(r)){u.unshift(i);break}if(u[0]in n)o=u[0];else{for(i in n){if(!u[0]||e.converters[i+" "+u[0]]){o=i;break}a||(a=i)}o=o||a}if(o)return o!==u[0]&&u.unshift(o),n[o]}(v,T,n)),!i&&-1<S.inArray("script",v.dataTypes)&&(v.converters["text script"]=function(){}),s=function(e,t,n,r){var i,o,a,s,u,l={},c=e.dataTypes.slice();if(c[1])for(a in e.converters)l[a.toLowerCase()]=e.converters[a];o=c.shift();while(o)if(e.responseFields[o]&&(n[e.responseFields[o]]=t),!u&&r&&e.dataFilter&&(t=e.dataFilter(t,e.dataType)),u=o,o=c.shift())if("*"===o)o=u;else if("*"!==u&&u!==o){if(!(a=l[u+" "+o]||l["* "+o]))for(i in l)if((s=i.split(" "))[1]===o&&(a=l[u+" "+s[0]]||l["* "+s[0]])){!0===a?a=l[i]:!0!==l[i]&&(o=s[0],c.unshift(s[1]));break}if(!0!==a)if(a&&e["throws"])t=a(t);else try{t=a(t)}catch(e){return{state:"parsererror",error:a?e:"No conversion from "+u+" to "+o}}}return{state:"success",data:t}}(v,s,T,i),i?(v.ifModified&&((u=T.getResponseHeader("Last-Modified"))&&(S.lastModified[f]=u),(u=T.getResponseHeader("etag"))&&(S.etag[f]=u)),204===e||"HEAD"===v.type?l="nocontent":304===e?l="notmodified":(l=s.state,o=s.data,i=!(a=s.error))):(a=l,!e&&l||(l="error",e<0&&(e=0))),T.status=e,T.statusText=(t||l)+"",i?x.resolveWith(y,[o,l,T]):x.rejectWith(y,[T,l,a]),T.statusCode(w),w=void 0,g&&m.trigger(i?"ajaxSuccess":"ajaxError",[T,v,i?o:a]),b.fireWith(y,[T,l]),g&&(m.trigger("ajaxComplete",[T,v]),--S.active||S.event.trigger("ajaxStop")))}return T},getJSON:function(e,t,n){return S.get(e,t,n,"json")},getScript:function(e,t){return S.get(e,void 0,t,"script")}}),S.each(["get","post"],function(e,i){S[i]=function(e,t,n,r){return m(t)&&(r=r||n,n=t,t=void 0),S.ajax(S.extend({url:e,type:i,dataType:r,data:t,success:n},S.isPlainObject(e)&&e))}}),S.ajaxPrefilter(function(e){var t;for(t in e.headers)"content-type"===t.toLowerCase()&&(e.contentType=e.headers[t]||"")}),S._evalUrl=function(e,t,n){return S.ajax({url:e,type:"GET",dataType:"script",cache:!0,async:!1,global:!1,converters:{"text script":function(){}},dataFilter:function(e){S.globalEval(e,t,n)}})},S.fn.extend({wrapAll:function(e){var t;return this[0]&&(m(e)&&(e=e.call(this[0])),t=S(e,this[0].ownerDocument).eq(0).clone(!0),this[0].parentNode&&t.insertBefore(this[0]),t.map(function(){var e=this;while(e.firstElementChild)e=e.firstElementChild;return e}).append(this)),this},wrapInner:function(n){return m(n)?this.each(function(e){S(this).wrapInner(n.call(this,e))}):this.each(function(){var e=S(this),t=e.contents();t.length?t.wrapAll(n):e.append(n)})},wrap:function(t){var n=m(t);return this.each(function(e){S(this).wrapAll(n?t.call(this,e):t)})},unwrap:function(e){return this.parent(e).not("body").each(function(){S(this).replaceWith(this.childNodes)}),this}}),S.expr.pseudos.hidden=function(e){return!S.expr.pseudos.visible(e)},S.expr.pseudos.visible=function(e){return!!(e.offsetWidth||e.offsetHeight||e.getClientRects().length)},S.ajaxSettings.xhr=function(){try{return new C.XMLHttpRequest}catch(e){}};var _t={0:200,1223:204},zt=S.ajaxSettings.xhr();y.cors=!!zt&&"withCredentials"in zt,y.ajax=zt=!!zt,S.ajaxTransport(function(i){var o,a;if(y.cors||zt&&!i.crossDomain)return{send:function(e,t){var n,r=i.xhr();if(r.open(i.type,i.url,i.async,i.username,i.password),i.xhrFields)for(n in i.xhrFields)r[n]=i.xhrFields[n];for(n in i.mimeType&&r.overrideMimeType&&r.overrideMimeType(i.mimeType),i.crossDomain||e["X-Requested-With"]||(e["X-Requested-With"]="XMLHttpRequest"),e)r.setRequestHeader(n,e[n]);o=function(e){return function(){o&&(o=a=r.onload=r.onerror=r.onabort=r.ontimeout=r.onreadystatechange=null,"abort"===e?r.abort():"error"===e?"number"!=typeof r.status?t(0,"error"):t(r.status,r.statusText):t(_t[r.status]||r.status,r.statusText,"text"!==(r.responseType||"text")||"string"!=typeof r.responseText?{binary:r.response}:{text:r.responseText},r.getAllResponseHeaders()))}},r.onload=o(),a=r.onerror=r.ontimeout=o("error"),void 0!==r.onabort?r.onabort=a:r.onreadystatechange=function(){4===r.readyState&&C.setTimeout(function(){o&&a()})},o=o("abort");try{r.send(i.hasContent&&i.data||null)}catch(e){if(o)throw e}},abort:function(){o&&o()}}}),S.ajaxPrefilter(function(e){e.crossDomain&&(e.contents.script=!1)}),S.ajaxSetup({accepts:{script:"text/javascript, application/javascript, application/ecmascript, application/x-ecmascript"},contents:{script:/\b(?:java|ecma)script\b/},converters:{"text script":function(e){return S.globalEval(e),e}}}),S.ajaxPrefilter("script",function(e){void 0===e.cache&&(e.cache=!1),e.crossDomain&&(e.type="GET")}),S.ajaxTransport("script",function(n){var r,i;if(n.crossDomain||n.scriptAttrs)return{send:function(e,t){r=S("<script>").attr(n.scriptAttrs||{}).prop({charset:n.scriptCharset,src:n.url}).on("load error",i=function(e){r.remove(),i=null,e&&t("error"===e.type?404:200,e.type)}),E.head.appendChild(r[0])},abort:function(){i&&i()}}});var Ut,Xt=[],Vt=/(=)\?(?=&|$)|\?\?/;S.ajaxSetup({jsonp:"callback",jsonpCallback:function(){var e=Xt.pop()||S.expando+"_"+Ct.guid++;return this[e]=!0,e}}),S.ajaxPrefilter("json jsonp",function(e,t,n){var r,i,o,a=!1!==e.jsonp&&(Vt.test(e.url)?"url":"string"==typeof e.data&&0===(e.contentType||"").indexOf("application/x-www-form-urlencoded")&&Vt.test(e.data)&&"data");if(a||"jsonp"===e.dataTypes[0])return r=e.jsonpCallback=m(e.jsonpCallback)?e.jsonpCallback():e.jsonpCallback,a?e[a]=e[a].replace(Vt,"$1"+r):!1!==e.jsonp&&(e.url+=(Et.test(e.url)?"&":"?")+e.jsonp+"="+r),e.converters["script json"]=function(){return o||S.error(r+" was not called"),o[0]},e.dataTypes[0]="json",i=C[r],C[r]=function(){o=arguments},n.always(function(){void 0===i?S(C).removeProp(r):C[r]=i,e[r]&&(e.jsonpCallback=t.jsonpCallback,Xt.push(r)),o&&m(i)&&i(o[0]),o=i=void 0}),"script"}),y.createHTMLDocument=((Ut=E.implementation.createHTMLDocument("").body).innerHTML="<form></form><form></form>",2===Ut.childNodes.length),S.parseHTML=function(e,t,n){return"string"!=typeof e?[]:("boolean"==typeof t&&(n=t,t=!1),t||(y.createHTMLDocument?((r=(t=E.implementation.createHTMLDocument("")).createElement("base")).href=E.location.href,t.head.appendChild(r)):t=E),o=!n&&[],(i=N.exec(e))?[t.createElement(i[1])]:(i=xe([e],t,o),o&&o.length&&S(o).remove(),S.merge([],i.childNodes)));var r,i,o},S.fn.load=function(e,t,n){var r,i,o,a=this,s=e.indexOf(" ");return-1<s&&(r=vt(e.slice(s)),e=e.slice(0,s)),m(t)?(n=t,t=void 0):t&&"object"==typeof t&&(i="POST"),0<a.length&&S.ajax({url:e,type:i||"GET",dataType:"html",data:t}).done(function(e){o=arguments,a.html(r?S("<div>").append(S.parseHTML(e)).find(r):e)}).always(n&&function(e,t){a.each(function(){n.apply(this,o||[e.responseText,t,e])})}),this},S.expr.pseudos.animated=function(t){return S.grep(S.timers,function(e){return t===e.elem}).length},S.offset={setOffset:function(e,t,n){var r,i,o,a,s,u,l=S.css(e,"position"),c=S(e),f={};"static"===l&&(e.style.position="relative"),s=c.offset(),o=S.css(e,"top"),u=S.css(e,"left"),("absolute"===l||"fixed"===l)&&-1<(o+u).indexOf("auto")?(a=(r=c.position()).top,i=r.left):(a=parseFloat(o)||0,i=parseFloat(u)||0),m(t)&&(t=t.call(e,n,S.extend({},s))),null!=t.top&&(f.top=t.top-s.top+a),null!=t.left&&(f.left=t.left-s.left+i),"using"in t?t.using.call(e,f):("number"==typeof f.top&&(f.top+="px"),"number"==typeof f.left&&(f.left+="px"),c.css(f))}},S.fn.extend({offset:function(t){if(arguments.length)return void 0===t?this:this.each(function(e){S.offset.setOffset(this,t,e)});var e,n,r=this[0];return r?r.getClientRects().length?(e=r.getBoundingClientRect(),n=r.ownerDocument.defaultView,{top:e.top+n.pageYOffset,left:e.left+n.pageXOffset}):{top:0,left:0}:void 0},position:function(){if(this[0]){var e,t,n,r=this[0],i={top:0,left:0};if("fixed"===S.css(r,"position"))t=r.getBoundingClientRect();else{t=this.offset(),n=r.ownerDocument,e=r.offsetParent||n.documentElement;while(e&&(e===n.body||e===n.documentElement)&&"static"===S.css(e,"position"))e=e.parentNode;e&&e!==r&&1===e.nodeType&&((i=S(e).offset()).top+=S.css(e,"borderTopWidth",!0),i.left+=S.css(e,"borderLeftWidth",!0))}return{top:t.top-i.top-S.css(r,"marginTop",!0),left:t.left-i.left-S.css(r,"marginLeft",!0)}}},offsetParent:function(){return this.map(function(){var e=this.offsetParent;while(e&&"static"===S.css(e,"position"))e=e.offsetParent;return e||re})}}),S.each({scrollLeft:"pageXOffset",scrollTop:"pageYOffset"},function(t,i){var o="pageYOffset"===i;S.fn[t]=function(e){return $(this,function(e,t,n){var r;if(x(e)?r=e:9===e.nodeType&&(r=e.defaultView),void 0===n)return r?r[i]:e[t];r?r.scrollTo(o?r.pageXOffset:n,o?n:r.pageYOffset):e[t]=n},t,e,arguments.length)}}),S.each(["top","left"],function(e,n){S.cssHooks[n]=$e(y.pixelPosition,function(e,t){if(t)return t=Be(e,n),Me.test(t)?S(e).position()[n]+"px":t})}),S.each({Height:"height",Width:"width"},function(a,s){S.each({padding:"inner"+a,content:s,"":"outer"+a},function(r,o){S.fn[o]=function(e,t){var n=arguments.length&&(r||"boolean"!=typeof e),i=r||(!0===e||!0===t?"margin":"border");return $(this,function(e,t,n){var r;return x(e)?0===o.indexOf("outer")?e["inner"+a]:e.document.documentElement["client"+a]:9===e.nodeType?(r=e.documentElement,Math.max(e.body["scroll"+a],r["scroll"+a],e.body["offset"+a],r["offset"+a],r["client"+a])):void 0===n?S.css(e,t,i):S.style(e,t,n,i)},s,n?e:void 0,n)}})}),S.each(["ajaxStart","ajaxStop","ajaxComplete","ajaxError","ajaxSuccess","ajaxSend"],function(e,t){S.fn[t]=function(e){return this.on(t,e)}}),S.fn.extend({bind:function(e,t,n){return this.on(e,null,t,n)},unbind:function(e,t){return this.off(e,null,t)},delegate:function(e,t,n,r){return this.on(t,e,n,r)},undelegate:function(e,t,n){return 1===arguments.length?this.off(e,"**"):this.off(t,e||"**",n)},hover:function(e,t){return this.mouseenter(e).mouseleave(t||e)}}),S.each("blur focus focusin focusout resize scroll click dblclick mousedown mouseup mousemove mouseover mouseout mouseenter mouseleave change select submit keydown keypress keyup contextmenu".split(" "),function(e,n){S.fn[n]=function(e,t){return 0<arguments.length?this.on(n,null,e,t):this.trigger(n)}});var Gt=/^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g;S.proxy=function(e,t){var n,r,i;if("string"==typeof t&&(n=e[t],t=e,e=n),m(e))return r=s.call(arguments,2),(i=function(){return e.apply(t||this,r.concat(s.call(arguments)))}).guid=e.guid=e.guid||S.guid++,i},S.holdReady=function(e){e?S.readyWait++:S.ready(!0)},S.isArray=Array.isArray,S.parseJSON=JSON.parse,S.nodeName=A,S.isFunction=m,S.isWindow=x,S.camelCase=X,S.type=w,S.now=Date.now,S.isNumeric=function(e){var t=S.type(e);return("number"===t||"string"===t)&&!isNaN(e-parseFloat(e))},S.trim=function(e){return null==e?"":(e+"").replace(Gt,"")},"function"==typeof define&&define.amd&&define("jquery",[],function(){return S});var Yt=C.jQuery,Qt=C.$;return S.noConflict=function(e){return C.$===S&&(C.$=Qt),e&&C.jQuery===S&&(C.jQuery=Yt),S},"undefined"==typeof e&&(C.jQuery=C.$=S),S});
+/*! jQuery v3.6.0 | (c) OpenJS Foundation and other contributors | jquery.org/license */
+!function(e,t){"use strict";"object"==typeof module&&"object"==typeof module.exports?module.exports=e.document?t(e,!0):function(e){if(!e.document)throw new Error("jQuery requires a window with a document");return t(e)}:t(e)}("undefined"!=typeof window?window:this,function(C,e){"use strict";var t=[],r=Object.getPrototypeOf,s=t.slice,g=t.flat?function(e){return t.flat.call(e)}:function(e){return t.concat.apply([],e)},u=t.push,i=t.indexOf,n={},o=n.toString,v=n.hasOwnProperty,a=v.toString,l=a.call(Object),y={},m=function(e){return"function"==typeof e&&"number"!=typeof e.nodeType&&"function"!=typeof e.item},x=function(e){return null!=e&&e===e.window},E=C.document,c={type:!0,src:!0,nonce:!0,noModule:!0};function b(e,t,n){var r,i,o=(n=n||E).createElement("script");if(o.text=e,t)for(r in c)(i=t[r]||t.getAttribute&&t.getAttribute(r))&&o.setAttribute(r,i);n.head.appendChild(o).parentNode.removeChild(o)}function w(e){return null==e?e+"":"object"==typeof e||"function"==typeof e?n[o.call(e)]||"object":typeof e}var f="3.6.0",S=function(e,t){return new S.fn.init(e,t)};function p(e){var t=!!e&&"length"in e&&e.length,n=w(e);return!m(e)&&!x(e)&&("array"===n||0===t||"number"==typeof t&&0<t&&t-1 in e)}S.fn=S.prototype={jquery:f,constructor:S,length:0,toArray:function(){return s.call(this)},get:function(e){return null==e?s.call(this):e<0?this[e+this.length]:this[e]},pushStack:function(e){var t=S.merge(this.constructor(),e);return t.prevObject=this,t},each:function(e){return S.each(this,e)},map:function(n){return this.pushStack(S.map(this,function(e,t){return n.call(e,t,e)}))},slice:function(){return this.pushStack(s.apply(this,arguments))},first:function(){return this.eq(0)},last:function(){return this.eq(-1)},even:function(){return this.pushStack(S.grep(this,function(e,t){return(t+1)%2}))},odd:function(){return this.pushStack(S.grep(this,function(e,t){return t%2}))},eq:function(e){var t=this.length,n=+e+(e<0?t:0);return this.pushStack(0<=n&&n<t?[this[n]]:[])},end:function(){return this.prevObject||this.constructor()},push:u,sort:t.sort,splice:t.splice},S.extend=S.fn.extend=function(){var e,t,n,r,i,o,a=arguments[0]||{},s=1,u=arguments.length,l=!1;for("boolean"==typeof a&&(l=a,a=arguments[s]||{},s++),"object"==typeof a||m(a)||(a={}),s===u&&(a=this,s--);s<u;s++)if(null!=(e=arguments[s]))for(t in e)r=e[t],"__proto__"!==t&&a!==r&&(l&&r&&(S.isPlainObject(r)||(i=Array.isArray(r)))?(n=a[t],o=i&&!Array.isArray(n)?[]:i||S.isPlainObject(n)?n:{},i=!1,a[t]=S.extend(l,o,r)):void 0!==r&&(a[t]=r));return a},S.extend({expando:"jQuery"+(f+Math.random()).replace(/\D/g,""),isReady:!0,error:function(e){throw new Error(e)},noop:function(){},isPlainObject:function(e){var t,n;return!(!e||"[object Object]"!==o.call(e))&&(!(t=r(e))||"function"==typeof(n=v.call(t,"constructor")&&t.constructor)&&a.call(n)===l)},isEmptyObject:function(e){var t;for(t in e)return!1;return!0},globalEval:function(e,t,n){b(e,{nonce:t&&t.nonce},n)},each:function(e,t){var n,r=0;if(p(e)){for(n=e.length;r<n;r++)if(!1===t.call(e[r],r,e[r]))break}else for(r in e)if(!1===t.call(e[r],r,e[r]))break;return e},makeArray:function(e,t){var n=t||[];return null!=e&&(p(Object(e))?S.merge(n,"string"==typeof e?[e]:e):u.call(n,e)),n},inArray:function(e,t,n){return null==t?-1:i.call(t,e,n)},merge:function(e,t){for(var n=+t.length,r=0,i=e.length;r<n;r++)e[i++]=t[r];return e.length=i,e},grep:function(e,t,n){for(var r=[],i=0,o=e.length,a=!n;i<o;i++)!t(e[i],i)!==a&&r.push(e[i]);return r},map:function(e,t,n){var r,i,o=0,a=[];if(p(e))for(r=e.length;o<r;o++)null!=(i=t(e[o],o,n))&&a.push(i);else for(o in e)null!=(i=t(e[o],o,n))&&a.push(i);return g(a)},guid:1,support:y}),"function"==typeof Symbol&&(S.fn[Symbol.iterator]=t[Symbol.iterator]),S.each("Boolean Number String Function Array Date RegExp Object Error Symbol".split(" "),function(e,t){n["[object "+t+"]"]=t.toLowerCase()});var d=function(n){var e,d,b,o,i,h,f,g,w,u,l,T,C,a,E,v,s,c,y,S="sizzle"+1*new Date,p=n.document,k=0,r=0,m=ue(),x=ue(),A=ue(),N=ue(),j=function(e,t){return e===t&&(l=!0),0},D={}.hasOwnProperty,t=[],q=t.pop,L=t.push,H=t.push,O=t.slice,P=function(e,t){for(var n=0,r=e.length;n<r;n++)if(e[n]===t)return n;return-1},R="checked|selected|async|autofocus|autoplay|controls|defer|disabled|hidden|ismap|loop|multiple|open|readonly|required|scoped",M="[\\x20\\t\\r\\n\\f]",I="(?:\\\\[\\da-fA-F]{1,6}"+M+"?|\\\\[^\\r\\n\\f]|[\\w-]|[^\0-\\x7f])+",W="\\["+M+"*("+I+")(?:"+M+"*([*^$|!~]?=)"+M+"*(?:'((?:\\\\.|[^\\\\'])*)'|\"((?:\\\\.|[^\\\\\"])*)\"|("+I+"))|)"+M+"*\\]",F=":("+I+")(?:\\((('((?:\\\\.|[^\\\\'])*)'|\"((?:\\\\.|[^\\\\\"])*)\")|((?:\\\\.|[^\\\\()[\\]]|"+W+")*)|.*)\\)|)",B=new RegExp(M+"+","g"),$=new RegExp("^"+M+"+|((?:^|[^\\\\])(?:\\\\.)*)"+M+"+$","g"),_=new RegExp("^"+M+"*,"+M+"*"),z=new RegExp("^"+M+"*([>+~]|"+M+")"+M+"*"),U=new RegExp(M+"|>"),X=new RegExp(F),V=new RegExp("^"+I+"$"),G={ID:new RegExp("^#("+I+")"),CLASS:new RegExp("^\\.("+I+")"),TAG:new RegExp("^("+I+"|[*])"),ATTR:new RegExp("^"+W),PSEUDO:new RegExp("^"+F),CHILD:new RegExp("^:(only|first|last|nth|nth-last)-(child|of-type)(?:\\("+M+"*(even|odd|(([+-]|)(\\d*)n|)"+M+"*(?:([+-]|)"+M+"*(\\d+)|))"+M+"*\\)|)","i"),bool:new RegExp("^(?:"+R+")$","i"),needsContext:new RegExp("^"+M+"*[>+~]|:(even|odd|eq|gt|lt|nth|first|last)(?:\\("+M+"*((?:-\\d)?\\d*)"+M+"*\\)|)(?=[^-]|$)","i")},Y=/HTML$/i,Q=/^(?:input|select|textarea|button)$/i,J=/^h\d$/i,K=/^[^{]+\{\s*\[native \w/,Z=/^(?:#([\w-]+)|(\w+)|\.([\w-]+))$/,ee=/[+~]/,te=new RegExp("\\\\[\\da-fA-F]{1,6}"+M+"?|\\\\([^\\r\\n\\f])","g"),ne=function(e,t){var n="0x"+e.slice(1)-65536;return t||(n<0?String.fromCharCode(n+65536):String.fromCharCode(n>>10|55296,1023&n|56320))},re=/([\0-\x1f\x7f]|^-?\d)|^-$|[^\0-\x1f\x7f-\uFFFF\w-]/g,ie=function(e,t){return t?"\0"===e?"\ufffd":e.slice(0,-1)+"\\"+e.charCodeAt(e.length-1).toString(16)+" ":"\\"+e},oe=function(){T()},ae=be(function(e){return!0===e.disabled&&"fieldset"===e.nodeName.toLowerCase()},{dir:"parentNode",next:"legend"});try{H.apply(t=O.call(p.childNodes),p.childNodes),t[p.childNodes.length].nodeType}catch(e){H={apply:t.length?function(e,t){L.apply(e,O.call(t))}:function(e,t){var n=e.length,r=0;while(e[n++]=t[r++]);e.length=n-1}}}function se(t,e,n,r){var i,o,a,s,u,l,c,f=e&&e.ownerDocument,p=e?e.nodeType:9;if(n=n||[],"string"!=typeof t||!t||1!==p&&9!==p&&11!==p)return n;if(!r&&(T(e),e=e||C,E)){if(11!==p&&(u=Z.exec(t)))if(i=u[1]){if(9===p){if(!(a=e.getElementById(i)))return n;if(a.id===i)return n.push(a),n}else if(f&&(a=f.getElementById(i))&&y(e,a)&&a.id===i)return n.push(a),n}else{if(u[2])return H.apply(n,e.getElementsByTagName(t)),n;if((i=u[3])&&d.getElementsByClassName&&e.getElementsByClassName)return H.apply(n,e.getElementsByClassName(i)),n}if(d.qsa&&!N[t+" "]&&(!v||!v.test(t))&&(1!==p||"object"!==e.nodeName.toLowerCase())){if(c=t,f=e,1===p&&(U.test(t)||z.test(t))){(f=ee.test(t)&&ye(e.parentNode)||e)===e&&d.scope||((s=e.getAttribute("id"))?s=s.replace(re,ie):e.setAttribute("id",s=S)),o=(l=h(t)).length;while(o--)l[o]=(s?"#"+s:":scope")+" "+xe(l[o]);c=l.join(",")}try{return H.apply(n,f.querySelectorAll(c)),n}catch(e){N(t,!0)}finally{s===S&&e.removeAttribute("id")}}}return g(t.replace($,"$1"),e,n,r)}function ue(){var r=[];return function e(t,n){return r.push(t+" ")>b.cacheLength&&delete e[r.shift()],e[t+" "]=n}}function le(e){return e[S]=!0,e}function ce(e){var t=C.createElement("fieldset");try{return!!e(t)}catch(e){return!1}finally{t.parentNode&&t.parentNode.removeChild(t),t=null}}function fe(e,t){var n=e.split("|"),r=n.length;while(r--)b.attrHandle[n[r]]=t}function pe(e,t){var n=t&&e,r=n&&1===e.nodeType&&1===t.nodeType&&e.sourceIndex-t.sourceIndex;if(r)return r;if(n)while(n=n.nextSibling)if(n===t)return-1;return e?1:-1}function de(t){return function(e){return"input"===e.nodeName.toLowerCase()&&e.type===t}}function he(n){return function(e){var t=e.nodeName.toLowerCase();return("input"===t||"button"===t)&&e.type===n}}function ge(t){return function(e){return"form"in e?e.parentNode&&!1===e.disabled?"label"in e?"label"in e.parentNode?e.parentNode.disabled===t:e.disabled===t:e.isDisabled===t||e.isDisabled!==!t&&ae(e)===t:e.disabled===t:"label"in e&&e.disabled===t}}function ve(a){return le(function(o){return o=+o,le(function(e,t){var n,r=a([],e.length,o),i=r.length;while(i--)e[n=r[i]]&&(e[n]=!(t[n]=e[n]))})})}function ye(e){return e&&"undefined"!=typeof e.getElementsByTagName&&e}for(e in d=se.support={},i=se.isXML=function(e){var t=e&&e.namespaceURI,n=e&&(e.ownerDocument||e).documentElement;return!Y.test(t||n&&n.nodeName||"HTML")},T=se.setDocument=function(e){var t,n,r=e?e.ownerDocument||e:p;return r!=C&&9===r.nodeType&&r.documentElement&&(a=(C=r).documentElement,E=!i(C),p!=C&&(n=C.defaultView)&&n.top!==n&&(n.addEventListener?n.addEventListener("unload",oe,!1):n.attachEvent&&n.attachEvent("onunload",oe)),d.scope=ce(function(e){return a.appendChild(e).appendChild(C.createElement("div")),"undefined"!=typeof e.querySelectorAll&&!e.querySelectorAll(":scope fieldset div").length}),d.attributes=ce(function(e){return e.className="i",!e.getAttribute("className")}),d.getElementsByTagName=ce(function(e){return e.appendChild(C.createComment("")),!e.getElementsByTagName("*").length}),d.getElementsByClassName=K.test(C.getElementsByClassName),d.getById=ce(function(e){return a.appendChild(e).id=S,!C.getElementsByName||!C.getElementsByName(S).length}),d.getById?(b.filter.ID=function(e){var t=e.replace(te,ne);return function(e){return e.getAttribute("id")===t}},b.find.ID=function(e,t){if("undefined"!=typeof t.getElementById&&E){var n=t.getElementById(e);return n?[n]:[]}}):(b.filter.ID=function(e){var n=e.replace(te,ne);return function(e){var t="undefined"!=typeof e.getAttributeNode&&e.getAttributeNode("id");return t&&t.value===n}},b.find.ID=function(e,t){if("undefined"!=typeof t.getElementById&&E){var n,r,i,o=t.getElementById(e);if(o){if((n=o.getAttributeNode("id"))&&n.value===e)return[o];i=t.getElementsByName(e),r=0;while(o=i[r++])if((n=o.getAttributeNode("id"))&&n.value===e)return[o]}return[]}}),b.find.TAG=d.getElementsByTagName?function(e,t){return"undefined"!=typeof t.getElementsByTagName?t.getElementsByTagName(e):d.qsa?t.querySelectorAll(e):void 0}:function(e,t){var n,r=[],i=0,o=t.getElementsByTagName(e);if("*"===e){while(n=o[i++])1===n.nodeType&&r.push(n);return r}return o},b.find.CLASS=d.getElementsByClassName&&function(e,t){if("undefined"!=typeof t.getElementsByClassName&&E)return t.getElementsByClassName(e)},s=[],v=[],(d.qsa=K.test(C.querySelectorAll))&&(ce(function(e){var t;a.appendChild(e).innerHTML="<a id='"+S+"'></a><select id='"+S+"-\r\\' msallowcapture=''><option selected=''></option></select>",e.querySelectorAll("[msallowcapture^='']").length&&v.push("[*^$]="+M+"*(?:''|\"\")"),e.querySelectorAll("[selected]").length||v.push("\\["+M+"*(?:value|"+R+")"),e.querySelectorAll("[id~="+S+"-]").length||v.push("~="),(t=C.createElement("input")).setAttribute("name",""),e.appendChild(t),e.querySelectorAll("[name='']").length||v.push("\\["+M+"*name"+M+"*="+M+"*(?:''|\"\")"),e.querySelectorAll(":checked").length||v.push(":checked"),e.querySelectorAll("a#"+S+"+*").length||v.push(".#.+[+~]"),e.querySelectorAll("\\\f"),v.push("[\\r\\n\\f]")}),ce(function(e){e.innerHTML="<a href='' disabled='disabled'></a><select disabled='disabled'><option/></select>";var t=C.createElement("input");t.setAttribute("type","hidden"),e.appendChild(t).setAttribute("name","D"),e.querySelectorAll("[name=d]").length&&v.push("name"+M+"*[*^$|!~]?="),2!==e.querySelectorAll(":enabled").length&&v.push(":enabled",":disabled"),a.appendChild(e).disabled=!0,2!==e.querySelectorAll(":disabled").length&&v.push(":enabled",":disabled"),e.querySelectorAll("*,:x"),v.push(",.*:")})),(d.matchesSelector=K.test(c=a.matches||a.webkitMatchesSelector||a.mozMatchesSelector||a.oMatchesSelector||a.msMatchesSelector))&&ce(function(e){d.disconnectedMatch=c.call(e,"*"),c.call(e,"[s!='']:x"),s.push("!=",F)}),v=v.length&&new RegExp(v.join("|")),s=s.length&&new RegExp(s.join("|")),t=K.test(a.compareDocumentPosition),y=t||K.test(a.contains)?function(e,t){var n=9===e.nodeType?e.documentElement:e,r=t&&t.parentNode;return e===r||!(!r||1!==r.nodeType||!(n.contains?n.contains(r):e.compareDocumentPosition&&16&e.compareDocumentPosition(r)))}:function(e,t){if(t)while(t=t.parentNode)if(t===e)return!0;return!1},j=t?function(e,t){if(e===t)return l=!0,0;var n=!e.compareDocumentPosition-!t.compareDocumentPosition;return n||(1&(n=(e.ownerDocument||e)==(t.ownerDocument||t)?e.compareDocumentPosition(t):1)||!d.sortDetached&&t.compareDocumentPosition(e)===n?e==C||e.ownerDocument==p&&y(p,e)?-1:t==C||t.ownerDocument==p&&y(p,t)?1:u?P(u,e)-P(u,t):0:4&n?-1:1)}:function(e,t){if(e===t)return l=!0,0;var n,r=0,i=e.parentNode,o=t.parentNode,a=[e],s=[t];if(!i||!o)return e==C?-1:t==C?1:i?-1:o?1:u?P(u,e)-P(u,t):0;if(i===o)return pe(e,t);n=e;while(n=n.parentNode)a.unshift(n);n=t;while(n=n.parentNode)s.unshift(n);while(a[r]===s[r])r++;return r?pe(a[r],s[r]):a[r]==p?-1:s[r]==p?1:0}),C},se.matches=function(e,t){return se(e,null,null,t)},se.matchesSelector=function(e,t){if(T(e),d.matchesSelector&&E&&!N[t+" "]&&(!s||!s.test(t))&&(!v||!v.test(t)))try{var n=c.call(e,t);if(n||d.disconnectedMatch||e.document&&11!==e.document.nodeType)return n}catch(e){N(t,!0)}return 0<se(t,C,null,[e]).length},se.contains=function(e,t){return(e.ownerDocument||e)!=C&&T(e),y(e,t)},se.attr=function(e,t){(e.ownerDocument||e)!=C&&T(e);var n=b.attrHandle[t.toLowerCase()],r=n&&D.call(b.attrHandle,t.toLowerCase())?n(e,t,!E):void 0;return void 0!==r?r:d.attributes||!E?e.getAttribute(t):(r=e.getAttributeNode(t))&&r.specified?r.value:null},se.escape=function(e){return(e+"").replace(re,ie)},se.error=function(e){throw new Error("Syntax error, unrecognized expression: "+e)},se.uniqueSort=function(e){var t,n=[],r=0,i=0;if(l=!d.detectDuplicates,u=!d.sortStable&&e.slice(0),e.sort(j),l){while(t=e[i++])t===e[i]&&(r=n.push(i));while(r--)e.splice(n[r],1)}return u=null,e},o=se.getText=function(e){var t,n="",r=0,i=e.nodeType;if(i){if(1===i||9===i||11===i){if("string"==typeof e.textContent)return e.textContent;for(e=e.firstChild;e;e=e.nextSibling)n+=o(e)}else if(3===i||4===i)return e.nodeValue}else while(t=e[r++])n+=o(t);return n},(b=se.selectors={cacheLength:50,createPseudo:le,match:G,attrHandle:{},find:{},relative:{">":{dir:"parentNode",first:!0}," ":{dir:"parentNode"},"+":{dir:"previousSibling",first:!0},"~":{dir:"previousSibling"}},preFilter:{ATTR:function(e){return e[1]=e[1].replace(te,ne),e[3]=(e[3]||e[4]||e[5]||"").replace(te,ne),"~="===e[2]&&(e[3]=" "+e[3]+" "),e.slice(0,4)},CHILD:function(e){return e[1]=e[1].toLowerCase(),"nth"===e[1].slice(0,3)?(e[3]||se.error(e[0]),e[4]=+(e[4]?e[5]+(e[6]||1):2*("even"===e[3]||"odd"===e[3])),e[5]=+(e[7]+e[8]||"odd"===e[3])):e[3]&&se.error(e[0]),e},PSEUDO:function(e){var t,n=!e[6]&&e[2];return G.CHILD.test(e[0])?null:(e[3]?e[2]=e[4]||e[5]||"":n&&X.test(n)&&(t=h(n,!0))&&(t=n.indexOf(")",n.length-t)-n.length)&&(e[0]=e[0].slice(0,t),e[2]=n.slice(0,t)),e.slice(0,3))}},filter:{TAG:function(e){var t=e.replace(te,ne).toLowerCase();return"*"===e?function(){return!0}:function(e){return e.nodeName&&e.nodeName.toLowerCase()===t}},CLASS:function(e){var t=m[e+" "];return t||(t=new RegExp("(^|"+M+")"+e+"("+M+"|$)"))&&m(e,function(e){return t.test("string"==typeof e.className&&e.className||"undefined"!=typeof e.getAttribute&&e.getAttribute("class")||"")})},ATTR:function(n,r,i){return function(e){var t=se.attr(e,n);return null==t?"!="===r:!r||(t+="","="===r?t===i:"!="===r?t!==i:"^="===r?i&&0===t.indexOf(i):"*="===r?i&&-1<t.indexOf(i):"$="===r?i&&t.slice(-i.length)===i:"~="===r?-1<(" "+t.replace(B," ")+" ").indexOf(i):"|="===r&&(t===i||t.slice(0,i.length+1)===i+"-"))}},CHILD:function(h,e,t,g,v){var y="nth"!==h.slice(0,3),m="last"!==h.slice(-4),x="of-type"===e;return 1===g&&0===v?function(e){return!!e.parentNode}:function(e,t,n){var r,i,o,a,s,u,l=y!==m?"nextSibling":"previousSibling",c=e.parentNode,f=x&&e.nodeName.toLowerCase(),p=!n&&!x,d=!1;if(c){if(y){while(l){a=e;while(a=a[l])if(x?a.nodeName.toLowerCase()===f:1===a.nodeType)return!1;u=l="only"===h&&!u&&"nextSibling"}return!0}if(u=[m?c.firstChild:c.lastChild],m&&p){d=(s=(r=(i=(o=(a=c)[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]||[])[0]===k&&r[1])&&r[2],a=s&&c.childNodes[s];while(a=++s&&a&&a[l]||(d=s=0)||u.pop())if(1===a.nodeType&&++d&&a===e){i[h]=[k,s,d];break}}else if(p&&(d=s=(r=(i=(o=(a=e)[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]||[])[0]===k&&r[1]),!1===d)while(a=++s&&a&&a[l]||(d=s=0)||u.pop())if((x?a.nodeName.toLowerCase()===f:1===a.nodeType)&&++d&&(p&&((i=(o=a[S]||(a[S]={}))[a.uniqueID]||(o[a.uniqueID]={}))[h]=[k,d]),a===e))break;return(d-=v)===g||d%g==0&&0<=d/g}}},PSEUDO:function(e,o){var t,a=b.pseudos[e]||b.setFilters[e.toLowerCase()]||se.error("unsupported pseudo: "+e);return a[S]?a(o):1<a.length?(t=[e,e,"",o],b.setFilters.hasOwnProperty(e.toLowerCase())?le(function(e,t){var n,r=a(e,o),i=r.length;while(i--)e[n=P(e,r[i])]=!(t[n]=r[i])}):function(e){return a(e,0,t)}):a}},pseudos:{not:le(function(e){var r=[],i=[],s=f(e.replace($,"$1"));return s[S]?le(function(e,t,n,r){var i,o=s(e,null,r,[]),a=e.length;while(a--)(i=o[a])&&(e[a]=!(t[a]=i))}):function(e,t,n){return r[0]=e,s(r,null,n,i),r[0]=null,!i.pop()}}),has:le(function(t){return function(e){return 0<se(t,e).length}}),contains:le(function(t){return t=t.replace(te,ne),function(e){return-1<(e.textContent||o(e)).indexOf(t)}}),lang:le(function(n){return V.test(n||"")||se.error("unsupported lang: "+n),n=n.replace(te,ne).toLowerCase(),function(e){var t;do{if(t=E?e.lang:e.getAttribute("xml:lang")||e.getAttribute("lang"))return(t=t.toLowerCase())===n||0===t.indexOf(n+"-")}while((e=e.parentNode)&&1===e.nodeType);return!1}}),target:function(e){var t=n.location&&n.location.hash;return t&&t.slice(1)===e.id},root:function(e){return e===a},focus:function(e){return e===C.activeElement&&(!C.hasFocus||C.hasFocus())&&!!(e.type||e.href||~e.tabIndex)},enabled:ge(!1),disabled:ge(!0),checked:function(e){var t=e.nodeName.toLowerCase();return"input"===t&&!!e.checked||"option"===t&&!!e.selected},selected:function(e){return e.parentNode&&e.parentNode.selectedIndex,!0===e.selected},empty:function(e){for(e=e.firstChild;e;e=e.nextSibling)if(e.nodeType<6)return!1;return!0},parent:function(e){return!b.pseudos.empty(e)},header:function(e){return J.test(e.nodeName)},input:function(e){return Q.test(e.nodeName)},button:function(e){var t=e.nodeName.toLowerCase();return"input"===t&&"button"===e.type||"button"===t},text:function(e){var t;return"input"===e.nodeName.toLowerCase()&&"text"===e.type&&(null==(t=e.getAttribute("type"))||"text"===t.toLowerCase())},first:ve(function(){return[0]}),last:ve(function(e,t){return[t-1]}),eq:ve(function(e,t,n){return[n<0?n+t:n]}),even:ve(function(e,t){for(var n=0;n<t;n+=2)e.push(n);return e}),odd:ve(function(e,t){for(var n=1;n<t;n+=2)e.push(n);return e}),lt:ve(function(e,t,n){for(var r=n<0?n+t:t<n?t:n;0<=--r;)e.push(r);return e}),gt:ve(function(e,t,n){for(var r=n<0?n+t:n;++r<t;)e.push(r);return e})}}).pseudos.nth=b.pseudos.eq,{radio:!0,checkbox:!0,file:!0,password:!0,image:!0})b.pseudos[e]=de(e);for(e in{submit:!0,reset:!0})b.pseudos[e]=he(e);function me(){}function xe(e){for(var t=0,n=e.length,r="";t<n;t++)r+=e[t].value;return r}function be(s,e,t){var u=e.dir,l=e.next,c=l||u,f=t&&"parentNode"===c,p=r++;return e.first?function(e,t,n){while(e=e[u])if(1===e.nodeType||f)return s(e,t,n);return!1}:function(e,t,n){var r,i,o,a=[k,p];if(n){while(e=e[u])if((1===e.nodeType||f)&&s(e,t,n))return!0}else while(e=e[u])if(1===e.nodeType||f)if(i=(o=e[S]||(e[S]={}))[e.uniqueID]||(o[e.uniqueID]={}),l&&l===e.nodeName.toLowerCase())e=e[u]||e;else{if((r=i[c])&&r[0]===k&&r[1]===p)return a[2]=r[2];if((i[c]=a)[2]=s(e,t,n))return!0}return!1}}function we(i){return 1<i.length?function(e,t,n){var r=i.length;while(r--)if(!i[r](e,t,n))return!1;return!0}:i[0]}function Te(e,t,n,r,i){for(var o,a=[],s=0,u=e.length,l=null!=t;s<u;s++)(o=e[s])&&(n&&!n(o,r,i)||(a.push(o),l&&t.push(s)));return a}function Ce(d,h,g,v,y,e){return v&&!v[S]&&(v=Ce(v)),y&&!y[S]&&(y=Ce(y,e)),le(function(e,t,n,r){var i,o,a,s=[],u=[],l=t.length,c=e||function(e,t,n){for(var r=0,i=t.length;r<i;r++)se(e,t[r],n);return n}(h||"*",n.nodeType?[n]:n,[]),f=!d||!e&&h?c:Te(c,s,d,n,r),p=g?y||(e?d:l||v)?[]:t:f;if(g&&g(f,p,n,r),v){i=Te(p,u),v(i,[],n,r),o=i.length;while(o--)(a=i[o])&&(p[u[o]]=!(f[u[o]]=a))}if(e){if(y||d){if(y){i=[],o=p.length;while(o--)(a=p[o])&&i.push(f[o]=a);y(null,p=[],i,r)}o=p.length;while(o--)(a=p[o])&&-1<(i=y?P(e,a):s[o])&&(e[i]=!(t[i]=a))}}else p=Te(p===t?p.splice(l,p.length):p),y?y(null,t,p,r):H.apply(t,p)})}function Ee(e){for(var i,t,n,r=e.length,o=b.relative[e[0].type],a=o||b.relative[" "],s=o?1:0,u=be(function(e){return e===i},a,!0),l=be(function(e){return-1<P(i,e)},a,!0),c=[function(e,t,n){var r=!o&&(n||t!==w)||((i=t).nodeType?u(e,t,n):l(e,t,n));return i=null,r}];s<r;s++)if(t=b.relative[e[s].type])c=[be(we(c),t)];else{if((t=b.filter[e[s].type].apply(null,e[s].matches))[S]){for(n=++s;n<r;n++)if(b.relative[e[n].type])break;return Ce(1<s&&we(c),1<s&&xe(e.slice(0,s-1).concat({value:" "===e[s-2].type?"*":""})).replace($,"$1"),t,s<n&&Ee(e.slice(s,n)),n<r&&Ee(e=e.slice(n)),n<r&&xe(e))}c.push(t)}return we(c)}return me.prototype=b.filters=b.pseudos,b.setFilters=new me,h=se.tokenize=function(e,t){var n,r,i,o,a,s,u,l=x[e+" "];if(l)return t?0:l.slice(0);a=e,s=[],u=b.preFilter;while(a){for(o in n&&!(r=_.exec(a))||(r&&(a=a.slice(r[0].length)||a),s.push(i=[])),n=!1,(r=z.exec(a))&&(n=r.shift(),i.push({value:n,type:r[0].replace($," ")}),a=a.slice(n.length)),b.filter)!(r=G[o].exec(a))||u[o]&&!(r=u[o](r))||(n=r.shift(),i.push({value:n,type:o,matches:r}),a=a.slice(n.length));if(!n)break}return t?a.length:a?se.error(e):x(e,s).slice(0)},f=se.compile=function(e,t){var n,v,y,m,x,r,i=[],o=[],a=A[e+" "];if(!a){t||(t=h(e)),n=t.length;while(n--)(a=Ee(t[n]))[S]?i.push(a):o.push(a);(a=A(e,(v=o,m=0<(y=i).length,x=0<v.length,r=function(e,t,n,r,i){var o,a,s,u=0,l="0",c=e&&[],f=[],p=w,d=e||x&&b.find.TAG("*",i),h=k+=null==p?1:Math.random()||.1,g=d.length;for(i&&(w=t==C||t||i);l!==g&&null!=(o=d[l]);l++){if(x&&o){a=0,t||o.ownerDocument==C||(T(o),n=!E);while(s=v[a++])if(s(o,t||C,n)){r.push(o);break}i&&(k=h)}m&&((o=!s&&o)&&u--,e&&c.push(o))}if(u+=l,m&&l!==u){a=0;while(s=y[a++])s(c,f,t,n);if(e){if(0<u)while(l--)c[l]||f[l]||(f[l]=q.call(r));f=Te(f)}H.apply(r,f),i&&!e&&0<f.length&&1<u+y.length&&se.uniqueSort(r)}return i&&(k=h,w=p),c},m?le(r):r))).selector=e}return a},g=se.select=function(e,t,n,r){var i,o,a,s,u,l="function"==typeof e&&e,c=!r&&h(e=l.selector||e);if(n=n||[],1===c.length){if(2<(o=c[0]=c[0].slice(0)).length&&"ID"===(a=o[0]).type&&9===t.nodeType&&E&&b.relative[o[1].type]){if(!(t=(b.find.ID(a.matches[0].replace(te,ne),t)||[])[0]))return n;l&&(t=t.parentNode),e=e.slice(o.shift().value.length)}i=G.needsContext.test(e)?0:o.length;while(i--){if(a=o[i],b.relative[s=a.type])break;if((u=b.find[s])&&(r=u(a.matches[0].replace(te,ne),ee.test(o[0].type)&&ye(t.parentNode)||t))){if(o.splice(i,1),!(e=r.length&&xe(o)))return H.apply(n,r),n;break}}}return(l||f(e,c))(r,t,!E,n,!t||ee.test(e)&&ye(t.parentNode)||t),n},d.sortStable=S.split("").sort(j).join("")===S,d.detectDuplicates=!!l,T(),d.sortDetached=ce(function(e){return 1&e.compareDocumentPosition(C.createElement("fieldset"))}),ce(function(e){return e.innerHTML="<a href='#'></a>","#"===e.firstChild.getAttribute("href")})||fe("type|href|height|width",function(e,t,n){if(!n)return e.getAttribute(t,"type"===t.toLowerCase()?1:2)}),d.attributes&&ce(function(e){return e.innerHTML="<input/>",e.firstChild.setAttribute("value",""),""===e.firstChild.getAttribute("value")})||fe("value",function(e,t,n){if(!n&&"input"===e.nodeName.toLowerCase())return e.defaultValue}),ce(function(e){return null==e.getAttribute("disabled")})||fe(R,function(e,t,n){var r;if(!n)return!0===e[t]?t.toLowerCase():(r=e.getAttributeNode(t))&&r.specified?r.value:null}),se}(C);S.find=d,S.expr=d.selectors,S.expr[":"]=S.expr.pseudos,S.uniqueSort=S.unique=d.uniqueSort,S.text=d.getText,S.isXMLDoc=d.isXML,S.contains=d.contains,S.escapeSelector=d.escape;var h=function(e,t,n){var r=[],i=void 0!==n;while((e=e[t])&&9!==e.nodeType)if(1===e.nodeType){if(i&&S(e).is(n))break;r.push(e)}return r},T=function(e,t){for(var n=[];e;e=e.nextSibling)1===e.nodeType&&e!==t&&n.push(e);return n},k=S.expr.match.needsContext;function A(e,t){return e.nodeName&&e.nodeName.toLowerCase()===t.toLowerCase()}var N=/^<([a-z][^\/\0>:\x20\t\r\n\f]*)[\x20\t\r\n\f]*\/?>(?:<\/\1>|)$/i;function j(e,n,r){return m(n)?S.grep(e,function(e,t){return!!n.call(e,t,e)!==r}):n.nodeType?S.grep(e,function(e){return e===n!==r}):"string"!=typeof n?S.grep(e,function(e){return-1<i.call(n,e)!==r}):S.filter(n,e,r)}S.filter=function(e,t,n){var r=t[0];return n&&(e=":not("+e+")"),1===t.length&&1===r.nodeType?S.find.matchesSelector(r,e)?[r]:[]:S.find.matches(e,S.grep(t,function(e){return 1===e.nodeType}))},S.fn.extend({find:function(e){var t,n,r=this.length,i=this;if("string"!=typeof e)return this.pushStack(S(e).filter(function(){for(t=0;t<r;t++)if(S.contains(i[t],this))return!0}));for(n=this.pushStack([]),t=0;t<r;t++)S.find(e,i[t],n);return 1<r?S.uniqueSort(n):n},filter:function(e){return this.pushStack(j(this,e||[],!1))},not:function(e){return this.pushStack(j(this,e||[],!0))},is:function(e){return!!j(this,"string"==typeof e&&k.test(e)?S(e):e||[],!1).length}});var D,q=/^(?:\s*(<[\w\W]+>)[^>]*|#([\w-]+))$/;(S.fn.init=function(e,t,n){var r,i;if(!e)return this;if(n=n||D,"string"==typeof e){if(!(r="<"===e[0]&&">"===e[e.length-1]&&3<=e.length?[null,e,null]:q.exec(e))||!r[1]&&t)return!t||t.jquery?(t||n).find(e):this.constructor(t).find(e);if(r[1]){if(t=t instanceof S?t[0]:t,S.merge(this,S.parseHTML(r[1],t&&t.nodeType?t.ownerDocument||t:E,!0)),N.test(r[1])&&S.isPlainObject(t))for(r in t)m(this[r])?this[r](t[r]):this.attr(r,t[r]);return this}return(i=E.getElementById(r[2]))&&(this[0]=i,this.length=1),this}return e.nodeType?(this[0]=e,this.length=1,this):m(e)?void 0!==n.ready?n.ready(e):e(S):S.makeArray(e,this)}).prototype=S.fn,D=S(E);var L=/^(?:parents|prev(?:Until|All))/,H={children:!0,contents:!0,next:!0,prev:!0};function O(e,t){while((e=e[t])&&1!==e.nodeType);return e}S.fn.extend({has:function(e){var t=S(e,this),n=t.length;return this.filter(function(){for(var e=0;e<n;e++)if(S.contains(this,t[e]))return!0})},closest:function(e,t){var n,r=0,i=this.length,o=[],a="string"!=typeof e&&S(e);if(!k.test(e))for(;r<i;r++)for(n=this[r];n&&n!==t;n=n.parentNode)if(n.nodeType<11&&(a?-1<a.index(n):1===n.nodeType&&S.find.matchesSelector(n,e))){o.push(n);break}return this.pushStack(1<o.length?S.uniqueSort(o):o)},index:function(e){return e?"string"==typeof e?i.call(S(e),this[0]):i.call(this,e.jquery?e[0]:e):this[0]&&this[0].parentNode?this.first().prevAll().length:-1},add:function(e,t){return this.pushStack(S.uniqueSort(S.merge(this.get(),S(e,t))))},addBack:function(e){return this.add(null==e?this.prevObject:this.prevObject.filter(e))}}),S.each({parent:function(e){var t=e.parentNode;return t&&11!==t.nodeType?t:null},parents:function(e){return h(e,"parentNode")},parentsUntil:function(e,t,n){return h(e,"parentNode",n)},next:function(e){return O(e,"nextSibling")},prev:function(e){return O(e,"previousSibling")},nextAll:function(e){return h(e,"nextSibling")},prevAll:function(e){return h(e,"previousSibling")},nextUntil:function(e,t,n){return h(e,"nextSibling",n)},prevUntil:function(e,t,n){return h(e,"previousSibling",n)},siblings:function(e){return T((e.parentNode||{}).firstChild,e)},children:function(e){return T(e.firstChild)},contents:function(e){return null!=e.contentDocument&&r(e.contentDocument)?e.contentDocument:(A(e,"template")&&(e=e.content||e),S.merge([],e.childNodes))}},function(r,i){S.fn[r]=function(e,t){var n=S.map(this,i,e);return"Until"!==r.slice(-5)&&(t=e),t&&"string"==typeof t&&(n=S.filter(t,n)),1<this.length&&(H[r]||S.uniqueSort(n),L.test(r)&&n.reverse()),this.pushStack(n)}});var P=/[^\x20\t\r\n\f]+/g;function R(e){return e}function M(e){throw e}function I(e,t,n,r){var i;try{e&&m(i=e.promise)?i.call(e).done(t).fail(n):e&&m(i=e.then)?i.call(e,t,n):t.apply(void 0,[e].slice(r))}catch(e){n.apply(void 0,[e])}}S.Callbacks=function(r){var e,n;r="string"==typeof r?(e=r,n={},S.each(e.match(P)||[],function(e,t){n[t]=!0}),n):S.extend({},r);var i,t,o,a,s=[],u=[],l=-1,c=function(){for(a=a||r.once,o=i=!0;u.length;l=-1){t=u.shift();while(++l<s.length)!1===s[l].apply(t[0],t[1])&&r.stopOnFalse&&(l=s.length,t=!1)}r.memory||(t=!1),i=!1,a&&(s=t?[]:"")},f={add:function(){return s&&(t&&!i&&(l=s.length-1,u.push(t)),function n(e){S.each(e,function(e,t){m(t)?r.unique&&f.has(t)||s.push(t):t&&t.length&&"string"!==w(t)&&n(t)})}(arguments),t&&!i&&c()),this},remove:function(){return S.each(arguments,function(e,t){var n;while(-1<(n=S.inArray(t,s,n)))s.splice(n,1),n<=l&&l--}),this},has:function(e){return e?-1<S.inArray(e,s):0<s.length},empty:function(){return s&&(s=[]),this},disable:function(){return a=u=[],s=t="",this},disabled:function(){return!s},lock:function(){return a=u=[],t||i||(s=t=""),this},locked:function(){return!!a},fireWith:function(e,t){return a||(t=[e,(t=t||[]).slice?t.slice():t],u.push(t),i||c()),this},fire:function(){return f.fireWith(this,arguments),this},fired:function(){return!!o}};return f},S.extend({Deferred:function(e){var o=[["notify","progress",S.Callbacks("memory"),S.Callbacks("memory"),2],["resolve","done",S.Callbacks("once memory"),S.Callbacks("once memory"),0,"resolved"],["reject","fail",S.Callbacks("once memory"),S.Callbacks("once memory"),1,"rejected"]],i="pending",a={state:function(){return i},always:function(){return s.done(arguments).fail(arguments),this},"catch":function(e){return a.then(null,e)},pipe:function(){var i=arguments;return S.Deferred(function(r){S.each(o,function(e,t){var n=m(i[t[4]])&&i[t[4]];s[t[1]](function(){var e=n&&n.apply(this,arguments);e&&m(e.promise)?e.promise().progress(r.notify).done(r.resolve).fail(r.reject):r[t[0]+"With"](this,n?[e]:arguments)})}),i=null}).promise()},then:function(t,n,r){var u=0;function l(i,o,a,s){return function(){var n=this,r=arguments,e=function(){var e,t;if(!(i<u)){if((e=a.apply(n,r))===o.promise())throw new TypeError("Thenable self-resolution");t=e&&("object"==typeof e||"function"==typeof e)&&e.then,m(t)?s?t.call(e,l(u,o,R,s),l(u,o,M,s)):(u++,t.call(e,l(u,o,R,s),l(u,o,M,s),l(u,o,R,o.notifyWith))):(a!==R&&(n=void 0,r=[e]),(s||o.resolveWith)(n,r))}},t=s?e:function(){try{e()}catch(e){S.Deferred.exceptionHook&&S.Deferred.exceptionHook(e,t.stackTrace),u<=i+1&&(a!==M&&(n=void 0,r=[e]),o.rejectWith(n,r))}};i?t():(S.Deferred.getStackHook&&(t.stackTrace=S.Deferred.getStackHook()),C.setTimeout(t))}}return S.Deferred(function(e){o[0][3].add(l(0,e,m(r)?r:R,e.notifyWith)),o[1][3].add(l(0,e,m(t)?t:R)),o[2][3].add(l(0,e,m(n)?n:M))}).promise()},promise:function(e){return null!=e?S.extend(e,a):a}},s={};return S.each(o,function(e,t){var n=t[2],r=t[5];a[t[1]]=n.add,r&&n.add(function(){i=r},o[3-e][2].disable,o[3-e][3].disable,o[0][2].lock,o[0][3].lock),n.add(t[3].fire),s[t[0]]=function(){return s[t[0]+"With"](this===s?void 0:this,arguments),this},s[t[0]+"With"]=n.fireWith}),a.promise(s),e&&e.call(s,s),s},when:function(e){var n=arguments.length,t=n,r=Array(t),i=s.call(arguments),o=S.Deferred(),a=function(t){return function(e){r[t]=this,i[t]=1<arguments.length?s.call(arguments):e,--n||o.resolveWith(r,i)}};if(n<=1&&(I(e,o.done(a(t)).resolve,o.reject,!n),"pending"===o.state()||m(i[t]&&i[t].then)))return o.then();while(t--)I(i[t],a(t),o.reject);return o.promise()}});var W=/^(Eval|Internal|Range|Reference|Syntax|Type|URI)Error$/;S.Deferred.exceptionHook=function(e,t){C.console&&C.console.warn&&e&&W.test(e.name)&&C.console.warn("jQuery.Deferred exception: "+e.message,e.stack,t)},S.readyException=function(e){C.setTimeout(function(){throw e})};var F=S.Deferred();function B(){E.removeEventListener("DOMContentLoaded",B),C.removeEventListener("load",B),S.ready()}S.fn.ready=function(e){return F.then(e)["catch"](function(e){S.readyException(e)}),this},S.extend({isReady:!1,readyWait:1,ready:function(e){(!0===e?--S.readyWait:S.isReady)||(S.isReady=!0)!==e&&0<--S.readyWait||F.resolveWith(E,[S])}}),S.ready.then=F.then,"complete"===E.readyState||"loading"!==E.readyState&&!E.documentElement.doScroll?C.setTimeout(S.ready):(E.addEventListener("DOMContentLoaded",B),C.addEventListener("load",B));var $=function(e,t,n,r,i,o,a){var s=0,u=e.length,l=null==n;if("object"===w(n))for(s in i=!0,n)$(e,t,s,n[s],!0,o,a);else if(void 0!==r&&(i=!0,m(r)||(a=!0),l&&(a?(t.call(e,r),t=null):(l=t,t=function(e,t,n){return l.call(S(e),n)})),t))for(;s<u;s++)t(e[s],n,a?r:r.call(e[s],s,t(e[s],n)));return i?e:l?t.call(e):u?t(e[0],n):o},_=/^-ms-/,z=/-([a-z])/g;function U(e,t){return t.toUpperCase()}function X(e){return e.replace(_,"ms-").replace(z,U)}var V=function(e){return 1===e.nodeType||9===e.nodeType||!+e.nodeType};function G(){this.expando=S.expando+G.uid++}G.uid=1,G.prototype={cache:function(e){var t=e[this.expando];return t||(t={},V(e)&&(e.nodeType?e[this.expando]=t:Object.defineProperty(e,this.expando,{value:t,configurable:!0}))),t},set:function(e,t,n){var r,i=this.cache(e);if("string"==typeof t)i[X(t)]=n;else for(r in t)i[X(r)]=t[r];return i},get:function(e,t){return void 0===t?this.cache(e):e[this.expando]&&e[this.expando][X(t)]},access:function(e,t,n){return void 0===t||t&&"string"==typeof t&&void 0===n?this.get(e,t):(this.set(e,t,n),void 0!==n?n:t)},remove:function(e,t){var n,r=e[this.expando];if(void 0!==r){if(void 0!==t){n=(t=Array.isArray(t)?t.map(X):(t=X(t))in r?[t]:t.match(P)||[]).length;while(n--)delete r[t[n]]}(void 0===t||S.isEmptyObject(r))&&(e.nodeType?e[this.expando]=void 0:delete e[this.expando])}},hasData:function(e){var t=e[this.expando];return void 0!==t&&!S.isEmptyObject(t)}};var Y=new G,Q=new G,J=/^(?:\{[\w\W]*\}|\[[\w\W]*\])$/,K=/[A-Z]/g;function Z(e,t,n){var r,i;if(void 0===n&&1===e.nodeType)if(r="data-"+t.replace(K,"-$&").toLowerCase(),"string"==typeof(n=e.getAttribute(r))){try{n="true"===(i=n)||"false"!==i&&("null"===i?null:i===+i+""?+i:J.test(i)?JSON.parse(i):i)}catch(e){}Q.set(e,t,n)}else n=void 0;return n}S.extend({hasData:function(e){return Q.hasData(e)||Y.hasData(e)},data:function(e,t,n){return Q.access(e,t,n)},removeData:function(e,t){Q.remove(e,t)},_data:function(e,t,n){return Y.access(e,t,n)},_removeData:function(e,t){Y.remove(e,t)}}),S.fn.extend({data:function(n,e){var t,r,i,o=this[0],a=o&&o.attributes;if(void 0===n){if(this.length&&(i=Q.get(o),1===o.nodeType&&!Y.get(o,"hasDataAttrs"))){t=a.length;while(t--)a[t]&&0===(r=a[t].name).indexOf("data-")&&(r=X(r.slice(5)),Z(o,r,i[r]));Y.set(o,"hasDataAttrs",!0)}return i}return"object"==typeof n?this.each(function(){Q.set(this,n)}):$(this,function(e){var t;if(o&&void 0===e)return void 0!==(t=Q.get(o,n))?t:void 0!==(t=Z(o,n))?t:void 0;this.each(function(){Q.set(this,n,e)})},null,e,1<arguments.length,null,!0)},removeData:function(e){return this.each(function(){Q.remove(this,e)})}}),S.extend({queue:function(e,t,n){var r;if(e)return t=(t||"fx")+"queue",r=Y.get(e,t),n&&(!r||Array.isArray(n)?r=Y.access(e,t,S.makeArray(n)):r.push(n)),r||[]},dequeue:function(e,t){t=t||"fx";var n=S.queue(e,t),r=n.length,i=n.shift(),o=S._queueHooks(e,t);"inprogress"===i&&(i=n.shift(),r--),i&&("fx"===t&&n.unshift("inprogress"),delete o.stop,i.call(e,function(){S.dequeue(e,t)},o)),!r&&o&&o.empty.fire()},_queueHooks:function(e,t){var n=t+"queueHooks";return Y.get(e,n)||Y.access(e,n,{empty:S.Callbacks("once memory").add(function(){Y.remove(e,[t+"queue",n])})})}}),S.fn.extend({queue:function(t,n){var e=2;return"string"!=typeof t&&(n=t,t="fx",e--),arguments.length<e?S.queue(this[0],t):void 0===n?this:this.each(function(){var e=S.queue(this,t,n);S._queueHooks(this,t),"fx"===t&&"inprogress"!==e[0]&&S.dequeue(this,t)})},dequeue:function(e){return this.each(function(){S.dequeue(this,e)})},clearQueue:function(e){return this.queue(e||"fx",[])},promise:function(e,t){var n,r=1,i=S.Deferred(),o=this,a=this.length,s=function(){--r||i.resolveWith(o,[o])};"string"!=typeof e&&(t=e,e=void 0),e=e||"fx";while(a--)(n=Y.get(o[a],e+"queueHooks"))&&n.empty&&(r++,n.empty.add(s));return s(),i.promise(t)}});var ee=/[+-]?(?:\d*\.|)\d+(?:[eE][+-]?\d+|)/.source,te=new RegExp("^(?:([+-])=|)("+ee+")([a-z%]*)$","i"),ne=["Top","Right","Bottom","Left"],re=E.documentElement,ie=function(e){return S.contains(e.ownerDocument,e)},oe={composed:!0};re.getRootNode&&(ie=function(e){return S.contains(e.ownerDocument,e)||e.getRootNode(oe)===e.ownerDocument});var ae=function(e,t){return"none"===(e=t||e).style.display||""===e.style.display&&ie(e)&&"none"===S.css(e,"display")};function se(e,t,n,r){var i,o,a=20,s=r?function(){return r.cur()}:function(){return S.css(e,t,"")},u=s(),l=n&&n[3]||(S.cssNumber[t]?"":"px"),c=e.nodeType&&(S.cssNumber[t]||"px"!==l&&+u)&&te.exec(S.css(e,t));if(c&&c[3]!==l){u/=2,l=l||c[3],c=+u||1;while(a--)S.style(e,t,c+l),(1-o)*(1-(o=s()/u||.5))<=0&&(a=0),c/=o;c*=2,S.style(e,t,c+l),n=n||[]}return n&&(c=+c||+u||0,i=n[1]?c+(n[1]+1)*n[2]:+n[2],r&&(r.unit=l,r.start=c,r.end=i)),i}var ue={};function le(e,t){for(var n,r,i,o,a,s,u,l=[],c=0,f=e.length;c<f;c++)(r=e[c]).style&&(n=r.style.display,t?("none"===n&&(l[c]=Y.get(r,"display")||null,l[c]||(r.style.display="")),""===r.style.display&&ae(r)&&(l[c]=(u=a=o=void 0,a=(i=r).ownerDocument,s=i.nodeName,(u=ue[s])||(o=a.body.appendChild(a.createElement(s)),u=S.css(o,"display"),o.parentNode.removeChild(o),"none"===u&&(u="block"),ue[s]=u)))):"none"!==n&&(l[c]="none",Y.set(r,"display",n)));for(c=0;c<f;c++)null!=l[c]&&(e[c].style.display=l[c]);return e}S.fn.extend({show:function(){return le(this,!0)},hide:function(){return le(this)},toggle:function(e){return"boolean"==typeof e?e?this.show():this.hide():this.each(function(){ae(this)?S(this).show():S(this).hide()})}});var ce,fe,pe=/^(?:checkbox|radio)$/i,de=/<([a-z][^\/\0>\x20\t\r\n\f]*)/i,he=/^$|^module$|\/(?:java|ecma)script/i;ce=E.createDocumentFragment().appendChild(E.createElement("div")),(fe=E.createElement("input")).setAttribute("type","radio"),fe.setAttribute("checked","checked"),fe.setAttribute("name","t"),ce.appendChild(fe),y.checkClone=ce.cloneNode(!0).cloneNode(!0).lastChild.checked,ce.innerHTML="<textarea>x</textarea>",y.noCloneChecked=!!ce.cloneNode(!0).lastChild.defaultValue,ce.innerHTML="<option></option>",y.option=!!ce.lastChild;var ge={thead:[1,"<table>","</table>"],col:[2,"<table><colgroup>","</colgroup></table>"],tr:[2,"<table><tbody>","</tbody></table>"],td:[3,"<table><tbody><tr>","</tr></tbody></table>"],_default:[0,"",""]};function ve(e,t){var n;return n="undefined"!=typeof e.getElementsByTagName?e.getElementsByTagName(t||"*"):"undefined"!=typeof e.querySelectorAll?e.querySelectorAll(t||"*"):[],void 0===t||t&&A(e,t)?S.merge([e],n):n}function ye(e,t){for(var n=0,r=e.length;n<r;n++)Y.set(e[n],"globalEval",!t||Y.get(t[n],"globalEval"))}ge.tbody=ge.tfoot=ge.colgroup=ge.caption=ge.thead,ge.th=ge.td,y.option||(ge.optgroup=ge.option=[1,"<select multiple='multiple'>","</select>"]);var me=/<|&#?\w+;/;function xe(e,t,n,r,i){for(var o,a,s,u,l,c,f=t.createDocumentFragment(),p=[],d=0,h=e.length;d<h;d++)if((o=e[d])||0===o)if("object"===w(o))S.merge(p,o.nodeType?[o]:o);else if(me.test(o)){a=a||f.appendChild(t.createElement("div")),s=(de.exec(o)||["",""])[1].toLowerCase(),u=ge[s]||ge._default,a.innerHTML=u[1]+S.htmlPrefilter(o)+u[2],c=u[0];while(c--)a=a.lastChild;S.merge(p,a.childNodes),(a=f.firstChild).textContent=""}else p.push(t.createTextNode(o));f.textContent="",d=0;while(o=p[d++])if(r&&-1<S.inArray(o,r))i&&i.push(o);else if(l=ie(o),a=ve(f.appendChild(o),"script"),l&&ye(a),n){c=0;while(o=a[c++])he.test(o.type||"")&&n.push(o)}return f}var be=/^([^.]*)(?:\.(.+)|)/;function we(){return!0}function Te(){return!1}function Ce(e,t){return e===function(){try{return E.activeElement}catch(e){}}()==("focus"===t)}function Ee(e,t,n,r,i,o){var a,s;if("object"==typeof t){for(s in"string"!=typeof n&&(r=r||n,n=void 0),t)Ee(e,s,n,r,t[s],o);return e}if(null==r&&null==i?(i=n,r=n=void 0):null==i&&("string"==typeof n?(i=r,r=void 0):(i=r,r=n,n=void 0)),!1===i)i=Te;else if(!i)return e;return 1===o&&(a=i,(i=function(e){return S().off(e),a.apply(this,arguments)}).guid=a.guid||(a.guid=S.guid++)),e.each(function(){S.event.add(this,t,i,r,n)})}function Se(e,i,o){o?(Y.set(e,i,!1),S.event.add(e,i,{namespace:!1,handler:function(e){var t,n,r=Y.get(this,i);if(1&e.isTrigger&&this[i]){if(r.length)(S.event.special[i]||{}).delegateType&&e.stopPropagation();else if(r=s.call(arguments),Y.set(this,i,r),t=o(this,i),this[i](),r!==(n=Y.get(this,i))||t?Y.set(this,i,!1):n={},r!==n)return e.stopImmediatePropagation(),e.preventDefault(),n&&n.value}else r.length&&(Y.set(this,i,{value:S.event.trigger(S.extend(r[0],S.Event.prototype),r.slice(1),this)}),e.stopImmediatePropagation())}})):void 0===Y.get(e,i)&&S.event.add(e,i,we)}S.event={global:{},add:function(t,e,n,r,i){var o,a,s,u,l,c,f,p,d,h,g,v=Y.get(t);if(V(t)){n.handler&&(n=(o=n).handler,i=o.selector),i&&S.find.matchesSelector(re,i),n.guid||(n.guid=S.guid++),(u=v.events)||(u=v.events=Object.create(null)),(a=v.handle)||(a=v.handle=function(e){return"undefined"!=typeof S&&S.event.triggered!==e.type?S.event.dispatch.apply(t,arguments):void 0}),l=(e=(e||"").match(P)||[""]).length;while(l--)d=g=(s=be.exec(e[l])||[])[1],h=(s[2]||"").split(".").sort(),d&&(f=S.event.special[d]||{},d=(i?f.delegateType:f.bindType)||d,f=S.event.special[d]||{},c=S.extend({type:d,origType:g,data:r,handler:n,guid:n.guid,selector:i,needsContext:i&&S.expr.match.needsContext.test(i),namespace:h.join(".")},o),(p=u[d])||((p=u[d]=[]).delegateCount=0,f.setup&&!1!==f.setup.call(t,r,h,a)||t.addEventListener&&t.addEventListener(d,a)),f.add&&(f.add.call(t,c),c.handler.guid||(c.handler.guid=n.guid)),i?p.splice(p.delegateCount++,0,c):p.push(c),S.event.global[d]=!0)}},remove:function(e,t,n,r,i){var o,a,s,u,l,c,f,p,d,h,g,v=Y.hasData(e)&&Y.get(e);if(v&&(u=v.events)){l=(t=(t||"").match(P)||[""]).length;while(l--)if(d=g=(s=be.exec(t[l])||[])[1],h=(s[2]||"").split(".").sort(),d){f=S.event.special[d]||{},p=u[d=(r?f.delegateType:f.bindType)||d]||[],s=s[2]&&new RegExp("(^|\\.)"+h.join("\\.(?:.*\\.|)")+"(\\.|$)"),a=o=p.length;while(o--)c=p[o],!i&&g!==c.origType||n&&n.guid!==c.guid||s&&!s.test(c.namespace)||r&&r!==c.selector&&("**"!==r||!c.selector)||(p.splice(o,1),c.selector&&p.delegateCount--,f.remove&&f.remove.call(e,c));a&&!p.length&&(f.teardown&&!1!==f.teardown.call(e,h,v.handle)||S.removeEvent(e,d,v.handle),delete u[d])}else for(d in u)S.event.remove(e,d+t[l],n,r,!0);S.isEmptyObject(u)&&Y.remove(e,"handle events")}},dispatch:function(e){var t,n,r,i,o,a,s=new Array(arguments.length),u=S.event.fix(e),l=(Y.get(this,"events")||Object.create(null))[u.type]||[],c=S.event.special[u.type]||{};for(s[0]=u,t=1;t<arguments.length;t++)s[t]=arguments[t];if(u.delegateTarget=this,!c.preDispatch||!1!==c.preDispatch.call(this,u)){a=S.event.handlers.call(this,u,l),t=0;while((i=a[t++])&&!u.isPropagationStopped()){u.currentTarget=i.elem,n=0;while((o=i.handlers[n++])&&!u.isImmediatePropagationStopped())u.rnamespace&&!1!==o.namespace&&!u.rnamespace.test(o.namespace)||(u.handleObj=o,u.data=o.data,void 0!==(r=((S.event.special[o.origType]||{}).handle||o.handler).apply(i.elem,s))&&!1===(u.result=r)&&(u.preventDefault(),u.stopPropagation()))}return c.postDispatch&&c.postDispatch.call(this,u),u.result}},handlers:function(e,t){var n,r,i,o,a,s=[],u=t.delegateCount,l=e.target;if(u&&l.nodeType&&!("click"===e.type&&1<=e.button))for(;l!==this;l=l.parentNode||this)if(1===l.nodeType&&("click"!==e.type||!0!==l.disabled)){for(o=[],a={},n=0;n<u;n++)void 0===a[i=(r=t[n]).selector+" "]&&(a[i]=r.needsContext?-1<S(i,this).index(l):S.find(i,this,null,[l]).length),a[i]&&o.push(r);o.length&&s.push({elem:l,handlers:o})}return l=this,u<t.length&&s.push({elem:l,handlers:t.slice(u)}),s},addProp:function(t,e){Object.defineProperty(S.Event.prototype,t,{enumerable:!0,configurable:!0,get:m(e)?function(){if(this.originalEvent)return e(this.originalEvent)}:function(){if(this.originalEvent)return this.originalEvent[t]},set:function(e){Object.defineProperty(this,t,{enumerable:!0,configurable:!0,writable:!0,value:e})}})},fix:function(e){return e[S.expando]?e:new S.Event(e)},special:{load:{noBubble:!0},click:{setup:function(e){var t=this||e;return pe.test(t.type)&&t.click&&A(t,"input")&&Se(t,"click",we),!1},trigger:function(e){var t=this||e;return pe.test(t.type)&&t.click&&A(t,"input")&&Se(t,"click"),!0},_default:function(e){var t=e.target;return pe.test(t.type)&&t.click&&A(t,"input")&&Y.get(t,"click")||A(t,"a")}},beforeunload:{postDispatch:function(e){void 0!==e.result&&e.originalEvent&&(e.originalEvent.returnValue=e.result)}}}},S.removeEvent=function(e,t,n){e.removeEventListener&&e.removeEventListener(t,n)},S.Event=function(e,t){if(!(this instanceof S.Event))return new S.Event(e,t);e&&e.type?(this.originalEvent=e,this.type=e.type,this.isDefaultPrevented=e.defaultPrevented||void 0===e.defaultPrevented&&!1===e.returnValue?we:Te,this.target=e.target&&3===e.target.nodeType?e.target.parentNode:e.target,this.currentTarget=e.currentTarget,this.relatedTarget=e.relatedTarget):this.type=e,t&&S.extend(this,t),this.timeStamp=e&&e.timeStamp||Date.now(),this[S.expando]=!0},S.Event.prototype={constructor:S.Event,isDefaultPrevented:Te,isPropagationStopped:Te,isImmediatePropagationStopped:Te,isSimulated:!1,preventDefault:function(){var e=this.originalEvent;this.isDefaultPrevented=we,e&&!this.isSimulated&&e.preventDefault()},stopPropagation:function(){var e=this.originalEvent;this.isPropagationStopped=we,e&&!this.isSimulated&&e.stopPropagation()},stopImmediatePropagation:function(){var e=this.originalEvent;this.isImmediatePropagationStopped=we,e&&!this.isSimulated&&e.stopImmediatePropagation(),this.stopPropagation()}},S.each({altKey:!0,bubbles:!0,cancelable:!0,changedTouches:!0,ctrlKey:!0,detail:!0,eventPhase:!0,metaKey:!0,pageX:!0,pageY:!0,shiftKey:!0,view:!0,"char":!0,code:!0,charCode:!0,key:!0,keyCode:!0,button:!0,buttons:!0,clientX:!0,clientY:!0,offsetX:!0,offsetY:!0,pointerId:!0,pointerType:!0,screenX:!0,screenY:!0,targetTouches:!0,toElement:!0,touches:!0,which:!0},S.event.addProp),S.each({focus:"focusin",blur:"focusout"},function(e,t){S.event.special[e]={setup:function(){return Se(this,e,Ce),!1},trigger:function(){return Se(this,e),!0},_default:function(){return!0},delegateType:t}}),S.each({mouseenter:"mouseover",mouseleave:"mouseout",pointerenter:"pointerover",pointerleave:"pointerout"},function(e,i){S.event.special[e]={delegateType:i,bindType:i,handle:function(e){var t,n=e.relatedTarget,r=e.handleObj;return n&&(n===this||S.contains(this,n))||(e.type=r.origType,t=r.handler.apply(this,arguments),e.type=i),t}}}),S.fn.extend({on:function(e,t,n,r){return Ee(this,e,t,n,r)},one:function(e,t,n,r){return Ee(this,e,t,n,r,1)},off:function(e,t,n){var r,i;if(e&&e.preventDefault&&e.handleObj)return r=e.handleObj,S(e.delegateTarget).off(r.namespace?r.origType+"."+r.namespace:r.origType,r.selector,r.handler),this;if("object"==typeof e){for(i in e)this.off(i,t,e[i]);return this}return!1!==t&&"function"!=typeof t||(n=t,t=void 0),!1===n&&(n=Te),this.each(function(){S.event.remove(this,e,n,t)})}});var ke=/<script|<style|<link/i,Ae=/checked\s*(?:[^=]|=\s*.checked.)/i,Ne=/^\s*<!(?:\[CDATA\[|--)|(?:\]\]|--)>\s*$/g;function je(e,t){return A(e,"table")&&A(11!==t.nodeType?t:t.firstChild,"tr")&&S(e).children("tbody")[0]||e}function De(e){return e.type=(null!==e.getAttribute("type"))+"/"+e.type,e}function qe(e){return"true/"===(e.type||"").slice(0,5)?e.type=e.type.slice(5):e.removeAttribute("type"),e}function Le(e,t){var n,r,i,o,a,s;if(1===t.nodeType){if(Y.hasData(e)&&(s=Y.get(e).events))for(i in Y.remove(t,"handle events"),s)for(n=0,r=s[i].length;n<r;n++)S.event.add(t,i,s[i][n]);Q.hasData(e)&&(o=Q.access(e),a=S.extend({},o),Q.set(t,a))}}function He(n,r,i,o){r=g(r);var e,t,a,s,u,l,c=0,f=n.length,p=f-1,d=r[0],h=m(d);if(h||1<f&&"string"==typeof d&&!y.checkClone&&Ae.test(d))return n.each(function(e){var t=n.eq(e);h&&(r[0]=d.call(this,e,t.html())),He(t,r,i,o)});if(f&&(t=(e=xe(r,n[0].ownerDocument,!1,n,o)).firstChild,1===e.childNodes.length&&(e=t),t||o)){for(s=(a=S.map(ve(e,"script"),De)).length;c<f;c++)u=e,c!==p&&(u=S.clone(u,!0,!0),s&&S.merge(a,ve(u,"script"))),i.call(n[c],u,c);if(s)for(l=a[a.length-1].ownerDocument,S.map(a,qe),c=0;c<s;c++)u=a[c],he.test(u.type||"")&&!Y.access(u,"globalEval")&&S.contains(l,u)&&(u.src&&"module"!==(u.type||"").toLowerCase()?S._evalUrl&&!u.noModule&&S._evalUrl(u.src,{nonce:u.nonce||u.getAttribute("nonce")},l):b(u.textContent.replace(Ne,""),u,l))}return n}function Oe(e,t,n){for(var r,i=t?S.filter(t,e):e,o=0;null!=(r=i[o]);o++)n||1!==r.nodeType||S.cleanData(ve(r)),r.parentNode&&(n&&ie(r)&&ye(ve(r,"script")),r.parentNode.removeChild(r));return e}S.extend({htmlPrefilter:function(e){return e},clone:function(e,t,n){var r,i,o,a,s,u,l,c=e.cloneNode(!0),f=ie(e);if(!(y.noCloneChecked||1!==e.nodeType&&11!==e.nodeType||S.isXMLDoc(e)))for(a=ve(c),r=0,i=(o=ve(e)).length;r<i;r++)s=o[r],u=a[r],void 0,"input"===(l=u.nodeName.toLowerCase())&&pe.test(s.type)?u.checked=s.checked:"input"!==l&&"textarea"!==l||(u.defaultValue=s.defaultValue);if(t)if(n)for(o=o||ve(e),a=a||ve(c),r=0,i=o.length;r<i;r++)Le(o[r],a[r]);else Le(e,c);return 0<(a=ve(c,"script")).length&&ye(a,!f&&ve(e,"script")),c},cleanData:function(e){for(var t,n,r,i=S.event.special,o=0;void 0!==(n=e[o]);o++)if(V(n)){if(t=n[Y.expando]){if(t.events)for(r in t.events)i[r]?S.event.remove(n,r):S.removeEvent(n,r,t.handle);n[Y.expando]=void 0}n[Q.expando]&&(n[Q.expando]=void 0)}}}),S.fn.extend({detach:function(e){return Oe(this,e,!0)},remove:function(e){return Oe(this,e)},text:function(e){return $(this,function(e){return void 0===e?S.text(this):this.empty().each(function(){1!==this.nodeType&&11!==this.nodeType&&9!==this.nodeType||(this.textContent=e)})},null,e,arguments.length)},append:function(){return He(this,arguments,function(e){1!==this.nodeType&&11!==this.nodeType&&9!==this.nodeType||je(this,e).appendChild(e)})},prepend:function(){return He(this,arguments,function(e){if(1===this.nodeType||11===this.nodeType||9===this.nodeType){var t=je(this,e);t.insertBefore(e,t.firstChild)}})},before:function(){return He(this,arguments,function(e){this.parentNode&&this.parentNode.insertBefore(e,this)})},after:function(){return He(this,arguments,function(e){this.parentNode&&this.parentNode.insertBefore(e,this.nextSibling)})},empty:function(){for(var e,t=0;null!=(e=this[t]);t++)1===e.nodeType&&(S.cleanData(ve(e,!1)),e.textContent="");return this},clone:function(e,t){return e=null!=e&&e,t=null==t?e:t,this.map(function(){return S.clone(this,e,t)})},html:function(e){return $(this,function(e){var t=this[0]||{},n=0,r=this.length;if(void 0===e&&1===t.nodeType)return t.innerHTML;if("string"==typeof e&&!ke.test(e)&&!ge[(de.exec(e)||["",""])[1].toLowerCase()]){e=S.htmlPrefilter(e);try{for(;n<r;n++)1===(t=this[n]||{}).nodeType&&(S.cleanData(ve(t,!1)),t.innerHTML=e);t=0}catch(e){}}t&&this.empty().append(e)},null,e,arguments.length)},replaceWith:function(){var n=[];return He(this,arguments,function(e){var t=this.parentNode;S.inArray(this,n)<0&&(S.cleanData(ve(this)),t&&t.replaceChild(e,this))},n)}}),S.each({appendTo:"append",prependTo:"prepend",insertBefore:"before",insertAfter:"after",replaceAll:"replaceWith"},function(e,a){S.fn[e]=function(e){for(var t,n=[],r=S(e),i=r.length-1,o=0;o<=i;o++)t=o===i?this:this.clone(!0),S(r[o])[a](t),u.apply(n,t.get());return this.pushStack(n)}});var Pe=new RegExp("^("+ee+")(?!px)[a-z%]+$","i"),Re=function(e){var t=e.ownerDocument.defaultView;return t&&t.opener||(t=C),t.getComputedStyle(e)},Me=function(e,t,n){var r,i,o={};for(i in t)o[i]=e.style[i],e.style[i]=t[i];for(i in r=n.call(e),t)e.style[i]=o[i];return r},Ie=new RegExp(ne.join("|"),"i");function We(e,t,n){var r,i,o,a,s=e.style;return(n=n||Re(e))&&(""!==(a=n.getPropertyValue(t)||n[t])||ie(e)||(a=S.style(e,t)),!y.pixelBoxStyles()&&Pe.test(a)&&Ie.test(t)&&(r=s.width,i=s.minWidth,o=s.maxWidth,s.minWidth=s.maxWidth=s.width=a,a=n.width,s.width=r,s.minWidth=i,s.maxWidth=o)),void 0!==a?a+"":a}function Fe(e,t){return{get:function(){if(!e())return(this.get=t).apply(this,arguments);delete this.get}}}!function(){function e(){if(l){u.style.cssText="position:absolute;left:-11111px;width:60px;margin-top:1px;padding:0;border:0",l.style.cssText="position:relative;display:block;box-sizing:border-box;overflow:scroll;margin:auto;border:1px;padding:1px;width:60%;top:1%",re.appendChild(u).appendChild(l);var e=C.getComputedStyle(l);n="1%"!==e.top,s=12===t(e.marginLeft),l.style.right="60%",o=36===t(e.right),r=36===t(e.width),l.style.position="absolute",i=12===t(l.offsetWidth/3),re.removeChild(u),l=null}}function t(e){return Math.round(parseFloat(e))}var n,r,i,o,a,s,u=E.createElement("div"),l=E.createElement("div");l.style&&(l.style.backgroundClip="content-box",l.cloneNode(!0).style.backgroundClip="",y.clearCloneStyle="content-box"===l.style.backgroundClip,S.extend(y,{boxSizingReliable:function(){return e(),r},pixelBoxStyles:function(){return e(),o},pixelPosition:function(){return e(),n},reliableMarginLeft:function(){return e(),s},scrollboxSize:function(){return e(),i},reliableTrDimensions:function(){var e,t,n,r;return null==a&&(e=E.createElement("table"),t=E.createElement("tr"),n=E.createElement("div"),e.style.cssText="position:absolute;left:-11111px;border-collapse:separate",t.style.cssText="border:1px solid",t.style.height="1px",n.style.height="9px",n.style.display="block",re.appendChild(e).appendChild(t).appendChild(n),r=C.getComputedStyle(t),a=parseInt(r.height,10)+parseInt(r.borderTopWidth,10)+parseInt(r.borderBottomWidth,10)===t.offsetHeight,re.removeChild(e)),a}}))}();var Be=["Webkit","Moz","ms"],$e=E.createElement("div").style,_e={};function ze(e){var t=S.cssProps[e]||_e[e];return t||(e in $e?e:_e[e]=function(e){var t=e[0].toUpperCase()+e.slice(1),n=Be.length;while(n--)if((e=Be[n]+t)in $e)return e}(e)||e)}var Ue=/^(none|table(?!-c[ea]).+)/,Xe=/^--/,Ve={position:"absolute",visibility:"hidden",display:"block"},Ge={letterSpacing:"0",fontWeight:"400"};function Ye(e,t,n){var r=te.exec(t);return r?Math.max(0,r[2]-(n||0))+(r[3]||"px"):t}function Qe(e,t,n,r,i,o){var a="width"===t?1:0,s=0,u=0;if(n===(r?"border":"content"))return 0;for(;a<4;a+=2)"margin"===n&&(u+=S.css(e,n+ne[a],!0,i)),r?("content"===n&&(u-=S.css(e,"padding"+ne[a],!0,i)),"margin"!==n&&(u-=S.css(e,"border"+ne[a]+"Width",!0,i))):(u+=S.css(e,"padding"+ne[a],!0,i),"padding"!==n?u+=S.css(e,"border"+ne[a]+"Width",!0,i):s+=S.css(e,"border"+ne[a]+"Width",!0,i));return!r&&0<=o&&(u+=Math.max(0,Math.ceil(e["offset"+t[0].toUpperCase()+t.slice(1)]-o-u-s-.5))||0),u}function Je(e,t,n){var r=Re(e),i=(!y.boxSizingReliable()||n)&&"border-box"===S.css(e,"boxSizing",!1,r),o=i,a=We(e,t,r),s="offset"+t[0].toUpperCase()+t.slice(1);if(Pe.test(a)){if(!n)return a;a="auto"}return(!y.boxSizingReliable()&&i||!y.reliableTrDimensions()&&A(e,"tr")||"auto"===a||!parseFloat(a)&&"inline"===S.css(e,"display",!1,r))&&e.getClientRects().length&&(i="border-box"===S.css(e,"boxSizing",!1,r),(o=s in e)&&(a=e[s])),(a=parseFloat(a)||0)+Qe(e,t,n||(i?"border":"content"),o,r,a)+"px"}function Ke(e,t,n,r,i){return new Ke.prototype.init(e,t,n,r,i)}S.extend({cssHooks:{opacity:{get:function(e,t){if(t){var n=We(e,"opacity");return""===n?"1":n}}}},cssNumber:{animationIterationCount:!0,columnCount:!0,fillOpacity:!0,flexGrow:!0,flexShrink:!0,fontWeight:!0,gridArea:!0,gridColumn:!0,gridColumnEnd:!0,gridColumnStart:!0,gridRow:!0,gridRowEnd:!0,gridRowStart:!0,lineHeight:!0,opacity:!0,order:!0,orphans:!0,widows:!0,zIndex:!0,zoom:!0},cssProps:{},style:function(e,t,n,r){if(e&&3!==e.nodeType&&8!==e.nodeType&&e.style){var i,o,a,s=X(t),u=Xe.test(t),l=e.style;if(u||(t=ze(s)),a=S.cssHooks[t]||S.cssHooks[s],void 0===n)return a&&"get"in a&&void 0!==(i=a.get(e,!1,r))?i:l[t];"string"===(o=typeof n)&&(i=te.exec(n))&&i[1]&&(n=se(e,t,i),o="number"),null!=n&&n==n&&("number"!==o||u||(n+=i&&i[3]||(S.cssNumber[s]?"":"px")),y.clearCloneStyle||""!==n||0!==t.indexOf("background")||(l[t]="inherit"),a&&"set"in a&&void 0===(n=a.set(e,n,r))||(u?l.setProperty(t,n):l[t]=n))}},css:function(e,t,n,r){var i,o,a,s=X(t);return Xe.test(t)||(t=ze(s)),(a=S.cssHooks[t]||S.cssHooks[s])&&"get"in a&&(i=a.get(e,!0,n)),void 0===i&&(i=We(e,t,r)),"normal"===i&&t in Ge&&(i=Ge[t]),""===n||n?(o=parseFloat(i),!0===n||isFinite(o)?o||0:i):i}}),S.each(["height","width"],function(e,u){S.cssHooks[u]={get:function(e,t,n){if(t)return!Ue.test(S.css(e,"display"))||e.getClientRects().length&&e.getBoundingClientRect().width?Je(e,u,n):Me(e,Ve,function(){return Je(e,u,n)})},set:function(e,t,n){var r,i=Re(e),o=!y.scrollboxSize()&&"absolute"===i.position,a=(o||n)&&"border-box"===S.css(e,"boxSizing",!1,i),s=n?Qe(e,u,n,a,i):0;return a&&o&&(s-=Math.ceil(e["offset"+u[0].toUpperCase()+u.slice(1)]-parseFloat(i[u])-Qe(e,u,"border",!1,i)-.5)),s&&(r=te.exec(t))&&"px"!==(r[3]||"px")&&(e.style[u]=t,t=S.css(e,u)),Ye(0,t,s)}}}),S.cssHooks.marginLeft=Fe(y.reliableMarginLeft,function(e,t){if(t)return(parseFloat(We(e,"marginLeft"))||e.getBoundingClientRect().left-Me(e,{marginLeft:0},function(){return e.getBoundingClientRect().left}))+"px"}),S.each({margin:"",padding:"",border:"Width"},function(i,o){S.cssHooks[i+o]={expand:function(e){for(var t=0,n={},r="string"==typeof e?e.split(" "):[e];t<4;t++)n[i+ne[t]+o]=r[t]||r[t-2]||r[0];return n}},"margin"!==i&&(S.cssHooks[i+o].set=Ye)}),S.fn.extend({css:function(e,t){return $(this,function(e,t,n){var r,i,o={},a=0;if(Array.isArray(t)){for(r=Re(e),i=t.length;a<i;a++)o[t[a]]=S.css(e,t[a],!1,r);return o}return void 0!==n?S.style(e,t,n):S.css(e,t)},e,t,1<arguments.length)}}),((S.Tween=Ke).prototype={constructor:Ke,init:function(e,t,n,r,i,o){this.elem=e,this.prop=n,this.easing=i||S.easing._default,this.options=t,this.start=this.now=this.cur(),this.end=r,this.unit=o||(S.cssNumber[n]?"":"px")},cur:function(){var e=Ke.propHooks[this.prop];return e&&e.get?e.get(this):Ke.propHooks._default.get(this)},run:function(e){var t,n=Ke.propHooks[this.prop];return this.options.duration?this.pos=t=S.easing[this.easing](e,this.options.duration*e,0,1,this.options.duration):this.pos=t=e,this.now=(this.end-this.start)*t+this.start,this.options.step&&this.options.step.call(this.elem,this.now,this),n&&n.set?n.set(this):Ke.propHooks._default.set(this),this}}).init.prototype=Ke.prototype,(Ke.propHooks={_default:{get:function(e){var t;return 1!==e.elem.nodeType||null!=e.elem[e.prop]&&null==e.elem.style[e.prop]?e.elem[e.prop]:(t=S.css(e.elem,e.prop,""))&&"auto"!==t?t:0},set:function(e){S.fx.step[e.prop]?S.fx.step[e.prop](e):1!==e.elem.nodeType||!S.cssHooks[e.prop]&&null==e.elem.style[ze(e.prop)]?e.elem[e.prop]=e.now:S.style(e.elem,e.prop,e.now+e.unit)}}}).scrollTop=Ke.propHooks.scrollLeft={set:function(e){e.elem.nodeType&&e.elem.parentNode&&(e.elem[e.prop]=e.now)}},S.easing={linear:function(e){return e},swing:function(e){return.5-Math.cos(e*Math.PI)/2},_default:"swing"},S.fx=Ke.prototype.init,S.fx.step={};var Ze,et,tt,nt,rt=/^(?:toggle|show|hide)$/,it=/queueHooks$/;function ot(){et&&(!1===E.hidden&&C.requestAnimationFrame?C.requestAnimationFrame(ot):C.setTimeout(ot,S.fx.interval),S.fx.tick())}function at(){return C.setTimeout(function(){Ze=void 0}),Ze=Date.now()}function st(e,t){var n,r=0,i={height:e};for(t=t?1:0;r<4;r+=2-t)i["margin"+(n=ne[r])]=i["padding"+n]=e;return t&&(i.opacity=i.width=e),i}function ut(e,t,n){for(var r,i=(lt.tweeners[t]||[]).concat(lt.tweeners["*"]),o=0,a=i.length;o<a;o++)if(r=i[o].call(n,t,e))return r}function lt(o,e,t){var n,a,r=0,i=lt.prefilters.length,s=S.Deferred().always(function(){delete u.elem}),u=function(){if(a)return!1;for(var e=Ze||at(),t=Math.max(0,l.startTime+l.duration-e),n=1-(t/l.duration||0),r=0,i=l.tweens.length;r<i;r++)l.tweens[r].run(n);return s.notifyWith(o,[l,n,t]),n<1&&i?t:(i||s.notifyWith(o,[l,1,0]),s.resolveWith(o,[l]),!1)},l=s.promise({elem:o,props:S.extend({},e),opts:S.extend(!0,{specialEasing:{},easing:S.easing._default},t),originalProperties:e,originalOptions:t,startTime:Ze||at(),duration:t.duration,tweens:[],createTween:function(e,t){var n=S.Tween(o,l.opts,e,t,l.opts.specialEasing[e]||l.opts.easing);return l.tweens.push(n),n},stop:function(e){var t=0,n=e?l.tweens.length:0;if(a)return this;for(a=!0;t<n;t++)l.tweens[t].run(1);return e?(s.notifyWith(o,[l,1,0]),s.resolveWith(o,[l,e])):s.rejectWith(o,[l,e]),this}}),c=l.props;for(!function(e,t){var n,r,i,o,a;for(n in e)if(i=t[r=X(n)],o=e[n],Array.isArray(o)&&(i=o[1],o=e[n]=o[0]),n!==r&&(e[r]=o,delete e[n]),(a=S.cssHooks[r])&&"expand"in a)for(n in o=a.expand(o),delete e[r],o)n in e||(e[n]=o[n],t[n]=i);else t[r]=i}(c,l.opts.specialEasing);r<i;r++)if(n=lt.prefilters[r].call(l,o,c,l.opts))return m(n.stop)&&(S._queueHooks(l.elem,l.opts.queue).stop=n.stop.bind(n)),n;return S.map(c,ut,l),m(l.opts.start)&&l.opts.start.call(o,l),l.progress(l.opts.progress).done(l.opts.done,l.opts.complete).fail(l.opts.fail).always(l.opts.always),S.fx.timer(S.extend(u,{elem:o,anim:l,queue:l.opts.queue})),l}S.Animation=S.extend(lt,{tweeners:{"*":[function(e,t){var n=this.createTween(e,t);return se(n.elem,e,te.exec(t),n),n}]},tweener:function(e,t){m(e)?(t=e,e=["*"]):e=e.match(P);for(var n,r=0,i=e.length;r<i;r++)n=e[r],lt.tweeners[n]=lt.tweeners[n]||[],lt.tweeners[n].unshift(t)},prefilters:[function(e,t,n){var r,i,o,a,s,u,l,c,f="width"in t||"height"in t,p=this,d={},h=e.style,g=e.nodeType&&ae(e),v=Y.get(e,"fxshow");for(r in n.queue||(null==(a=S._queueHooks(e,"fx")).unqueued&&(a.unqueued=0,s=a.empty.fire,a.empty.fire=function(){a.unqueued||s()}),a.unqueued++,p.always(function(){p.always(function(){a.unqueued--,S.queue(e,"fx").length||a.empty.fire()})})),t)if(i=t[r],rt.test(i)){if(delete t[r],o=o||"toggle"===i,i===(g?"hide":"show")){if("show"!==i||!v||void 0===v[r])continue;g=!0}d[r]=v&&v[r]||S.style(e,r)}if((u=!S.isEmptyObject(t))||!S.isEmptyObject(d))for(r in f&&1===e.nodeType&&(n.overflow=[h.overflow,h.overflowX,h.overflowY],null==(l=v&&v.display)&&(l=Y.get(e,"display")),"none"===(c=S.css(e,"display"))&&(l?c=l:(le([e],!0),l=e.style.display||l,c=S.css(e,"display"),le([e]))),("inline"===c||"inline-block"===c&&null!=l)&&"none"===S.css(e,"float")&&(u||(p.done(function(){h.display=l}),null==l&&(c=h.display,l="none"===c?"":c)),h.display="inline-block")),n.overflow&&(h.overflow="hidden",p.always(function(){h.overflow=n.overflow[0],h.overflowX=n.overflow[1],h.overflowY=n.overflow[2]})),u=!1,d)u||(v?"hidden"in v&&(g=v.hidden):v=Y.access(e,"fxshow",{display:l}),o&&(v.hidden=!g),g&&le([e],!0),p.done(function(){for(r in g||le([e]),Y.remove(e,"fxshow"),d)S.style(e,r,d[r])})),u=ut(g?v[r]:0,r,p),r in v||(v[r]=u.start,g&&(u.end=u.start,u.start=0))}],prefilter:function(e,t){t?lt.prefilters.unshift(e):lt.prefilters.push(e)}}),S.speed=function(e,t,n){var r=e&&"object"==typeof e?S.extend({},e):{complete:n||!n&&t||m(e)&&e,duration:e,easing:n&&t||t&&!m(t)&&t};return S.fx.off?r.duration=0:"number"!=typeof r.duration&&(r.duration in S.fx.speeds?r.duration=S.fx.speeds[r.duration]:r.duration=S.fx.speeds._default),null!=r.queue&&!0!==r.queue||(r.queue="fx"),r.old=r.complete,r.complete=function(){m(r.old)&&r.old.call(this),r.queue&&S.dequeue(this,r.queue)},r},S.fn.extend({fadeTo:function(e,t,n,r){return this.filter(ae).css("opacity",0).show().end().animate({opacity:t},e,n,r)},animate:function(t,e,n,r){var i=S.isEmptyObject(t),o=S.speed(e,n,r),a=function(){var e=lt(this,S.extend({},t),o);(i||Y.get(this,"finish"))&&e.stop(!0)};return a.finish=a,i||!1===o.queue?this.each(a):this.queue(o.queue,a)},stop:function(i,e,o){var a=function(e){var t=e.stop;delete e.stop,t(o)};return"string"!=typeof i&&(o=e,e=i,i=void 0),e&&this.queue(i||"fx",[]),this.each(function(){var e=!0,t=null!=i&&i+"queueHooks",n=S.timers,r=Y.get(this);if(t)r[t]&&r[t].stop&&a(r[t]);else for(t in r)r[t]&&r[t].stop&&it.test(t)&&a(r[t]);for(t=n.length;t--;)n[t].elem!==this||null!=i&&n[t].queue!==i||(n[t].anim.stop(o),e=!1,n.splice(t,1));!e&&o||S.dequeue(this,i)})},finish:function(a){return!1!==a&&(a=a||"fx"),this.each(function(){var e,t=Y.get(this),n=t[a+"queue"],r=t[a+"queueHooks"],i=S.timers,o=n?n.length:0;for(t.finish=!0,S.queue(this,a,[]),r&&r.stop&&r.stop.call(this,!0),e=i.length;e--;)i[e].elem===this&&i[e].queue===a&&(i[e].anim.stop(!0),i.splice(e,1));for(e=0;e<o;e++)n[e]&&n[e].finish&&n[e].finish.call(this);delete t.finish})}}),S.each(["toggle","show","hide"],function(e,r){var i=S.fn[r];S.fn[r]=function(e,t,n){return null==e||"boolean"==typeof e?i.apply(this,arguments):this.animate(st(r,!0),e,t,n)}}),S.each({slideDown:st("show"),slideUp:st("hide"),slideToggle:st("toggle"),fadeIn:{opacity:"show"},fadeOut:{opacity:"hide"},fadeToggle:{opacity:"toggle"}},function(e,r){S.fn[e]=function(e,t,n){return this.animate(r,e,t,n)}}),S.timers=[],S.fx.tick=function(){var e,t=0,n=S.timers;for(Ze=Date.now();t<n.length;t++)(e=n[t])()||n[t]!==e||n.splice(t--,1);n.length||S.fx.stop(),Ze=void 0},S.fx.timer=function(e){S.timers.push(e),S.fx.start()},S.fx.interval=13,S.fx.start=function(){et||(et=!0,ot())},S.fx.stop=function(){et=null},S.fx.speeds={slow:600,fast:200,_default:400},S.fn.delay=function(r,e){return r=S.fx&&S.fx.speeds[r]||r,e=e||"fx",this.queue(e,function(e,t){var n=C.setTimeout(e,r);t.stop=function(){C.clearTimeout(n)}})},tt=E.createElement("input"),nt=E.createElement("select").appendChild(E.createElement("option")),tt.type="checkbox",y.checkOn=""!==tt.value,y.optSelected=nt.selected,(tt=E.createElement("input")).value="t",tt.type="radio",y.radioValue="t"===tt.value;var ct,ft=S.expr.attrHandle;S.fn.extend({attr:function(e,t){return $(this,S.attr,e,t,1<arguments.length)},removeAttr:function(e){return this.each(function(){S.removeAttr(this,e)})}}),S.extend({attr:function(e,t,n){var r,i,o=e.nodeType;if(3!==o&&8!==o&&2!==o)return"undefined"==typeof e.getAttribute?S.prop(e,t,n):(1===o&&S.isXMLDoc(e)||(i=S.attrHooks[t.toLowerCase()]||(S.expr.match.bool.test(t)?ct:void 0)),void 0!==n?null===n?void S.removeAttr(e,t):i&&"set"in i&&void 0!==(r=i.set(e,n,t))?r:(e.setAttribute(t,n+""),n):i&&"get"in i&&null!==(r=i.get(e,t))?r:null==(r=S.find.attr(e,t))?void 0:r)},attrHooks:{type:{set:function(e,t){if(!y.radioValue&&"radio"===t&&A(e,"input")){var n=e.value;return e.setAttribute("type",t),n&&(e.value=n),t}}}},removeAttr:function(e,t){var n,r=0,i=t&&t.match(P);if(i&&1===e.nodeType)while(n=i[r++])e.removeAttribute(n)}}),ct={set:function(e,t,n){return!1===t?S.removeAttr(e,n):e.setAttribute(n,n),n}},S.each(S.expr.match.bool.source.match(/\w+/g),function(e,t){var a=ft[t]||S.find.attr;ft[t]=function(e,t,n){var r,i,o=t.toLowerCase();return n||(i=ft[o],ft[o]=r,r=null!=a(e,t,n)?o:null,ft[o]=i),r}});var pt=/^(?:input|select|textarea|button)$/i,dt=/^(?:a|area)$/i;function ht(e){return(e.match(P)||[]).join(" ")}function gt(e){return e.getAttribute&&e.getAttribute("class")||""}function vt(e){return Array.isArray(e)?e:"string"==typeof e&&e.match(P)||[]}S.fn.extend({prop:function(e,t){return $(this,S.prop,e,t,1<arguments.length)},removeProp:function(e){return this.each(function(){delete this[S.propFix[e]||e]})}}),S.extend({prop:function(e,t,n){var r,i,o=e.nodeType;if(3!==o&&8!==o&&2!==o)return 1===o&&S.isXMLDoc(e)||(t=S.propFix[t]||t,i=S.propHooks[t]),void 0!==n?i&&"set"in i&&void 0!==(r=i.set(e,n,t))?r:e[t]=n:i&&"get"in i&&null!==(r=i.get(e,t))?r:e[t]},propHooks:{tabIndex:{get:function(e){var t=S.find.attr(e,"tabindex");return t?parseInt(t,10):pt.test(e.nodeName)||dt.test(e.nodeName)&&e.href?0:-1}}},propFix:{"for":"htmlFor","class":"className"}}),y.optSelected||(S.propHooks.selected={get:function(e){var t=e.parentNode;return t&&t.parentNode&&t.parentNode.selectedIndex,null},set:function(e){var t=e.parentNode;t&&(t.selectedIndex,t.parentNode&&t.parentNode.selectedIndex)}}),S.each(["tabIndex","readOnly","maxLength","cellSpacing","cellPadding","rowSpan","colSpan","useMap","frameBorder","contentEditable"],function(){S.propFix[this.toLowerCase()]=this}),S.fn.extend({addClass:function(t){var e,n,r,i,o,a,s,u=0;if(m(t))return this.each(function(e){S(this).addClass(t.call(this,e,gt(this)))});if((e=vt(t)).length)while(n=this[u++])if(i=gt(n),r=1===n.nodeType&&" "+ht(i)+" "){a=0;while(o=e[a++])r.indexOf(" "+o+" ")<0&&(r+=o+" ");i!==(s=ht(r))&&n.setAttribute("class",s)}return this},removeClass:function(t){var e,n,r,i,o,a,s,u=0;if(m(t))return this.each(function(e){S(this).removeClass(t.call(this,e,gt(this)))});if(!arguments.length)return this.attr("class","");if((e=vt(t)).length)while(n=this[u++])if(i=gt(n),r=1===n.nodeType&&" "+ht(i)+" "){a=0;while(o=e[a++])while(-1<r.indexOf(" "+o+" "))r=r.replace(" "+o+" "," ");i!==(s=ht(r))&&n.setAttribute("class",s)}return this},toggleClass:function(i,t){var o=typeof i,a="string"===o||Array.isArray(i);return"boolean"==typeof t&&a?t?this.addClass(i):this.removeClass(i):m(i)?this.each(function(e){S(this).toggleClass(i.call(this,e,gt(this),t),t)}):this.each(function(){var e,t,n,r;if(a){t=0,n=S(this),r=vt(i);while(e=r[t++])n.hasClass(e)?n.removeClass(e):n.addClass(e)}else void 0!==i&&"boolean"!==o||((e=gt(this))&&Y.set(this,"__className__",e),this.setAttribute&&this.setAttribute("class",e||!1===i?"":Y.get(this,"__className__")||""))})},hasClass:function(e){var t,n,r=0;t=" "+e+" ";while(n=this[r++])if(1===n.nodeType&&-1<(" "+ht(gt(n))+" ").indexOf(t))return!0;return!1}});var yt=/\r/g;S.fn.extend({val:function(n){var r,e,i,t=this[0];return arguments.length?(i=m(n),this.each(function(e){var t;1===this.nodeType&&(null==(t=i?n.call(this,e,S(this).val()):n)?t="":"number"==typeof t?t+="":Array.isArray(t)&&(t=S.map(t,function(e){return null==e?"":e+""})),(r=S.valHooks[this.type]||S.valHooks[this.nodeName.toLowerCase()])&&"set"in r&&void 0!==r.set(this,t,"value")||(this.value=t))})):t?(r=S.valHooks[t.type]||S.valHooks[t.nodeName.toLowerCase()])&&"get"in r&&void 0!==(e=r.get(t,"value"))?e:"string"==typeof(e=t.value)?e.replace(yt,""):null==e?"":e:void 0}}),S.extend({valHooks:{option:{get:function(e){var t=S.find.attr(e,"value");return null!=t?t:ht(S.text(e))}},select:{get:function(e){var t,n,r,i=e.options,o=e.selectedIndex,a="select-one"===e.type,s=a?null:[],u=a?o+1:i.length;for(r=o<0?u:a?o:0;r<u;r++)if(((n=i[r]).selected||r===o)&&!n.disabled&&(!n.parentNode.disabled||!A(n.parentNode,"optgroup"))){if(t=S(n).val(),a)return t;s.push(t)}return s},set:function(e,t){var n,r,i=e.options,o=S.makeArray(t),a=i.length;while(a--)((r=i[a]).selected=-1<S.inArray(S.valHooks.option.get(r),o))&&(n=!0);return n||(e.selectedIndex=-1),o}}}}),S.each(["radio","checkbox"],function(){S.valHooks[this]={set:function(e,t){if(Array.isArray(t))return e.checked=-1<S.inArray(S(e).val(),t)}},y.checkOn||(S.valHooks[this].get=function(e){return null===e.getAttribute("value")?"on":e.value})}),y.focusin="onfocusin"in C;var mt=/^(?:focusinfocus|focusoutblur)$/,xt=function(e){e.stopPropagation()};S.extend(S.event,{trigger:function(e,t,n,r){var i,o,a,s,u,l,c,f,p=[n||E],d=v.call(e,"type")?e.type:e,h=v.call(e,"namespace")?e.namespace.split("."):[];if(o=f=a=n=n||E,3!==n.nodeType&&8!==n.nodeType&&!mt.test(d+S.event.triggered)&&(-1<d.indexOf(".")&&(d=(h=d.split(".")).shift(),h.sort()),u=d.indexOf(":")<0&&"on"+d,(e=e[S.expando]?e:new S.Event(d,"object"==typeof e&&e)).isTrigger=r?2:3,e.namespace=h.join("."),e.rnamespace=e.namespace?new RegExp("(^|\\.)"+h.join("\\.(?:.*\\.|)")+"(\\.|$)"):null,e.result=void 0,e.target||(e.target=n),t=null==t?[e]:S.makeArray(t,[e]),c=S.event.special[d]||{},r||!c.trigger||!1!==c.trigger.apply(n,t))){if(!r&&!c.noBubble&&!x(n)){for(s=c.delegateType||d,mt.test(s+d)||(o=o.parentNode);o;o=o.parentNode)p.push(o),a=o;a===(n.ownerDocument||E)&&p.push(a.defaultView||a.parentWindow||C)}i=0;while((o=p[i++])&&!e.isPropagationStopped())f=o,e.type=1<i?s:c.bindType||d,(l=(Y.get(o,"events")||Object.create(null))[e.type]&&Y.get(o,"handle"))&&l.apply(o,t),(l=u&&o[u])&&l.apply&&V(o)&&(e.result=l.apply(o,t),!1===e.result&&e.preventDefault());return e.type=d,r||e.isDefaultPrevented()||c._default&&!1!==c._default.apply(p.pop(),t)||!V(n)||u&&m(n[d])&&!x(n)&&((a=n[u])&&(n[u]=null),S.event.triggered=d,e.isPropagationStopped()&&f.addEventListener(d,xt),n[d](),e.isPropagationStopped()&&f.removeEventListener(d,xt),S.event.triggered=void 0,a&&(n[u]=a)),e.result}},simulate:function(e,t,n){var r=S.extend(new S.Event,n,{type:e,isSimulated:!0});S.event.trigger(r,null,t)}}),S.fn.extend({trigger:function(e,t){return this.each(function(){S.event.trigger(e,t,this)})},triggerHandler:function(e,t){var n=this[0];if(n)return S.event.trigger(e,t,n,!0)}}),y.focusin||S.each({focus:"focusin",blur:"focusout"},function(n,r){var i=function(e){S.event.simulate(r,e.target,S.event.fix(e))};S.event.special[r]={setup:function(){var e=this.ownerDocument||this.document||this,t=Y.access(e,r);t||e.addEventListener(n,i,!0),Y.access(e,r,(t||0)+1)},teardown:function(){var e=this.ownerDocument||this.document||this,t=Y.access(e,r)-1;t?Y.access(e,r,t):(e.removeEventListener(n,i,!0),Y.remove(e,r))}}});var bt=C.location,wt={guid:Date.now()},Tt=/\?/;S.parseXML=function(e){var t,n;if(!e||"string"!=typeof e)return null;try{t=(new C.DOMParser).parseFromString(e,"text/xml")}catch(e){}return n=t&&t.getElementsByTagName("parsererror")[0],t&&!n||S.error("Invalid XML: "+(n?S.map(n.childNodes,function(e){return e.textContent}).join("\n"):e)),t};var Ct=/\[\]$/,Et=/\r?\n/g,St=/^(?:submit|button|image|reset|file)$/i,kt=/^(?:input|select|textarea|keygen)/i;function At(n,e,r,i){var t;if(Array.isArray(e))S.each(e,function(e,t){r||Ct.test(n)?i(n,t):At(n+"["+("object"==typeof t&&null!=t?e:"")+"]",t,r,i)});else if(r||"object"!==w(e))i(n,e);else for(t in e)At(n+"["+t+"]",e[t],r,i)}S.param=function(e,t){var n,r=[],i=function(e,t){var n=m(t)?t():t;r[r.length]=encodeURIComponent(e)+"="+encodeURIComponent(null==n?"":n)};if(null==e)return"";if(Array.isArray(e)||e.jquery&&!S.isPlainObject(e))S.each(e,function(){i(this.name,this.value)});else for(n in e)At(n,e[n],t,i);return r.join("&")},S.fn.extend({serialize:function(){return S.param(this.serializeArray())},serializeArray:function(){return this.map(function(){var e=S.prop(this,"elements");return e?S.makeArray(e):this}).filter(function(){var e=this.type;return this.name&&!S(this).is(":disabled")&&kt.test(this.nodeName)&&!St.test(e)&&(this.checked||!pe.test(e))}).map(function(e,t){var n=S(this).val();return null==n?null:Array.isArray(n)?S.map(n,function(e){return{name:t.name,value:e.replace(Et,"\r\n")}}):{name:t.name,value:n.replace(Et,"\r\n")}}).get()}});var Nt=/%20/g,jt=/#.*$/,Dt=/([?&])_=[^&]*/,qt=/^(.*?):[ \t]*([^\r\n]*)$/gm,Lt=/^(?:GET|HEAD)$/,Ht=/^\/\//,Ot={},Pt={},Rt="*/".concat("*"),Mt=E.createElement("a");function It(o){return function(e,t){"string"!=typeof e&&(t=e,e="*");var n,r=0,i=e.toLowerCase().match(P)||[];if(m(t))while(n=i[r++])"+"===n[0]?(n=n.slice(1)||"*",(o[n]=o[n]||[]).unshift(t)):(o[n]=o[n]||[]).push(t)}}function Wt(t,i,o,a){var s={},u=t===Pt;function l(e){var r;return s[e]=!0,S.each(t[e]||[],function(e,t){var n=t(i,o,a);return"string"!=typeof n||u||s[n]?u?!(r=n):void 0:(i.dataTypes.unshift(n),l(n),!1)}),r}return l(i.dataTypes[0])||!s["*"]&&l("*")}function Ft(e,t){var n,r,i=S.ajaxSettings.flatOptions||{};for(n in t)void 0!==t[n]&&((i[n]?e:r||(r={}))[n]=t[n]);return r&&S.extend(!0,e,r),e}Mt.href=bt.href,S.extend({active:0,lastModified:{},etag:{},ajaxSettings:{url:bt.href,type:"GET",isLocal:/^(?:about|app|app-storage|.+-extension|file|res|widget):$/.test(bt.protocol),global:!0,processData:!0,async:!0,contentType:"application/x-www-form-urlencoded; charset=UTF-8",accepts:{"*":Rt,text:"text/plain",html:"text/html",xml:"application/xml, text/xml",json:"application/json, text/javascript"},contents:{xml:/\bxml\b/,html:/\bhtml/,json:/\bjson\b/},responseFields:{xml:"responseXML",text:"responseText",json:"responseJSON"},converters:{"* text":String,"text html":!0,"text json":JSON.parse,"text xml":S.parseXML},flatOptions:{url:!0,context:!0}},ajaxSetup:function(e,t){return t?Ft(Ft(e,S.ajaxSettings),t):Ft(S.ajaxSettings,e)},ajaxPrefilter:It(Ot),ajaxTransport:It(Pt),ajax:function(e,t){"object"==typeof e&&(t=e,e=void 0),t=t||{};var c,f,p,n,d,r,h,g,i,o,v=S.ajaxSetup({},t),y=v.context||v,m=v.context&&(y.nodeType||y.jquery)?S(y):S.event,x=S.Deferred(),b=S.Callbacks("once memory"),w=v.statusCode||{},a={},s={},u="canceled",T={readyState:0,getResponseHeader:function(e){var t;if(h){if(!n){n={};while(t=qt.exec(p))n[t[1].toLowerCase()+" "]=(n[t[1].toLowerCase()+" "]||[]).concat(t[2])}t=n[e.toLowerCase()+" "]}return null==t?null:t.join(", ")},getAllResponseHeaders:function(){return h?p:null},setRequestHeader:function(e,t){return null==h&&(e=s[e.toLowerCase()]=s[e.toLowerCase()]||e,a[e]=t),this},overrideMimeType:function(e){return null==h&&(v.mimeType=e),this},statusCode:function(e){var t;if(e)if(h)T.always(e[T.status]);else for(t in e)w[t]=[w[t],e[t]];return this},abort:function(e){var t=e||u;return c&&c.abort(t),l(0,t),this}};if(x.promise(T),v.url=((e||v.url||bt.href)+"").replace(Ht,bt.protocol+"//"),v.type=t.method||t.type||v.method||v.type,v.dataTypes=(v.dataType||"*").toLowerCase().match(P)||[""],null==v.crossDomain){r=E.createElement("a");try{r.href=v.url,r.href=r.href,v.crossDomain=Mt.protocol+"//"+Mt.host!=r.protocol+"//"+r.host}catch(e){v.crossDomain=!0}}if(v.data&&v.processData&&"string"!=typeof v.data&&(v.data=S.param(v.data,v.traditional)),Wt(Ot,v,t,T),h)return T;for(i in(g=S.event&&v.global)&&0==S.active++&&S.event.trigger("ajaxStart"),v.type=v.type.toUpperCase(),v.hasContent=!Lt.test(v.type),f=v.url.replace(jt,""),v.hasContent?v.data&&v.processData&&0===(v.contentType||"").indexOf("application/x-www-form-urlencoded")&&(v.data=v.data.replace(Nt,"+")):(o=v.url.slice(f.length),v.data&&(v.processData||"string"==typeof v.data)&&(f+=(Tt.test(f)?"&":"?")+v.data,delete v.data),!1===v.cache&&(f=f.replace(Dt,"$1"),o=(Tt.test(f)?"&":"?")+"_="+wt.guid+++o),v.url=f+o),v.ifModified&&(S.lastModified[f]&&T.setRequestHeader("If-Modified-Since",S.lastModified[f]),S.etag[f]&&T.setRequestHeader("If-None-Match",S.etag[f])),(v.data&&v.hasContent&&!1!==v.contentType||t.contentType)&&T.setRequestHeader("Content-Type",v.contentType),T.setRequestHeader("Accept",v.dataTypes[0]&&v.accepts[v.dataTypes[0]]?v.accepts[v.dataTypes[0]]+("*"!==v.dataTypes[0]?", "+Rt+"; q=0.01":""):v.accepts["*"]),v.headers)T.setRequestHeader(i,v.headers[i]);if(v.beforeSend&&(!1===v.beforeSend.call(y,T,v)||h))return T.abort();if(u="abort",b.add(v.complete),T.done(v.success),T.fail(v.error),c=Wt(Pt,v,t,T)){if(T.readyState=1,g&&m.trigger("ajaxSend",[T,v]),h)return T;v.async&&0<v.timeout&&(d=C.setTimeout(function(){T.abort("timeout")},v.timeout));try{h=!1,c.send(a,l)}catch(e){if(h)throw e;l(-1,e)}}else l(-1,"No Transport");function l(e,t,n,r){var i,o,a,s,u,l=t;h||(h=!0,d&&C.clearTimeout(d),c=void 0,p=r||"",T.readyState=0<e?4:0,i=200<=e&&e<300||304===e,n&&(s=function(e,t,n){var r,i,o,a,s=e.contents,u=e.dataTypes;while("*"===u[0])u.shift(),void 0===r&&(r=e.mimeType||t.getResponseHeader("Content-Type"));if(r)for(i in s)if(s[i]&&s[i].test(r)){u.unshift(i);break}if(u[0]in n)o=u[0];else{for(i in n){if(!u[0]||e.converters[i+" "+u[0]]){o=i;break}a||(a=i)}o=o||a}if(o)return o!==u[0]&&u.unshift(o),n[o]}(v,T,n)),!i&&-1<S.inArray("script",v.dataTypes)&&S.inArray("json",v.dataTypes)<0&&(v.converters["text script"]=function(){}),s=function(e,t,n,r){var i,o,a,s,u,l={},c=e.dataTypes.slice();if(c[1])for(a in e.converters)l[a.toLowerCase()]=e.converters[a];o=c.shift();while(o)if(e.responseFields[o]&&(n[e.responseFields[o]]=t),!u&&r&&e.dataFilter&&(t=e.dataFilter(t,e.dataType)),u=o,o=c.shift())if("*"===o)o=u;else if("*"!==u&&u!==o){if(!(a=l[u+" "+o]||l["* "+o]))for(i in l)if((s=i.split(" "))[1]===o&&(a=l[u+" "+s[0]]||l["* "+s[0]])){!0===a?a=l[i]:!0!==l[i]&&(o=s[0],c.unshift(s[1]));break}if(!0!==a)if(a&&e["throws"])t=a(t);else try{t=a(t)}catch(e){return{state:"parsererror",error:a?e:"No conversion from "+u+" to "+o}}}return{state:"success",data:t}}(v,s,T,i),i?(v.ifModified&&((u=T.getResponseHeader("Last-Modified"))&&(S.lastModified[f]=u),(u=T.getResponseHeader("etag"))&&(S.etag[f]=u)),204===e||"HEAD"===v.type?l="nocontent":304===e?l="notmodified":(l=s.state,o=s.data,i=!(a=s.error))):(a=l,!e&&l||(l="error",e<0&&(e=0))),T.status=e,T.statusText=(t||l)+"",i?x.resolveWith(y,[o,l,T]):x.rejectWith(y,[T,l,a]),T.statusCode(w),w=void 0,g&&m.trigger(i?"ajaxSuccess":"ajaxError",[T,v,i?o:a]),b.fireWith(y,[T,l]),g&&(m.trigger("ajaxComplete",[T,v]),--S.active||S.event.trigger("ajaxStop")))}return T},getJSON:function(e,t,n){return S.get(e,t,n,"json")},getScript:function(e,t){return S.get(e,void 0,t,"script")}}),S.each(["get","post"],function(e,i){S[i]=function(e,t,n,r){return m(t)&&(r=r||n,n=t,t=void 0),S.ajax(S.extend({url:e,type:i,dataType:r,data:t,success:n},S.isPlainObject(e)&&e))}}),S.ajaxPrefilter(function(e){var t;for(t in e.headers)"content-type"===t.toLowerCase()&&(e.contentType=e.headers[t]||"")}),S._evalUrl=function(e,t,n){return S.ajax({url:e,type:"GET",dataType:"script",cache:!0,async:!1,global:!1,converters:{"text script":function(){}},dataFilter:function(e){S.globalEval(e,t,n)}})},S.fn.extend({wrapAll:function(e){var t;return this[0]&&(m(e)&&(e=e.call(this[0])),t=S(e,this[0].ownerDocument).eq(0).clone(!0),this[0].parentNode&&t.insertBefore(this[0]),t.map(function(){var e=this;while(e.firstElementChild)e=e.firstElementChild;return e}).append(this)),this},wrapInner:function(n){return m(n)?this.each(function(e){S(this).wrapInner(n.call(this,e))}):this.each(function(){var e=S(this),t=e.contents();t.length?t.wrapAll(n):e.append(n)})},wrap:function(t){var n=m(t);return this.each(function(e){S(this).wrapAll(n?t.call(this,e):t)})},unwrap:function(e){return this.parent(e).not("body").each(function(){S(this).replaceWith(this.childNodes)}),this}}),S.expr.pseudos.hidden=function(e){return!S.expr.pseudos.visible(e)},S.expr.pseudos.visible=function(e){return!!(e.offsetWidth||e.offsetHeight||e.getClientRects().length)},S.ajaxSettings.xhr=function(){try{return new C.XMLHttpRequest}catch(e){}};var Bt={0:200,1223:204},$t=S.ajaxSettings.xhr();y.cors=!!$t&&"withCredentials"in $t,y.ajax=$t=!!$t,S.ajaxTransport(function(i){var o,a;if(y.cors||$t&&!i.crossDomain)return{send:function(e,t){var n,r=i.xhr();if(r.open(i.type,i.url,i.async,i.username,i.password),i.xhrFields)for(n in i.xhrFields)r[n]=i.xhrFields[n];for(n in i.mimeType&&r.overrideMimeType&&r.overrideMimeType(i.mimeType),i.crossDomain||e["X-Requested-With"]||(e["X-Requested-With"]="XMLHttpRequest"),e)r.setRequestHeader(n,e[n]);o=function(e){return function(){o&&(o=a=r.onload=r.onerror=r.onabort=r.ontimeout=r.onreadystatechange=null,"abort"===e?r.abort():"error"===e?"number"!=typeof r.status?t(0,"error"):t(r.status,r.statusText):t(Bt[r.status]||r.status,r.statusText,"text"!==(r.responseType||"text")||"string"!=typeof r.responseText?{binary:r.response}:{text:r.responseText},r.getAllResponseHeaders()))}},r.onload=o(),a=r.onerror=r.ontimeout=o("error"),void 0!==r.onabort?r.onabort=a:r.onreadystatechange=function(){4===r.readyState&&C.setTimeout(function(){o&&a()})},o=o("abort");try{r.send(i.hasContent&&i.data||null)}catch(e){if(o)throw e}},abort:function(){o&&o()}}}),S.ajaxPrefilter(function(e){e.crossDomain&&(e.contents.script=!1)}),S.ajaxSetup({accepts:{script:"text/javascript, application/javascript, application/ecmascript, application/x-ecmascript"},contents:{script:/\b(?:java|ecma)script\b/},converters:{"text script":function(e){return S.globalEval(e),e}}}),S.ajaxPrefilter("script",function(e){void 0===e.cache&&(e.cache=!1),e.crossDomain&&(e.type="GET")}),S.ajaxTransport("script",function(n){var r,i;if(n.crossDomain||n.scriptAttrs)return{send:function(e,t){r=S("<script>").attr(n.scriptAttrs||{}).prop({charset:n.scriptCharset,src:n.url}).on("load error",i=function(e){r.remove(),i=null,e&&t("error"===e.type?404:200,e.type)}),E.head.appendChild(r[0])},abort:function(){i&&i()}}});var _t,zt=[],Ut=/(=)\?(?=&|$)|\?\?/;S.ajaxSetup({jsonp:"callback",jsonpCallback:function(){var e=zt.pop()||S.expando+"_"+wt.guid++;return this[e]=!0,e}}),S.ajaxPrefilter("json jsonp",function(e,t,n){var r,i,o,a=!1!==e.jsonp&&(Ut.test(e.url)?"url":"string"==typeof e.data&&0===(e.contentType||"").indexOf("application/x-www-form-urlencoded")&&Ut.test(e.data)&&"data");if(a||"jsonp"===e.dataTypes[0])return r=e.jsonpCallback=m(e.jsonpCallback)?e.jsonpCallback():e.jsonpCallback,a?e[a]=e[a].replace(Ut,"$1"+r):!1!==e.jsonp&&(e.url+=(Tt.test(e.url)?"&":"?")+e.jsonp+"="+r),e.converters["script json"]=function(){return o||S.error(r+" was not called"),o[0]},e.dataTypes[0]="json",i=C[r],C[r]=function(){o=arguments},n.always(function(){void 0===i?S(C).removeProp(r):C[r]=i,e[r]&&(e.jsonpCallback=t.jsonpCallback,zt.push(r)),o&&m(i)&&i(o[0]),o=i=void 0}),"script"}),y.createHTMLDocument=((_t=E.implementation.createHTMLDocument("").body).innerHTML="<form></form><form></form>",2===_t.childNodes.length),S.parseHTML=function(e,t,n){return"string"!=typeof e?[]:("boolean"==typeof t&&(n=t,t=!1),t||(y.createHTMLDocument?((r=(t=E.implementation.createHTMLDocument("")).createElement("base")).href=E.location.href,t.head.appendChild(r)):t=E),o=!n&&[],(i=N.exec(e))?[t.createElement(i[1])]:(i=xe([e],t,o),o&&o.length&&S(o).remove(),S.merge([],i.childNodes)));var r,i,o},S.fn.load=function(e,t,n){var r,i,o,a=this,s=e.indexOf(" ");return-1<s&&(r=ht(e.slice(s)),e=e.slice(0,s)),m(t)?(n=t,t=void 0):t&&"object"==typeof t&&(i="POST"),0<a.length&&S.ajax({url:e,type:i||"GET",dataType:"html",data:t}).done(function(e){o=arguments,a.html(r?S("<div>").append(S.parseHTML(e)).find(r):e)}).always(n&&function(e,t){a.each(function(){n.apply(this,o||[e.responseText,t,e])})}),this},S.expr.pseudos.animated=function(t){return S.grep(S.timers,function(e){return t===e.elem}).length},S.offset={setOffset:function(e,t,n){var r,i,o,a,s,u,l=S.css(e,"position"),c=S(e),f={};"static"===l&&(e.style.position="relative"),s=c.offset(),o=S.css(e,"top"),u=S.css(e,"left"),("absolute"===l||"fixed"===l)&&-1<(o+u).indexOf("auto")?(a=(r=c.position()).top,i=r.left):(a=parseFloat(o)||0,i=parseFloat(u)||0),m(t)&&(t=t.call(e,n,S.extend({},s))),null!=t.top&&(f.top=t.top-s.top+a),null!=t.left&&(f.left=t.left-s.left+i),"using"in t?t.using.call(e,f):c.css(f)}},S.fn.extend({offset:function(t){if(arguments.length)return void 0===t?this:this.each(function(e){S.offset.setOffset(this,t,e)});var e,n,r=this[0];return r?r.getClientRects().length?(e=r.getBoundingClientRect(),n=r.ownerDocument.defaultView,{top:e.top+n.pageYOffset,left:e.left+n.pageXOffset}):{top:0,left:0}:void 0},position:function(){if(this[0]){var e,t,n,r=this[0],i={top:0,left:0};if("fixed"===S.css(r,"position"))t=r.getBoundingClientRect();else{t=this.offset(),n=r.ownerDocument,e=r.offsetParent||n.documentElement;while(e&&(e===n.body||e===n.documentElement)&&"static"===S.css(e,"position"))e=e.parentNode;e&&e!==r&&1===e.nodeType&&((i=S(e).offset()).top+=S.css(e,"borderTopWidth",!0),i.left+=S.css(e,"borderLeftWidth",!0))}return{top:t.top-i.top-S.css(r,"marginTop",!0),left:t.left-i.left-S.css(r,"marginLeft",!0)}}},offsetParent:function(){return this.map(function(){var e=this.offsetParent;while(e&&"static"===S.css(e,"position"))e=e.offsetParent;return e||re})}}),S.each({scrollLeft:"pageXOffset",scrollTop:"pageYOffset"},function(t,i){var o="pageYOffset"===i;S.fn[t]=function(e){return $(this,function(e,t,n){var r;if(x(e)?r=e:9===e.nodeType&&(r=e.defaultView),void 0===n)return r?r[i]:e[t];r?r.scrollTo(o?r.pageXOffset:n,o?n:r.pageYOffset):e[t]=n},t,e,arguments.length)}}),S.each(["top","left"],function(e,n){S.cssHooks[n]=Fe(y.pixelPosition,function(e,t){if(t)return t=We(e,n),Pe.test(t)?S(e).position()[n]+"px":t})}),S.each({Height:"height",Width:"width"},function(a,s){S.each({padding:"inner"+a,content:s,"":"outer"+a},function(r,o){S.fn[o]=function(e,t){var n=arguments.length&&(r||"boolean"!=typeof e),i=r||(!0===e||!0===t?"margin":"border");return $(this,function(e,t,n){var r;return x(e)?0===o.indexOf("outer")?e["inner"+a]:e.document.documentElement["client"+a]:9===e.nodeType?(r=e.documentElement,Math.max(e.body["scroll"+a],r["scroll"+a],e.body["offset"+a],r["offset"+a],r["client"+a])):void 0===n?S.css(e,t,i):S.style(e,t,n,i)},s,n?e:void 0,n)}})}),S.each(["ajaxStart","ajaxStop","ajaxComplete","ajaxError","ajaxSuccess","ajaxSend"],function(e,t){S.fn[t]=function(e){return this.on(t,e)}}),S.fn.extend({bind:function(e,t,n){return this.on(e,null,t,n)},unbind:function(e,t){return this.off(e,null,t)},delegate:function(e,t,n,r){return this.on(t,e,n,r)},undelegate:function(e,t,n){return 1===arguments.length?this.off(e,"**"):this.off(t,e||"**",n)},hover:function(e,t){return this.mouseenter(e).mouseleave(t||e)}}),S.each("blur focus focusin focusout resize scroll click dblclick mousedown mouseup mousemove mouseover mouseout mouseenter mouseleave change select submit keydown keypress keyup contextmenu".split(" "),function(e,n){S.fn[n]=function(e,t){return 0<arguments.length?this.on(n,null,e,t):this.trigger(n)}});var Xt=/^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g;S.proxy=function(e,t){var n,r,i;if("string"==typeof t&&(n=e[t],t=e,e=n),m(e))return r=s.call(arguments,2),(i=function(){return e.apply(t||this,r.concat(s.call(arguments)))}).guid=e.guid=e.guid||S.guid++,i},S.holdReady=function(e){e?S.readyWait++:S.ready(!0)},S.isArray=Array.isArray,S.parseJSON=JSON.parse,S.nodeName=A,S.isFunction=m,S.isWindow=x,S.camelCase=X,S.type=w,S.now=Date.now,S.isNumeric=function(e){var t=S.type(e);return("number"===t||"string"===t)&&!isNaN(e-parseFloat(e))},S.trim=function(e){return null==e?"":(e+"").replace(Xt,"")},"function"==typeof define&&define.amd&&define("jquery",[],function(){return S});var Vt=C.jQuery,Gt=C.$;return S.noConflict=function(e){return C.$===S&&(C.$=Gt),e&&C.jQuery===S&&(C.jQuery=Vt),S},"undefined"==typeof e&&(C.jQuery=C.$=S),S});
diff --git a/docs/_static/language_data.js b/docs/_static/language_data.js
index ebe2f03b..2e22b06a 100644
--- a/docs/_static/language_data.js
+++ b/docs/_static/language_data.js
@@ -10,7 +10,7 @@
  *
  */
 
-var stopwords = ["a","and","are","as","at","be","but","by","for","if","in","into","is","it","near","no","not","of","on","or","such","that","the","their","then","there","these","they","this","to","was","will","with"];
+var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
 
 
 /* Non-minified version is copied as a separate JS file, is available */
@@ -197,101 +197,3 @@ var Stemmer = function() {
   }
 }
 
-
-
-
-var splitChars = (function() {
-    var result = {};
-    var singles = [96, 180, 187, 191, 215, 247, 749, 885, 903, 907, 909, 930, 1014, 1648,
-         1748, 1809, 2416, 2473, 2481, 2526, 2601, 2609, 2612, 2615, 2653, 2702,
-         2706, 2729, 2737, 2740, 2857, 2865, 2868, 2910, 2928, 2948, 2961, 2971,
-         2973, 3085, 3089, 3113, 3124, 3213, 3217, 3241, 3252, 3295, 3341, 3345,
-         3369, 3506, 3516, 3633, 3715, 3721, 3736, 3744, 3748, 3750, 3756, 3761,
-         3781, 3912, 4239, 4347, 4681, 4695, 4697, 4745, 4785, 4799, 4801, 4823,
-         4881, 5760, 5901, 5997, 6313, 7405, 8024, 8026, 8028, 8030, 8117, 8125,
-         8133, 8181, 8468, 8485, 8487, 8489, 8494, 8527, 11311, 11359, 11687, 11695,
-         11703, 11711, 11719, 11727, 11735, 12448, 12539, 43010, 43014, 43019, 43587,
-         43696, 43713, 64286, 64297, 64311, 64317, 64319, 64322, 64325, 65141];
-    var i, j, start, end;
-    for (i = 0; i < singles.length; i++) {
-        result[singles[i]] = true;
-    }
-    var ranges = [[0, 47], [58, 64], [91, 94], [123, 169], [171, 177], [182, 184], [706, 709],
-         [722, 735], [741, 747], [751, 879], [888, 889], [894, 901], [1154, 1161],
-         [1318, 1328], [1367, 1368], [1370, 1376], [1416, 1487], [1515, 1519], [1523, 1568],
-         [1611, 1631], [1642, 1645], [1750, 1764], [1767, 1773], [1789, 1790], [1792, 1807],
-         [1840, 1868], [1958, 1968], [1970, 1983], [2027, 2035], [2038, 2041], [2043, 2047],
-         [2070, 2073], [2075, 2083], [2085, 2087], [2089, 2307], [2362, 2364], [2366, 2383],
-         [2385, 2391], [2402, 2405], [2419, 2424], [2432, 2436], [2445, 2446], [2449, 2450],
-         [2483, 2485], [2490, 2492], [2494, 2509], [2511, 2523], [2530, 2533], [2546, 2547],
-         [2554, 2564], [2571, 2574], [2577, 2578], [2618, 2648], [2655, 2661], [2672, 2673],
-         [2677, 2692], [2746, 2748], [2750, 2767], [2769, 2783], [2786, 2789], [2800, 2820],
-         [2829, 2830], [2833, 2834], [2874, 2876], [2878, 2907], [2914, 2917], [2930, 2946],
-         [2955, 2957], [2966, 2968], [2976, 2978], [2981, 2983], [2987, 2989], [3002, 3023],
-         [3025, 3045], [3059, 3076], [3130, 3132], [3134, 3159], [3162, 3167], [3170, 3173],
-         [3184, 3191], [3199, 3204], [3258, 3260], [3262, 3293], [3298, 3301], [3312, 3332],
-         [3386, 3388], [3390, 3423], [3426, 3429], [3446, 3449], [3456, 3460], [3479, 3481],
-         [3518, 3519], [3527, 3584], [3636, 3647], [3655, 3663], [3674, 3712], [3717, 3718],
-         [3723, 3724], [3726, 3731], [3752, 3753], [3764, 3772], [3774, 3775], [3783, 3791],
-         [3802, 3803], [3806, 3839], [3841, 3871], [3892, 3903], [3949, 3975], [3980, 4095],
-         [4139, 4158], [4170, 4175], [4182, 4185], [4190, 4192], [4194, 4196], [4199, 4205],
-         [4209, 4212], [4226, 4237], [4250, 4255], [4294, 4303], [4349, 4351], [4686, 4687],
-         [4702, 4703], [4750, 4751], [4790, 4791], [4806, 4807], [4886, 4887], [4955, 4968],
-         [4989, 4991], [5008, 5023], [5109, 5120], [5741, 5742], [5787, 5791], [5867, 5869],
-         [5873, 5887], [5906, 5919], [5938, 5951], [5970, 5983], [6001, 6015], [6068, 6102],
-         [6104, 6107], [6109, 6111], [6122, 6127], [6138, 6159], [6170, 6175], [6264, 6271],
-         [6315, 6319], [6390, 6399], [6429, 6469], [6510, 6511], [6517, 6527], [6572, 6592],
-         [6600, 6607], [6619, 6655], [6679, 6687], [6741, 6783], [6794, 6799], [6810, 6822],
-         [6824, 6916], [6964, 6980], [6988, 6991], [7002, 7042], [7073, 7085], [7098, 7167],
-         [7204, 7231], [7242, 7244], [7294, 7400], [7410, 7423], [7616, 7679], [7958, 7959],
-         [7966, 7967], [8006, 8007], [8014, 8015], [8062, 8063], [8127, 8129], [8141, 8143],
-         [8148, 8149], [8156, 8159], [8173, 8177], [8189, 8303], [8306, 8307], [8314, 8318],
-         [8330, 8335], [8341, 8449], [8451, 8454], [8456, 8457], [8470, 8472], [8478, 8483],
-         [8506, 8507], [8512, 8516], [8522, 8525], [8586, 9311], [9372, 9449], [9472, 10101],
-         [10132, 11263], [11493, 11498], [11503, 11516], [11518, 11519], [11558, 11567],
-         [11622, 11630], [11632, 11647], [11671, 11679], [11743, 11822], [11824, 12292],
-         [12296, 12320], [12330, 12336], [12342, 12343], [12349, 12352], [12439, 12444],
-         [12544, 12548], [12590, 12592], [12687, 12689], [12694, 12703], [12728, 12783],
-         [12800, 12831], [12842, 12880], [12896, 12927], [12938, 12976], [12992, 13311],
-         [19894, 19967], [40908, 40959], [42125, 42191], [42238, 42239], [42509, 42511],
-         [42540, 42559], [42592, 42593], [42607, 42622], [42648, 42655], [42736, 42774],
-         [42784, 42785], [42889, 42890], [42893, 43002], [43043, 43055], [43062, 43071],
-         [43124, 43137], [43188, 43215], [43226, 43249], [43256, 43258], [43260, 43263],
-         [43302, 43311], [43335, 43359], [43389, 43395], [43443, 43470], [43482, 43519],
-         [43561, 43583], [43596, 43599], [43610, 43615], [43639, 43641], [43643, 43647],
-         [43698, 43700], [43703, 43704], [43710, 43711], [43715, 43738], [43742, 43967],
-         [44003, 44015], [44026, 44031], [55204, 55215], [55239, 55242], [55292, 55295],
-         [57344, 63743], [64046, 64047], [64110, 64111], [64218, 64255], [64263, 64274],
-         [64280, 64284], [64434, 64466], [64830, 64847], [64912, 64913], [64968, 65007],
-         [65020, 65135], [65277, 65295], [65306, 65312], [65339, 65344], [65371, 65381],
-         [65471, 65473], [65480, 65481], [65488, 65489], [65496, 65497]];
-    for (i = 0; i < ranges.length; i++) {
-        start = ranges[i][0];
-        end = ranges[i][1];
-        for (j = start; j <= end; j++) {
-            result[j] = true;
-        }
-    }
-    return result;
-})();
-
-function splitQuery(query) {
-    var result = [];
-    var start = -1;
-    for (var i = 0; i < query.length; i++) {
-        if (splitChars[query.charCodeAt(i)]) {
-            if (start !== -1) {
-                result.push(query.slice(start, i));
-                start = -1;
-            }
-        } else if (start === -1) {
-            start = i;
-        }
-    }
-    if (start !== -1) {
-        result.push(query.slice(start));
-    }
-    return result;
-}
-
-
diff --git a/docs/_static/pygments.css b/docs/_static/pygments.css
index 582d5c3a..08bec689 100644
--- a/docs/_static/pygments.css
+++ b/docs/_static/pygments.css
@@ -5,22 +5,22 @@ td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5
 span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
 .highlight .hll { background-color: #ffffcc }
 .highlight { background: #f8f8f8; }
-.highlight .c { color: #408080; font-style: italic } /* Comment */
+.highlight .c { color: #3D7B7B; font-style: italic } /* Comment */
 .highlight .err { border: 1px solid #FF0000 } /* Error */
 .highlight .k { color: #008000; font-weight: bold } /* Keyword */
 .highlight .o { color: #666666 } /* Operator */
-.highlight .ch { color: #408080; font-style: italic } /* Comment.Hashbang */
-.highlight .cm { color: #408080; font-style: italic } /* Comment.Multiline */
-.highlight .cp { color: #BC7A00 } /* Comment.Preproc */
-.highlight .cpf { color: #408080; font-style: italic } /* Comment.PreprocFile */
-.highlight .c1 { color: #408080; font-style: italic } /* Comment.Single */
-.highlight .cs { color: #408080; font-style: italic } /* Comment.Special */
+.highlight .ch { color: #3D7B7B; font-style: italic } /* Comment.Hashbang */
+.highlight .cm { color: #3D7B7B; font-style: italic } /* Comment.Multiline */
+.highlight .cp { color: #9C6500 } /* Comment.Preproc */
+.highlight .cpf { color: #3D7B7B; font-style: italic } /* Comment.PreprocFile */
+.highlight .c1 { color: #3D7B7B; font-style: italic } /* Comment.Single */
+.highlight .cs { color: #3D7B7B; font-style: italic } /* Comment.Special */
 .highlight .gd { color: #A00000 } /* Generic.Deleted */
 .highlight .ge { font-style: italic } /* Generic.Emph */
-.highlight .gr { color: #FF0000 } /* Generic.Error */
+.highlight .gr { color: #E40000 } /* Generic.Error */
 .highlight .gh { color: #000080; font-weight: bold } /* Generic.Heading */
-.highlight .gi { color: #00A000 } /* Generic.Inserted */
-.highlight .go { color: #888888 } /* Generic.Output */
+.highlight .gi { color: #008400 } /* Generic.Inserted */
+.highlight .go { color: #717171 } /* Generic.Output */
 .highlight .gp { color: #000080; font-weight: bold } /* Generic.Prompt */
 .highlight .gs { font-weight: bold } /* Generic.Strong */
 .highlight .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
@@ -33,15 +33,15 @@ span.linenos.special { color: #000000; background-color: #ffffc0; padding-left:
 .highlight .kt { color: #B00040 } /* Keyword.Type */
 .highlight .m { color: #666666 } /* Literal.Number */
 .highlight .s { color: #BA2121 } /* Literal.String */
-.highlight .na { color: #7D9029 } /* Name.Attribute */
+.highlight .na { color: #687822 } /* Name.Attribute */
 .highlight .nb { color: #008000 } /* Name.Builtin */
 .highlight .nc { color: #0000FF; font-weight: bold } /* Name.Class */
 .highlight .no { color: #880000 } /* Name.Constant */
 .highlight .nd { color: #AA22FF } /* Name.Decorator */
-.highlight .ni { color: #999999; font-weight: bold } /* Name.Entity */
-.highlight .ne { color: #D2413A; font-weight: bold } /* Name.Exception */
+.highlight .ni { color: #717171; font-weight: bold } /* Name.Entity */
+.highlight .ne { color: #CB3F38; font-weight: bold } /* Name.Exception */
 .highlight .nf { color: #0000FF } /* Name.Function */
-.highlight .nl { color: #A0A000 } /* Name.Label */
+.highlight .nl { color: #767600 } /* Name.Label */
 .highlight .nn { color: #0000FF; font-weight: bold } /* Name.Namespace */
 .highlight .nt { color: #008000; font-weight: bold } /* Name.Tag */
 .highlight .nv { color: #19177C } /* Name.Variable */
@@ -58,11 +58,11 @@ span.linenos.special { color: #000000; background-color: #ffffc0; padding-left:
 .highlight .dl { color: #BA2121 } /* Literal.String.Delimiter */
 .highlight .sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */
 .highlight .s2 { color: #BA2121 } /* Literal.String.Double */
-.highlight .se { color: #BB6622; font-weight: bold } /* Literal.String.Escape */
+.highlight .se { color: #AA5D1F; font-weight: bold } /* Literal.String.Escape */
 .highlight .sh { color: #BA2121 } /* Literal.String.Heredoc */
-.highlight .si { color: #BB6688; font-weight: bold } /* Literal.String.Interpol */
+.highlight .si { color: #A45A77; font-weight: bold } /* Literal.String.Interpol */
 .highlight .sx { color: #008000 } /* Literal.String.Other */
-.highlight .sr { color: #BB6688 } /* Literal.String.Regex */
+.highlight .sr { color: #A45A77 } /* Literal.String.Regex */
 .highlight .s1 { color: #BA2121 } /* Literal.String.Single */
 .highlight .ss { color: #19177C } /* Literal.String.Symbol */
 .highlight .bp { color: #008000 } /* Name.Builtin.Pseudo */
diff --git a/docs/_static/searchtools.js b/docs/_static/searchtools.js
index 2d778593..e89e34d4 100644
--- a/docs/_static/searchtools.js
+++ b/docs/_static/searchtools.js
@@ -8,18 +8,20 @@
  * :license: BSD, see LICENSE for details.
  *
  */
+"use strict";
 
-if (!Scorer) {
-  /**
-   * Simple result scoring code.
-   */
+/**
+ * Simple result scoring code.
+ */
+if (typeof Scorer === "undefined") {
   var Scorer = {
     // Implement the following function to further tweak the score for each result
-    // The function takes a result array [filename, title, anchor, descr, score]
+    // The function takes a result array [docname, title, anchor, descr, score, filename]
     // and returns the new score.
     /*
-    score: function(result) {
-      return result[4];
+    score: result => {
+      const [docname, title, anchor, descr, score, filename] = result
+      return score
     },
     */
 
@@ -28,9 +30,11 @@ if (!Scorer) {
     // or matches in the last dotted part of the object name
     objPartialMatch: 6,
     // Additive scores depending on the priority of the object
-    objPrio: {0:  15,   // used to be importantResults
-              1:  5,   // used to be objectResults
-              2: -5},  // used to be unimportantResults
+    objPrio: {
+      0: 15, // used to be importantResults
+      1: 5, // used to be objectResults
+      2: -5, // used to be unimportantResults
+    },
     //  Used when the priority is not in the mapping.
     objPrioDefault: 0,
 
@@ -39,456 +43,495 @@ if (!Scorer) {
     partialTitle: 7,
     // query found in terms
     term: 5,
-    partialTerm: 2
+    partialTerm: 2,
   };
 }
 
-if (!splitQuery) {
-  function splitQuery(query) {
-    return query.split(/\s+/);
+const _removeChildren = (element) => {
+  while (element && element.lastChild) element.removeChild(element.lastChild);
+};
+
+/**
+ * See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions#escaping
+ */
+const _escapeRegExp = (string) =>
+  string.replace(/[.*+\-?^${}()|[\]\\]/g, "\\$&"); // $& means the whole matched string
+
+const _displayItem = (item, searchTerms) => {
+  const docBuilder = DOCUMENTATION_OPTIONS.BUILDER;
+  const docUrlRoot = DOCUMENTATION_OPTIONS.URL_ROOT;
+  const docFileSuffix = DOCUMENTATION_OPTIONS.FILE_SUFFIX;
+  const docLinkSuffix = DOCUMENTATION_OPTIONS.LINK_SUFFIX;
+  const showSearchSummary = DOCUMENTATION_OPTIONS.SHOW_SEARCH_SUMMARY;
+
+  const [docName, title, anchor, descr, score, _filename] = item;
+
+  let listItem = document.createElement("li");
+  let requestUrl;
+  let linkUrl;
+  if (docBuilder === "dirhtml") {
+    // dirhtml builder
+    let dirname = docName + "/";
+    if (dirname.match(/\/index\/$/))
+      dirname = dirname.substring(0, dirname.length - 6);
+    else if (dirname === "index/") dirname = "";
+    requestUrl = docUrlRoot + dirname;
+    linkUrl = requestUrl;
+  } else {
+    // normal html builders
+    requestUrl = docUrlRoot + docName + docFileSuffix;
+    linkUrl = docName + docLinkSuffix;
   }
+  let linkEl = listItem.appendChild(document.createElement("a"));
+  linkEl.href = linkUrl + anchor;
+  linkEl.dataset.score = score;
+  linkEl.innerHTML = title;
+  if (descr)
+    listItem.appendChild(document.createElement("span")).innerHTML =
+      " (" + descr + ")";
+  else if (showSearchSummary)
+    fetch(requestUrl)
+      .then((responseData) => responseData.text())
+      .then((data) => {
+        if (data)
+          listItem.appendChild(
+            Search.makeSearchSummary(data, searchTerms)
+          );
+      });
+  Search.output.appendChild(listItem);
+};
+const _finishSearch = (resultCount) => {
+  Search.stopPulse();
+  Search.title.innerText = _("Search Results");
+  if (!resultCount)
+    Search.status.innerText = Documentation.gettext(
+      "Your search did not match any documents. Please make sure that all words are spelled correctly and that you've selected enough categories."
+    );
+  else
+    Search.status.innerText = _(
+      `Search finished, found ${resultCount} page(s) matching the search query.`
+    );
+};
+const _displayNextItem = (
+  results,
+  resultCount,
+  searchTerms
+) => {
+  // results left, load the summary and display it
+  // this is intended to be dynamic (don't sub resultsCount)
+  if (results.length) {
+    _displayItem(results.pop(), searchTerms);
+    setTimeout(
+      () => _displayNextItem(results, resultCount, searchTerms),
+      5
+    );
+  }
+  // search finished, update title and status message
+  else _finishSearch(resultCount);
+};
+
+/**
+ * Default splitQuery function. Can be overridden in ``sphinx.search`` with a
+ * custom function per language.
+ *
+ * The regular expression works by splitting the string on consecutive characters
+ * that are not Unicode letters, numbers, underscores, or emoji characters.
+ * This is the same as ``\W+`` in Python, preserving the surrogate pair area.
+ */
+if (typeof splitQuery === "undefined") {
+  var splitQuery = (query) => query
+      .split(/[^\p{Letter}\p{Number}_\p{Emoji_Presentation}]+/gu)
+      .filter(term => term)  // remove remaining empty strings
 }
 
 /**
  * Search Module
  */
-var Search = {
-
-  _index : null,
-  _queued_query : null,
-  _pulse_status : -1,
-
-  htmlToText : function(htmlString) {
-      var virtualDocument = document.implementation.createHTMLDocument('virtual');
-      var htmlElement = $(htmlString, virtualDocument);
-      htmlElement.find('.headerlink').remove();
-      docContent = htmlElement.find('[role=main]')[0];
-      if(docContent === undefined) {
-          console.warn("Content block not found. Sphinx search tries to obtain it " +
-                       "via '[role=main]'. Could you check your theme or template.");
-          return "";
-      }
-      return docContent.textContent || docContent.innerText;
+const Search = {
+  _index: null,
+  _queued_query: null,
+  _pulse_status: -1,
+
+  htmlToText: (htmlString) => {
+    const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
+    htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
+    const docContent = htmlElement.querySelector('[role="main"]');
+    if (docContent !== undefined) return docContent.textContent;
+    console.warn(
+      "Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
+    );
+    return "";
   },
 
-  init : function() {
-      var params = $.getQueryParameters();
-      if (params.q) {
-          var query = params.q[0];
-          $('input[name="q"]')[0].value = query;
-          this.performSearch(query);
-      }
+  init: () => {
+    const query = new URLSearchParams(window.location.search).get("q");
+    document
+      .querySelectorAll('input[name="q"]')
+      .forEach((el) => (el.value = query));
+    if (query) Search.performSearch(query);
   },
 
-  loadIndex : function(url) {
-    $.ajax({type: "GET", url: url, data: null,
-            dataType: "script", cache: true,
-            complete: function(jqxhr, textstatus) {
-              if (textstatus != "success") {
-                document.getElementById("searchindexloader").src = url;
-              }
-            }});
-  },
+  loadIndex: (url) =>
+    (document.body.appendChild(document.createElement("script")).src = url),
 
-  setIndex : function(index) {
-    var q;
-    this._index = index;
-    if ((q = this._queued_query) !== null) {
-      this._queued_query = null;
-      Search.query(q);
+  setIndex: (index) => {
+    Search._index = index;
+    if (Search._queued_query !== null) {
+      const query = Search._queued_query;
+      Search._queued_query = null;
+      Search.query(query);
     }
   },
 
-  hasIndex : function() {
-      return this._index !== null;
-  },
+  hasIndex: () => Search._index !== null,
 
-  deferQuery : function(query) {
-      this._queued_query = query;
-  },
+  deferQuery: (query) => (Search._queued_query = query),
 
-  stopPulse : function() {
-      this._pulse_status = 0;
-  },
+  stopPulse: () => (Search._pulse_status = -1),
 
-  startPulse : function() {
-    if (this._pulse_status >= 0)
-        return;
-    function pulse() {
-      var i;
+  startPulse: () => {
+    if (Search._pulse_status >= 0) return;
+
+    const pulse = () => {
       Search._pulse_status = (Search._pulse_status + 1) % 4;
-      var dotString = '';
-      for (i = 0; i < Search._pulse_status; i++)
-        dotString += '.';
-      Search.dots.text(dotString);
-      if (Search._pulse_status > -1)
-        window.setTimeout(pulse, 500);
-    }
+      Search.dots.innerText = ".".repeat(Search._pulse_status);
+      if (Search._pulse_status >= 0) window.setTimeout(pulse, 500);
+    };
     pulse();
   },
 
   /**
    * perform a search for something (or wait until index is loaded)
    */
-  performSearch : function(query) {
+  performSearch: (query) => {
     // create the required interface elements
-    this.out = $('#search-results');
-    this.title = $('<h2>' + _('Searching') + '</h2>').appendTo(this.out);
-    this.dots = $('<span></span>').appendTo(this.title);
-    this.status = $('<p class="search-summary">&nbsp;</p>').appendTo(this.out);
-    this.output = $('<ul class="search"/>').appendTo(this.out);
-
-    $('#search-progress').text(_('Preparing search...'));
-    this.startPulse();
+    const searchText = document.createElement("h2");
+    searchText.textContent = _("Searching");
+    const searchSummary = document.createElement("p");
+    searchSummary.classList.add("search-summary");
+    searchSummary.innerText = "";
+    const searchList = document.createElement("ul");
+    searchList.classList.add("search");
+
+    const out = document.getElementById("search-results");
+    Search.title = out.appendChild(searchText);
+    Search.dots = Search.title.appendChild(document.createElement("span"));
+    Search.status = out.appendChild(searchSummary);
+    Search.output = out.appendChild(searchList);
+
+    const searchProgress = document.getElementById("search-progress");
+    // Some themes don't use the search progress node
+    if (searchProgress) {
+      searchProgress.innerText = _("Preparing search...");
+    }
+    Search.startPulse();
 
     // index already loaded, the browser was quick!
-    if (this.hasIndex())
-      this.query(query);
-    else
-      this.deferQuery(query);
+    if (Search.hasIndex()) Search.query(query);
+    else Search.deferQuery(query);
   },
 
   /**
    * execute search (requires search index to be loaded)
    */
-  query : function(query) {
-    var i;
-
-    // stem the searchterms and add them to the correct list
-    var stemmer = new Stemmer();
-    var searchterms = [];
-    var excluded = [];
-    var hlterms = [];
-    var tmp = splitQuery(query);
-    var objectterms = [];
-    for (i = 0; i < tmp.length; i++) {
-      if (tmp[i] !== "") {
-          objectterms.push(tmp[i].toLowerCase());
-      }
+  query: (query) => {
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const titles = Search._index.titles;
+    const allTitles = Search._index.alltitles;
+    const indexEntries = Search._index.indexentries;
+
+    // stem the search terms and add them to the correct list
+    const stemmer = new Stemmer();
+    const searchTerms = new Set();
+    const excludedTerms = new Set();
+    const highlightTerms = new Set();
+    const objectTerms = new Set(splitQuery(query.toLowerCase().trim()));
+    splitQuery(query.trim()).forEach((queryTerm) => {
+      const queryTermLower = queryTerm.toLowerCase();
+
+      // maybe skip this "word"
+      // stopwords array is from language_data.js
+      if (
+        stopwords.indexOf(queryTermLower) !== -1 ||
+        queryTerm.match(/^\d+$/)
+      )
+        return;
 
-      if ($u.indexOf(stopwords, tmp[i].toLowerCase()) != -1 || tmp[i] === "") {
-        // skip this "word"
-        continue;
-      }
       // stem the word
-      var word = stemmer.stemWord(tmp[i].toLowerCase());
-      // prevent stemmer from cutting word smaller than two chars
-      if(word.length < 3 && tmp[i].length >= 3) {
-        word = tmp[i];
-      }
-      var toAppend;
+      let word = stemmer.stemWord(queryTermLower);
       // select the correct list
-      if (word[0] == '-') {
-        toAppend = excluded;
-        word = word.substr(1);
-      }
+      if (word[0] === "-") excludedTerms.add(word.substr(1));
       else {
-        toAppend = searchterms;
-        hlterms.push(tmp[i].toLowerCase());
+        searchTerms.add(word);
+        highlightTerms.add(queryTermLower);
       }
-      // only add if not already in the list
-      if (!$u.contains(toAppend, word))
-        toAppend.push(word);
-    }
-    var highlightstring = '?highlight=' + $.urlencode(hlterms.join(" "));
+    });
 
-    // console.debug('SEARCH: searching for:');
-    // console.info('required: ', searchterms);
-    // console.info('excluded: ', excluded);
+    if (SPHINX_HIGHLIGHT_ENABLED) {  // set in sphinx_highlight.js
+      localStorage.setItem("sphinx_highlight_terms", [...highlightTerms].join(" "))
+    }
 
-    // prepare search
-    var terms = this._index.terms;
-    var titleterms = this._index.titleterms;
+    // console.debug("SEARCH: searching for:");
+    // console.info("required: ", [...searchTerms]);
+    // console.info("excluded: ", [...excludedTerms]);
+
+    // array of [docname, title, anchor, descr, score, filename]
+    let results = [];
+    _removeChildren(document.getElementById("search-progress"));
+
+    const queryLower = query.toLowerCase();
+    for (const [title, foundTitles] of Object.entries(allTitles)) {
+      if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
+        for (const [file, id] of foundTitles) {
+          let score = Math.round(100 * queryLower.length / title.length)
+          results.push([
+            docNames[file],
+            titles[file] !== title ? `${titles[file]} > ${title}` : title,
+            id !== null ? "#" + id : "",
+            null,
+            score,
+            filenames[file],
+          ]);
+        }
+      }
+    }
 
-    // array of [filename, title, anchor, descr, score]
-    var results = [];
-    $('#search-progress').empty();
+    // search for explicit entries in index directives
+    for (const [entry, foundEntries] of Object.entries(indexEntries)) {
+      if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
+        for (const [file, id] of foundEntries) {
+          let score = Math.round(100 * queryLower.length / entry.length)
+          results.push([
+            docNames[file],
+            titles[file],
+            id ? "#" + id : "",
+            null,
+            score,
+            filenames[file],
+          ]);
+        }
+      }
+    }
 
     // lookup as object
-    for (i = 0; i < objectterms.length; i++) {
-      var others = [].concat(objectterms.slice(0, i),
-                             objectterms.slice(i+1, objectterms.length));
-      results = results.concat(this.performObjectSearch(objectterms[i], others));
-    }
+    objectTerms.forEach((term) =>
+      results.push(...Search.performObjectSearch(term, objectTerms))
+    );
 
     // lookup as search terms in fulltext
-    results = results.concat(this.performTermsSearch(searchterms, excluded, terms, titleterms));
+    results.push(...Search.performTermsSearch(searchTerms, excludedTerms));
 
     // let the scorer override scores with a custom scoring function
-    if (Scorer.score) {
-      for (i = 0; i < results.length; i++)
-        results[i][4] = Scorer.score(results[i]);
-    }
+    if (Scorer.score) results.forEach((item) => (item[4] = Scorer.score(item)));
 
     // now sort the results by score (in opposite order of appearance, since the
     // display function below uses pop() to retrieve items) and then
     // alphabetically
-    results.sort(function(a, b) {
-      var left = a[4];
-      var right = b[4];
-      if (left > right) {
-        return 1;
-      } else if (left < right) {
-        return -1;
-      } else {
+    results.sort((a, b) => {
+      const leftScore = a[4];
+      const rightScore = b[4];
+      if (leftScore === rightScore) {
         // same score: sort alphabetically
-        left = a[1].toLowerCase();
-        right = b[1].toLowerCase();
-        return (left > right) ? -1 : ((left < right) ? 1 : 0);
+        const leftTitle = a[1].toLowerCase();
+        const rightTitle = b[1].toLowerCase();
+        if (leftTitle === rightTitle) return 0;
+        return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
       }
+      return leftScore > rightScore ? 1 : -1;
     });
 
+    // remove duplicate search results
+    // note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
+    let seen = new Set();
+    results = results.reverse().reduce((acc, result) => {
+      let resultStr = result.slice(0, 4).concat([result[5]]).map(v => String(v)).join(',');
+      if (!seen.has(resultStr)) {
+        acc.push(result);
+        seen.add(resultStr);
+      }
+      return acc;
+    }, []);
+
+    results = results.reverse();
+
     // for debugging
     //Search.lastresults = results.slice();  // a copy
-    //console.info('search results:', Search.lastresults);
+    // console.info("search results:", Search.lastresults);
 
     // print the results
-    var resultCount = results.length;
-    function displayNextItem() {
-      // results left, load the summary and display it
-      if (results.length) {
-        var item = results.pop();
-        var listItem = $('<li></li>');
-        var requestUrl = "";
-        var linkUrl = "";
-        if (DOCUMENTATION_OPTIONS.BUILDER === 'dirhtml') {
-          // dirhtml builder
-          var dirname = item[0] + '/';
-          if (dirname.match(/\/index\/$/)) {
-            dirname = dirname.substring(0, dirname.length-6);
-          } else if (dirname == 'index/') {
-            dirname = '';
-          }
-          requestUrl = DOCUMENTATION_OPTIONS.URL_ROOT + dirname;
-          linkUrl = requestUrl;
-
-        } else {
-          // normal html builders
-          requestUrl = DOCUMENTATION_OPTIONS.URL_ROOT + item[0] + DOCUMENTATION_OPTIONS.FILE_SUFFIX;
-          linkUrl = item[0] + DOCUMENTATION_OPTIONS.LINK_SUFFIX;
-        }
-        listItem.append($('<a/>').attr('href',
-            linkUrl +
-            highlightstring + item[2]).html(item[1]));
-        if (item[3]) {
-          listItem.append($('<span> (' + item[3] + ')</span>'));
-          Search.output.append(listItem);
-          setTimeout(function() {
-            displayNextItem();
-          }, 5);
-        } else if (DOCUMENTATION_OPTIONS.HAS_SOURCE) {
-          $.ajax({url: requestUrl,
-                  dataType: "text",
-                  complete: function(jqxhr, textstatus) {
-                    var data = jqxhr.responseText;
-                    if (data !== '' && data !== undefined) {
-                      var summary = Search.makeSearchSummary(data, searchterms, hlterms);
-                      if (summary) {
-                        listItem.append(summary);
-                      }
-                    }
-                    Search.output.append(listItem);
-                    setTimeout(function() {
-                      displayNextItem();
-                    }, 5);
-                  }});
-        } else {
-          // no source available, just display title
-          Search.output.append(listItem);
-          setTimeout(function() {
-            displayNextItem();
-          }, 5);
-        }
-      }
-      // search finished, update title and status message
-      else {
-        Search.stopPulse();
-        Search.title.text(_('Search Results'));
-        if (!resultCount)
-          Search.status.text(_('Your search did not match any documents. Please make sure that all words are spelled correctly and that you\'ve selected enough categories.'));
-        else
-            Search.status.text(_('Search finished, found %s page(s) matching the search query.').replace('%s', resultCount));
-        Search.status.fadeIn(500);
-      }
-    }
-    displayNextItem();
+    _displayNextItem(results, results.length, searchTerms);
   },
 
   /**
    * search for object names
    */
-  performObjectSearch : function(object, otherterms) {
-    var filenames = this._index.filenames;
-    var docnames = this._index.docnames;
-    var objects = this._index.objects;
-    var objnames = this._index.objnames;
-    var titles = this._index.titles;
-
-    var i;
-    var results = [];
-
-    for (var prefix in objects) {
-      for (var iMatch = 0; iMatch != objects[prefix].length; ++iMatch) {
-        var match = objects[prefix][iMatch];
-        var name = match[4];
-        var fullname = (prefix ? prefix + '.' : '') + name;
-        var fullnameLower = fullname.toLowerCase()
-        if (fullnameLower.indexOf(object) > -1) {
-          var score = 0;
-          var parts = fullnameLower.split('.');
-          // check for different match types: exact matches of full name or
-          // "last name" (i.e. last dotted part)
-          if (fullnameLower == object || parts[parts.length - 1] == object) {
-            score += Scorer.objNameMatch;
-          // matches in last name
-          } else if (parts[parts.length - 1].indexOf(object) > -1) {
-            score += Scorer.objPartialMatch;
-          }
-          var objname = objnames[match[1]][2];
-          var title = titles[match[0]];
-          // If more than one term searched for, we require other words to be
-          // found in the name/title/description
-          if (otherterms.length > 0) {
-            var haystack = (prefix + ' ' + name + ' ' +
-                            objname + ' ' + title).toLowerCase();
-            var allfound = true;
-            for (i = 0; i < otherterms.length; i++) {
-              if (haystack.indexOf(otherterms[i]) == -1) {
-                allfound = false;
-                break;
-              }
-            }
-            if (!allfound) {
-              continue;
-            }
-          }
-          var descr = objname + _(', in ') + title;
-
-          var anchor = match[3];
-          if (anchor === '')
-            anchor = fullname;
-          else if (anchor == '-')
-            anchor = objnames[match[1]][1] + '-' + fullname;
-          // add custom score for some objects according to scorer
-          if (Scorer.objPrio.hasOwnProperty(match[2])) {
-            score += Scorer.objPrio[match[2]];
-          } else {
-            score += Scorer.objPrioDefault;
-          }
-          results.push([docnames[match[0]], fullname, '#'+anchor, descr, score, filenames[match[0]]]);
-        }
+  performObjectSearch: (object, objectTerms) => {
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const objects = Search._index.objects;
+    const objNames = Search._index.objnames;
+    const titles = Search._index.titles;
+
+    const results = [];
+
+    const objectSearchCallback = (prefix, match) => {
+      const name = match[4]
+      const fullname = (prefix ? prefix + "." : "") + name;
+      const fullnameLower = fullname.toLowerCase();
+      if (fullnameLower.indexOf(object) < 0) return;
+
+      let score = 0;
+      const parts = fullnameLower.split(".");
+
+      // check for different match types: exact matches of full name or
+      // "last name" (i.e. last dotted part)
+      if (fullnameLower === object || parts.slice(-1)[0] === object)
+        score += Scorer.objNameMatch;
+      else if (parts.slice(-1)[0].indexOf(object) > -1)
+        score += Scorer.objPartialMatch; // matches in last name
+
+      const objName = objNames[match[1]][2];
+      const title = titles[match[0]];
+
+      // If more than one term searched for, we require other words to be
+      // found in the name/title/description
+      const otherTerms = new Set(objectTerms);
+      otherTerms.delete(object);
+      if (otherTerms.size > 0) {
+        const haystack = `${prefix} ${name} ${objName} ${title}`.toLowerCase();
+        if (
+          [...otherTerms].some((otherTerm) => haystack.indexOf(otherTerm) < 0)
+        )
+          return;
       }
-    }
 
+      let anchor = match[3];
+      if (anchor === "") anchor = fullname;
+      else if (anchor === "-") anchor = objNames[match[1]][1] + "-" + fullname;
+
+      const descr = objName + _(", in ") + title;
+
+      // add custom score for some objects according to scorer
+      if (Scorer.objPrio.hasOwnProperty(match[2]))
+        score += Scorer.objPrio[match[2]];
+      else score += Scorer.objPrioDefault;
+
+      results.push([
+        docNames[match[0]],
+        fullname,
+        "#" + anchor,
+        descr,
+        score,
+        filenames[match[0]],
+      ]);
+    };
+    Object.keys(objects).forEach((prefix) =>
+      objects[prefix].forEach((array) =>
+        objectSearchCallback(prefix, array)
+      )
+    );
     return results;
   },
 
-  /**
-   * See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions
-   */
-  escapeRegExp : function(string) {
-    return string.replace(/[.*+\-?^${}()|[\]\\]/g, '\\$&'); // $& means the whole matched string
-  },
-
   /**
    * search for full-text terms in the index
    */
-  performTermsSearch : function(searchterms, excluded, terms, titleterms) {
-    var docnames = this._index.docnames;
-    var filenames = this._index.filenames;
-    var titles = this._index.titles;
+  performTermsSearch: (searchTerms, excludedTerms) => {
+    // prepare search
+    const terms = Search._index.terms;
+    const titleTerms = Search._index.titleterms;
+    const filenames = Search._index.filenames;
+    const docNames = Search._index.docnames;
+    const titles = Search._index.titles;
 
-    var i, j, file;
-    var fileMap = {};
-    var scoreMap = {};
-    var results = [];
+    const scoreMap = new Map();
+    const fileMap = new Map();
 
     // perform the search on the required terms
-    for (i = 0; i < searchterms.length; i++) {
-      var word = searchterms[i];
-      var files = [];
-      var _o = [
-        {files: terms[word], score: Scorer.term},
-        {files: titleterms[word], score: Scorer.title}
+    searchTerms.forEach((word) => {
+      const files = [];
+      const arr = [
+        { files: terms[word], score: Scorer.term },
+        { files: titleTerms[word], score: Scorer.title },
       ];
       // add support for partial matches
       if (word.length > 2) {
-        var word_regex = this.escapeRegExp(word);
-        for (var w in terms) {
-          if (w.match(word_regex) && !terms[word]) {
-            _o.push({files: terms[w], score: Scorer.partialTerm})
-          }
-        }
-        for (var w in titleterms) {
-          if (w.match(word_regex) && !titleterms[word]) {
-              _o.push({files: titleterms[w], score: Scorer.partialTitle})
-          }
-        }
+        const escapedWord = _escapeRegExp(word);
+        Object.keys(terms).forEach((term) => {
+          if (term.match(escapedWord) && !terms[word])
+            arr.push({ files: terms[term], score: Scorer.partialTerm });
+        });
+        Object.keys(titleTerms).forEach((term) => {
+          if (term.match(escapedWord) && !titleTerms[word])
+            arr.push({ files: titleTerms[word], score: Scorer.partialTitle });
+        });
       }
 
       // no match but word was a required one
-      if ($u.every(_o, function(o){return o.files === undefined;})) {
-        break;
-      }
+      if (arr.every((record) => record.files === undefined)) return;
+
       // found search word in contents
-      $u.each(_o, function(o) {
-        var _files = o.files;
-        if (_files === undefined)
-          return
-
-        if (_files.length === undefined)
-          _files = [_files];
-        files = files.concat(_files);
-
-        // set score for the word in each file to Scorer.term
-        for (j = 0; j < _files.length; j++) {
-          file = _files[j];
-          if (!(file in scoreMap))
-            scoreMap[file] = {};
-          scoreMap[file][word] = o.score;
-        }
+      arr.forEach((record) => {
+        if (record.files === undefined) return;
+
+        let recordFiles = record.files;
+        if (recordFiles.length === undefined) recordFiles = [recordFiles];
+        files.push(...recordFiles);
+
+        // set score for the word in each file
+        recordFiles.forEach((file) => {
+          if (!scoreMap.has(file)) scoreMap.set(file, {});
+          scoreMap.get(file)[word] = record.score;
+        });
       });
 
       // create the mapping
-      for (j = 0; j < files.length; j++) {
-        file = files[j];
-        if (file in fileMap && fileMap[file].indexOf(word) === -1)
-          fileMap[file].push(word);
-        else
-          fileMap[file] = [word];
-      }
-    }
+      files.forEach((file) => {
+        if (fileMap.has(file) && fileMap.get(file).indexOf(word) === -1)
+          fileMap.get(file).push(word);
+        else fileMap.set(file, [word]);
+      });
+    });
 
     // now check if the files don't contain excluded terms
-    for (file in fileMap) {
-      var valid = true;
-
+    const results = [];
+    for (const [file, wordList] of fileMap) {
       // check if all requirements are matched
-      var filteredTermCount = // as search terms with length < 3 are discarded: ignore
-        searchterms.filter(function(term){return term.length > 2}).length
+
+      // as search terms with length < 3 are discarded
+      const filteredTermCount = [...searchTerms].filter(
+        (term) => term.length > 2
+      ).length;
       if (
-        fileMap[file].length != searchterms.length &&
-        fileMap[file].length != filteredTermCount
-      ) continue;
+        wordList.length !== searchTerms.size &&
+        wordList.length !== filteredTermCount
+      )
+        continue;
 
       // ensure that none of the excluded terms is in the search result
-      for (i = 0; i < excluded.length; i++) {
-        if (terms[excluded[i]] == file ||
-            titleterms[excluded[i]] == file ||
-            $u.contains(terms[excluded[i]] || [], file) ||
-            $u.contains(titleterms[excluded[i]] || [], file)) {
-          valid = false;
-          break;
-        }
-      }
+      if (
+        [...excludedTerms].some(
+          (term) =>
+            terms[term] === file ||
+            titleTerms[term] === file ||
+            (terms[term] || []).includes(file) ||
+            (titleTerms[term] || []).includes(file)
+        )
+      )
+        break;
 
-      // if we have still a valid result we can add it to the result list
-      if (valid) {
-        // select one (max) score for the file.
-        // for better ranking, we should calculate ranking by using words statistics like basic tf-idf...
-        var score = $u.max($u.map(fileMap[file], function(w){return scoreMap[file][w]}));
-        results.push([docnames[file], titles[file], '', null, score, filenames[file]]);
-      }
+      // select one (max) score for the file.
+      const score = Math.max(...wordList.map((w) => scoreMap.get(file)[w]));
+      // add result to the result list
+      results.push([
+        docNames[file],
+        titles[file],
+        "",
+        null,
+        score,
+        filenames[file],
+      ]);
     }
     return results;
   },
@@ -496,34 +539,28 @@ var Search = {
   /**
    * helper function to return a node containing the
    * search summary for a given text. keywords is a list
-   * of stemmed words, hlwords is the list of normal, unstemmed
-   * words. the first one is used to find the occurrence, the
-   * latter for highlighting it.
+   * of stemmed words.
    */
-  makeSearchSummary : function(htmlText, keywords, hlwords) {
-    var text = Search.htmlToText(htmlText);
-    if (text == "") {
-      return null;
-    }
-    var textLower = text.toLowerCase();
-    var start = 0;
-    $.each(keywords, function() {
-      var i = textLower.indexOf(this.toLowerCase());
-      if (i > -1)
-        start = i;
-    });
-    start = Math.max(start - 120, 0);
-    var excerpt = ((start > 0) ? '...' : '') +
-      $.trim(text.substr(start, 240)) +
-      ((start + 240 - text.length) ? '...' : '');
-    var rv = $('<p class="context"></p>').text(excerpt);
-    $.each(hlwords, function() {
-      rv = rv.highlightText(this, 'highlighted');
-    });
-    return rv;
-  }
+  makeSearchSummary: (htmlText, keywords) => {
+    const text = Search.htmlToText(htmlText);
+    if (text === "") return null;
+
+    const textLower = text.toLowerCase();
+    const actualStartPosition = [...keywords]
+      .map((k) => textLower.indexOf(k.toLowerCase()))
+      .filter((i) => i > -1)
+      .slice(-1)[0];
+    const startWithContext = Math.max(actualStartPosition - 120, 0);
+
+    const top = startWithContext === 0 ? "" : "...";
+    const tail = startWithContext + 240 < text.length ? "..." : "";
+
+    let summary = document.createElement("p");
+    summary.classList.add("context");
+    summary.textContent = top + text.substr(startWithContext, 240).trim() + tail;
+
+    return summary;
+  },
 };
 
-$(document).ready(function() {
-  Search.init();
-});
+_ready(Search.init);
diff --git a/docs/dice_ml.data_interfaces.html b/docs/dice_ml.data_interfaces.html
index 8512a2ea..dac63237 100644
--- a/docs/dice_ml.data_interfaces.html
+++ b/docs/dice_ml.data_interfaces.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.data_interfaces package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.data_interfaces package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -134,25 +136,25 @@
 }
 </style>
 <section id="dice-ml-data-interfaces-package">
-<h1>dice_ml.data_interfaces package<a class="headerlink" href="#dice-ml-data-interfaces-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.data_interfaces package<a class="headerlink" href="#dice-ml-data-interfaces-package" title="Permalink to this heading"></a></h1>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.data_interfaces.base_data_interface">
-<span id="dice-ml-data-interfaces-base-data-interface-module"></span><h2>dice_ml.data_interfaces.base_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.base_data_interface" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-data-interfaces-base-data-interface-module"></span><h2>dice_ml.data_interfaces.base_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.base_data_interface" title="Permalink to this heading"></a></h2>
 <p>Module containing base class for data interfaces for dice-ml.</p>
 </section>
 <section id="module-dice_ml.data_interfaces.private_data_interface">
-<span id="dice-ml-data-interfaces-private-data-interface-module"></span><h2>dice_ml.data_interfaces.private_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.private_data_interface" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-data-interfaces-private-data-interface-module"></span><h2>dice_ml.data_interfaces.private_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.private_data_interface" title="Permalink to this heading"></a></h2>
 <p>Module containing meta data information about private data.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.data_interfaces.private_data_interface.</span></span><span class="sig-name descname"><span class="pre">PrivateData</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.data_interfaces.base_data_interface._BaseData</span></code></p>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">_BaseData</span></code></p>
 <p>A data interface for private data with meta information.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params">
-<span class="sig-name descname"><span class="pre">create_ohe_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.create_ohe_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">create_ohe_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">one_hot_encoded_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.create_ohe_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
@@ -161,6 +163,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>De-normalizes continuous features from [0,1] range to original range.</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders">
+<span class="sig-name descname"><span class="pre">fit_label_encoders</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.fit_label_encoders"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.from_dummies">
 <span class="sig-name descname"><span class="pre">from_dummies</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix_sep</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'_'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.from_dummies"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.from_dummies" title="Permalink to this definition"></a></dt>
@@ -173,6 +180,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>Transforms label encoded data back to categorical values</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames">
+<span class="sig-name descname"><span class="pre">get_all_dummy_colnames</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_all_dummy_colnames"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_data_params_for_gradient_dice">
 <span class="sig-name descname"><span class="pre">get_data_params_for_gradient_dice</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_data_params_for_gradient_dice"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_data_params_for_gradient_dice" title="Permalink to this definition"></a></dt>
@@ -181,7 +193,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions">
-<span class="sig-name descname"><span class="pre">get_decimal_precisions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_decimal_precisions"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">get_decimal_precisions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'list'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_decimal_precisions"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions" title="Permalink to this definition"></a></dt>
 <dd><p>“Gets the precision of continuous features in the data.</p>
 </dd></dl>
 
@@ -197,6 +209,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>Gets the column indexes categorical features after one-hot-encoding.</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range">
+<span class="sig-name descname"><span class="pre">get_features_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permitted_range_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_features_range"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_indexes_of_features_to_vary">
 <span class="sig-name descname"><span class="pre">get_indexes_of_features_to_vary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_indexes_of_features_to_vary"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_indexes_of_features_to_vary" title="Permalink to this definition"></a></dt>
@@ -229,6 +246,16 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 a dataframe, a list, or a list of dicts</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range">
+<span class="sig-name descname"><span class="pre">get_valid_feature_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_range_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_valid_feature_range"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range" title="Permalink to this definition"></a></dt>
+<dd><p>Gets the min/max value of features in normalized or de-normalized
+form. Assumes that all features are already encoded to numerical form
+such that the number of features remains the same.</p>
+<p># TODO needs work adhere to label encoded max and to support permitted_range for
+both continuous and discrete when provided in _generate_counterfactuals.</p>
+</dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_mads">
 <span class="sig-name descname"><span class="pre">get_valid_mads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">display_warnings</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_mads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.get_valid_mads"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_mads" title="Permalink to this definition"></a></dt>
@@ -237,7 +264,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data">
-<span class="sig-name descname"><span class="pre">normalize_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'one-hot'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.normalize_data"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">normalize_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/private_data_interface.html#PrivateData.normalize_data"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data" title="Permalink to this definition"></a></dt>
 <dd><p>Normalizes continuous features to make them fall in the range [0,1].</p>
 </dd></dl>
 
@@ -263,36 +290,19 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.data_interfaces.public_data_interface">
-<span id="dice-ml-data-interfaces-public-data-interface-module"></span><h2>dice_ml.data_interfaces.public_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.public_data_interface" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-data-interfaces-public-data-interface-module"></span><h2>dice_ml.data_interfaces.public_data_interface module<a class="headerlink" href="#module-dice_ml.data_interfaces.public_data_interface" title="Permalink to this heading"></a></h2>
 <p>Module containing all required information about the interface between raw (or transformed)
 public data and DiCE explainers.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.data_interfaces.public_data_interface.</span></span><span class="sig-name descname"><span class="pre">PublicData</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.data_interfaces.base_data_interface._BaseData</span></code></p>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">_BaseData</span></code></p>
 <p>A data interface for public data. This class is an interface to DiCE explainers
 and contains methods to transform user-fed raw data into the format a DiCE explainer
 requires, and vice versa.</p>
-<dl class="py method">
-<dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.check_features_to_vary">
-<span class="sig-name descname"><span class="pre">check_features_to_vary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.check_features_to_vary"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.check_features_to_vary" title="Permalink to this definition"></a></dt>
-<dd></dd></dl>
-
-<dl class="py method">
-<dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.check_mad_validity">
-<span class="sig-name descname"><span class="pre">check_mad_validity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.check_mad_validity"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.check_mad_validity" title="Permalink to this definition"></a></dt>
-<dd><p>checks feature MAD validity and throw warnings.
-TODO: add comments as to where this is used if this function is necessary, else remove.</p>
-</dd></dl>
-
-<dl class="py method">
-<dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.check_permitted_range">
-<span class="sig-name descname"><span class="pre">check_permitted_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.check_permitted_range"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.check_permitted_range" title="Permalink to this definition"></a></dt>
-<dd></dd></dl>
-
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params">
-<span class="sig-name descname"><span class="pre">create_ohe_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.create_ohe_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">create_ohe_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">one_hot_encoded_data</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.create_ohe_params"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
@@ -301,6 +311,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>De-normalizes continuous features from [0,1] range to original range.</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders">
+<span class="sig-name descname"><span class="pre">fit_label_encoders</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.fit_label_encoders"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.from_dummies">
 <span class="sig-name descname"><span class="pre">from_dummies</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix_sep</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'_'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.from_dummies"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.from_dummies" title="Permalink to this definition"></a></dt>
@@ -313,6 +328,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>Transforms label encoded data back to categorical values</p>
 </dd></dl>
 
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames">
+<span class="sig-name descname"><span class="pre">get_all_dummy_colnames</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.get_all_dummy_colnames"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.get_data_params_for_gradient_dice">
 <span class="sig-name descname"><span class="pre">get_data_params_for_gradient_dice</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.get_data_params_for_gradient_dice"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.get_data_params_for_gradient_dice" title="Permalink to this definition"></a></dt>
@@ -345,7 +365,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range">
-<span class="sig-name descname"><span class="pre">get_features_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permitted_range_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.get_features_range"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">get_features_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permitted_range_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data_interfaces/public_data_interface.html#PublicData.get_features_range"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
@@ -430,7 +450,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.data_interfaces">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.data_interfaces" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.data_interfaces" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/dice_ml.explainer_interfaces.html b/docs/dice_ml.explainer_interfaces.html
index 7dfb634e..1191329b 100644
--- a/docs/dice_ml.explainer_interfaces.html
+++ b/docs/dice_ml.explainer_interfaces.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.explainer_interfaces package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.explainer_interfaces package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -140,18 +142,18 @@
 }
 </style>
 <section id="dice-ml-explainer-interfaces-package">
-<h1>dice_ml.explainer_interfaces package<a class="headerlink" href="#dice-ml-explainer-interfaces-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.explainer_interfaces package<a class="headerlink" href="#dice-ml-explainer-interfaces-package" title="Permalink to this heading"></a></h1>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_KD">
-<span id="dice-ml-explainer-interfaces-dice-kd-module"></span><h2>dice_ml.explainer_interfaces.dice_KD module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_KD" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-kd-module"></span><h2>dice_ml.explainer_interfaces.dice_KD module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_KD" title="Permalink to this heading"></a></h2>
 <p>Module to generate counterfactual explanations from a KD-Tree
 This code is similar to ‘Interpretable Counterfactual Explanations Guided by Prototypes’: <a class="reference external" href="https://arxiv.org/pdf/1907.02584.pdf">https://arxiv.org/pdf/1907.02584.pdf</a></p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_KD.DiceKD">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_KD.</span></span><span class="sig-name descname"><span class="pre">DiceKD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_KD.html#DiceKD"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_KD.DiceKD" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_KD.DiceKD.do_sparsity_check">
 <span class="sig-name descname"><span class="pre">do_sparsity_check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cfs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparsity_weight</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_KD.html#DiceKD.do_sparsity_check"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_KD.DiceKD.do_sparsity_check" title="Permalink to this definition"></a></dt>
@@ -164,7 +166,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals">
-<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_df_copy</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance_orig</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparsity_weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_KD.html#DiceKD.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_df_copy</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance_orig</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparsity_weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_KD.html#DiceKD.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Finds counterfactuals by querying a K-D tree for the nearest data points in the desired class from the dataset.</p>
 </dd></dl>
 
@@ -184,13 +186,13 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_genetic">
-<span id="dice-ml-explainer-interfaces-dice-genetic-module"></span><h2>dice_ml.explainer_interfaces.dice_genetic module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_genetic" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-genetic-module"></span><h2>dice_ml.explainer_interfaces.dice_genetic module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_genetic" title="Permalink to this heading"></a></h2>
 <p>Module to generate diverse counterfactual explanations based on genetic algorithm
 This code is similar to ‘GeCo: Quality Counterfactual Explanations in Real Time’: <a class="reference external" href="https://arxiv.org/pdf/2101.01292.pdf">https://arxiv.org/pdf/2101.01292.pdf</a></p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_genetic.DiceGenetic">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_genetic.</span></span><span class="sig-name descname"><span class="pre">DiceGenetic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_genetic.html#DiceGenetic"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_loss">
 <span class="sig-name descname"><span class="pre">compute_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cfs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_genetic.html#DiceGenetic.compute_loss"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_loss" title="Permalink to this definition"></a></dt>
@@ -297,12 +299,12 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_pytorch">
-<span id="dice-ml-explainer-interfaces-dice-pytorch-module"></span><h2>dice_ml.explainer_interfaces.dice_pytorch module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_pytorch" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-pytorch-module"></span><h2>dice_ml.explainer_interfaces.dice_pytorch module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_pytorch" title="Permalink to this heading"></a></h2>
 <p>Module to generate diverse counterfactual explanations based on PyTorch framework</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_pytorch.</span></span><span class="sig-name descname"><span class="pre">DicePyTorch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_dist">
 <span class="sig-name descname"><span class="pre">compute_dist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x_hat</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x1</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.compute_dist"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_dist" title="Permalink to this definition"></a></dt>
@@ -366,66 +368,13 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals">
-<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Finds counterfactuals by gradient-descent.</p>
 </dd></dl>
 
-<dl class="py method">
-<dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.generate_counterfactuals">
-<span class="sig-name descname"><span class="pre">generate_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proximity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">categorical_penalty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'DiverseCF'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">yloss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'hinge_loss'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_loss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dpp_style:inverse_dist'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'inverse_mad'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pytorch:adam'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.generate_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.generate_counterfactuals" title="Permalink to this definition"></a></dt>
-<dd><p>Generates diverse counterfactual explanations.</p>
-<dl class="field-list simple">
-<dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><ul class="simple">
-<li><p><strong>query_instance</strong> – Test point of interest. A dictionary of feature names and values or a single row dataframe</p></li>
-<li><p><strong>total_CFs</strong> – Total number of counterfactuals required.</p></li>
-<li><p><strong>desired_class</strong> – Desired counterfactual class - can take 0 or 1. Default value is “opposite” to the outcome class
-of query_instance for binary classification.</p></li>
-<li><p><strong>proximity_weight</strong> – A positive float. Larger this weight, more close the counterfactuals are to the
-query_instance.</p></li>
-<li><p><strong>diversity_weight</strong> – A positive float. Larger this weight, more diverse the counterfactuals are.</p></li>
-<li><p><strong>categorical_penalty</strong> – A positive float. A weight to ensure that all levels of a categorical variable sums to 1.</p></li>
-<li><p><strong>algorithm</strong> – Counterfactual generation algorithm. Either “DiverseCF” or “RandomInitCF”.</p></li>
-<li><p><strong>features_to_vary</strong> – Either a string “all” or a list of feature names to vary.</p></li>
-<li><p><strong>permitted_range</strong> – Dictionary with continuous feature names as keys and permitted min-max range in list as values.
-Defaults to the range inferred from training data. If None, uses the parameters initialized in
-data_interface.</p></li>
-<li><p><strong>yloss_type</strong> – Metric for y-loss of the optimization function. Takes “l2_loss” or “log_loss” or “hinge_loss”.</p></li>
-<li><p><strong>diversity_loss_type</strong> – Metric for diversity loss of the optimization function.
-Takes “avg_dist” or “dpp_style:inverse_dist”.</p></li>
-<li><p><strong>feature_weights</strong> – Either “inverse_mad” or a dictionary with feature names as keys and corresponding weights as
-values. Default option is “inverse_mad” where the weight for a continuous feature is the
-inverse of the Median Absolute Devidation (MAD) of the feature’s values in the training set;
-the weight for a categorical feature is equal to 1 by default.</p></li>
-<li><p><strong>optimizer</strong> – PyTorch optimization algorithm. Currently tested only with “pytorch:adam”.</p></li>
-<li><p><strong>learning_rate</strong> – Learning rate for optimizer.</p></li>
-<li><p><strong>min_iter</strong> – Min iterations to run gradient descent for.</p></li>
-<li><p><strong>max_iter</strong> – Max iterations to run gradient descent for.</p></li>
-<li><p><strong>project_iter</strong> – Project the gradients at an interval of these many iterations.</p></li>
-<li><p><strong>loss_diff_thres</strong> – Minimum difference between successive loss values to check convergence.</p></li>
-<li><p><strong>loss_converge_maxiter</strong> – Maximum number of iterations for loss_diff_thres to hold to declare convergence.
-Defaults to 1, but we assigned a more conservative value of 2 in the paper.</p></li>
-<li><p><strong>verbose</strong> – Print intermediate loss value.</p></li>
-<li><p><strong>init_near_query_instance</strong> – Boolean to indicate if counterfactuals are to be initialized near query_instance.</p></li>
-<li><p><strong>tie_random</strong> – Used in rounding off CFs and intermediate projection.</p></li>
-<li><p><strong>stopping_threshold</strong> – Minimum threshold for counterfactuals target class probability.</p></li>
-<li><p><strong>posthoc_sparsity_param</strong> – Parameter for the post-hoc operation on continuous features to enhance sparsity.</p></li>
-<li><p><strong>posthoc_sparsity_algorithm</strong> – Perform either linear or binary search. Takes “linear” or “binary”.
-Prefer binary search when a feature range is large
-(for instance, income varying from 10k to 1000k) and only if the features
-share a monotonic relationship with predicted outcome in the model.</p></li>
-</ul>
-</dd>
-<dt class="field-even">Returns</dt>
-<dd class="field-even"><p>A CounterfactualExamples object to store and visualize the resulting
-counterfactual explanations (see diverse_counterfactuals.py).</p>
-</dd>
-</dl>
-</dd></dl>
-
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output">
-<span class="sig-name descname"><span class="pre">get_model_output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_instance</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.get_model_output"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">get_model_output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transform_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_pytorch.html#DicePyTorch.get_model_output"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output" title="Permalink to this definition"></a></dt>
 <dd><p>get output probability of ML model</p>
 </dd></dl>
 
@@ -469,13 +418,13 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_random">
-<span id="dice-ml-explainer-interfaces-dice-random-module"></span><h2>dice_ml.explainer_interfaces.dice_random module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_random" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-random-module"></span><h2>dice_ml.explainer_interfaces.dice_random module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_random" title="Permalink to this heading"></a></h2>
 <p>Module to generate diverse counterfactual explanations based on random sampling.
 A simple implementation.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_random.DiceRandom">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_random.</span></span><span class="sig-name descname"><span class="pre">DiceRandom</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_random.html#DiceRandom"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_random.DiceRandom" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_random.DiceRandom.get_continuous_samples">
 <span class="sig-name descname"><span class="pre">get_continuous_samples</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">low</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">high</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">precision</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_random.html#DiceRandom.get_continuous_samples"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_random.DiceRandom.get_continuous_samples" title="Permalink to this definition"></a></dt>
@@ -490,12 +439,12 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_tensorflow1">
-<span id="dice-ml-explainer-interfaces-dice-tensorflow1-module"></span><h2>dice_ml.explainer_interfaces.dice_tensorflow1 module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_tensorflow1" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-tensorflow1-module"></span><h2>dice_ml.explainer_interfaces.dice_tensorflow1 module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_tensorflow1" title="Permalink to this heading"></a></h2>
 <p>Module to generate diverse counterfactual explanations based on tensorflow 1.x</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_tensorflow1.</span></span><span class="sig-name descname"><span class="pre">DiceTensorFlow1</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_dist">
 <span class="sig-name descname"><span class="pre">compute_dist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x_hat</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x1</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1.compute_dist"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_dist" title="Permalink to this definition"></a></dt>
@@ -553,13 +502,13 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals">
-<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Finds counterfactuals by gradient-descent.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals">
-<span class="sig-name descname"><span class="pre">generate_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proximity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">categorical_penalty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'DiverseCF'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">yloss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'hinge_loss'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_loss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dpp_style:inverse_dist'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'inverse_mad'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow:adam'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1.generate_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">generate_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proximity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">categorical_penalty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'DiverseCF'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">yloss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'hinge_loss'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_loss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dpp_style:inverse_dist'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'inverse_mad'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow:adam'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow1.html#DiceTensorFlow1.generate_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Generates diverse counterfactual explanations</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -602,6 +551,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 Prefer binary search when a feature range is large
 (for instance, income varying from 10k to 1000k) and only if the features
 share a monotonic relationship with predicted outcome in the model.</p></li>
+<li><p><strong>limit_steps_ls</strong> – Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</p></li>
 </ul>
 </dd>
 <dt class="field-even">Returns</dt>
@@ -662,12 +612,12 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.dice_tensorflow2">
-<span id="dice-ml-explainer-interfaces-dice-tensorflow2-module"></span><h2>dice_ml.explainer_interfaces.dice_tensorflow2 module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_tensorflow2" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-dice-tensorflow2-module"></span><h2>dice_ml.explainer_interfaces.dice_tensorflow2 module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.dice_tensorflow2" title="Permalink to this heading"></a></h2>
 <p>Module to generate diverse counterfactual explanations based on tensorflow 2.x</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.dice_tensorflow2.</span></span><span class="sig-name descname"><span class="pre">DiceTensorFlow2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_dist">
 <span class="sig-name descname"><span class="pre">compute_dist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x_hat</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x1</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2.compute_dist"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_dist" title="Permalink to this definition"></a></dt>
@@ -731,13 +681,13 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals">
-<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">find_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2.find_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Finds counterfactuals by gradient-descent.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals">
-<span class="sig-name descname"><span class="pre">generate_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proximity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">categorical_penalty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'DiverseCF'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">yloss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'hinge_loss'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_loss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dpp_style:inverse_dist'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'inverse_mad'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow:adam'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2.generate_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">generate_counterfactuals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_CFs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proximity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">categorical_penalty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'DiverseCF'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">features_to_vary</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">permitted_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">yloss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'hinge_loss'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">diversity_loss_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dpp_style:inverse_dist'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'inverse_mad'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow:adam'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">learning_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">500</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">project_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_diff_thres</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_converge_maxiter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_near_query_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stopping_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'linear'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/dice_tensorflow2.html#DiceTensorFlow2.generate_counterfactuals"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals" title="Permalink to this definition"></a></dt>
 <dd><p>Generates diverse counterfactual explanations</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -780,6 +730,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 Prefer binary search when a feature range is large
 (for instance, income varying from 10k to 1000k) and only if the features
 share a monotonic relationship with predicted outcome in the model.</p></li>
+<li><p><strong>limit_steps_ls</strong> – Defines an upper limit for the linear search step in the posthoc_sparsity_enhancement</p></li>
 </ul>
 </dd>
 <dt class="field-even">Returns</dt>
@@ -829,14 +780,14 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.explainer_base">
-<span id="dice-ml-explainer-interfaces-explainer-base-module"></span><h2>dice_ml.explainer_interfaces.explainer_base module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.explainer_base" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-explainer-base-module"></span><h2>dice_ml.explainer_interfaces.explainer_base module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.explainer_base" title="Permalink to this heading"></a></h2>
 <p>Module containing a template class to generate counterfactual explanations.
 Subclasses implement interfaces for different ML frameworks such as TensorFlow or PyTorch.
 All methods are in dice_ml.explainer_interfaces</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.explainer_base.ExplainerBase">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.explainer_base.</span></span><span class="sig-name descname"><span class="pre">ExplainerBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">abc.ABC</span></code></p>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">ABC</span></code></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.explainer_base.ExplainerBase.build_KD_tree">
 <span class="sig-name descname"><span class="pre">build_KD_tree</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_df_copy</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_range</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">predicted_outcome_name</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase.build_KD_tree"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.build_KD_tree" title="Permalink to this definition"></a></dt>
@@ -874,14 +825,14 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search">
-<span class="sig-name descname"><span class="pre">do_linear_search</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">diff</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decimal_prec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cf_ix</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_cfs_sparse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">current_pred_orig</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase.do_linear_search"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">do_linear_search</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">diff</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decimal_prec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cf_ix</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_cfs_sparse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">current_pred_orig</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase.do_linear_search"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search" title="Permalink to this definition"></a></dt>
 <dd><p>Performs a greedy linear search - moves the continuous features in CFs towards original values in
-query_instance greedily until the prediction class changes.</p>
+query_instance greedily until the prediction class changes, or it reaches the maximum number of steps</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement">
-<span class="sig-name descname"><span class="pre">do_posthoc_sparsity_enhancement</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">final_cfs_sparse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase.do_posthoc_sparsity_enhancement"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">do_posthoc_sparsity_enhancement</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">final_cfs_sparse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_algorithm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_steps_ls</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/explainer_base.html#ExplainerBase.do_posthoc_sparsity_enhancement"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement" title="Permalink to this definition"></a></dt>
 <dd><p>Post-hoc method to encourage sparsity in a generated counterfactuals.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -894,6 +845,8 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 large (for instance, income varying from 10k to 1000k)
 and only if the features share a monotonic relationship
 with predicted outcome in the model.</p></li>
+<li><p><strong>limit_steps_ls</strong> – Defines the limit of steps to be done in the linear search,
+necessary to avoid infinite loops</p></li>
 </ul>
 </dd>
 </dl>
@@ -1092,11 +1045,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.feasible_base_vae">
-<span id="dice-ml-explainer-interfaces-feasible-base-vae-module"></span><h2>dice_ml.explainer_interfaces.feasible_base_vae module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.feasible_base_vae" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-feasible-base-vae-module"></span><h2>dice_ml.explainer_interfaces.feasible_base_vae module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.feasible_base_vae" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.feasible_base_vae.</span></span><span class="sig-name descname"><span class="pre">FeasibleBaseVAE</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/feasible_base_vae.html#FeasibleBaseVAE"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.compute_loss">
 <span class="sig-name descname"><span class="pre">compute_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model_out</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_label</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/feasible_base_vae.html#FeasibleBaseVAE.compute_loss"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.compute_loss" title="Permalink to this definition"></a></dt>
@@ -1159,11 +1112,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces.feasible_model_approx">
-<span id="dice-ml-explainer-interfaces-feasible-model-approx-module"></span><h2>dice_ml.explainer_interfaces.feasible_model_approx module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.feasible_model_approx" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-explainer-interfaces-feasible-model-approx-module"></span><h2>dice_ml.explainer_interfaces.feasible_model_approx module<a class="headerlink" href="#module-dice_ml.explainer_interfaces.feasible_model_approx" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.explainer_interfaces.feasible_model_approx.</span></span><span class="sig-name descname"><span class="pre">FeasibleModelApprox</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/feasible_model_approx.html#FeasibleModelApprox"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE" title="dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE</span></code></a>, <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE" title="dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE"><code class="xref py py-class docutils literal notranslate"><span class="pre">FeasibleBaseVAE</span></code></a>, <a class="reference internal" href="#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox.train">
 <span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constraint_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_variables</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_direction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_reg</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pre_trained</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/explainer_interfaces/feasible_model_approx.html#FeasibleModelApprox.train"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox.train" title="Permalink to this definition"></a></dt>
@@ -1185,7 +1138,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.explainer_interfaces">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.explainer_interfaces" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.explainer_interfaces" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/dice_ml.html b/docs/dice_ml.html
index 19d8e332..b07f00cf 100644
--- a/docs/dice_ml.html
+++ b/docs/dice_ml.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -66,13 +68,96 @@
 </ul>
 </li>
 <li class="toctree-l2"><a class="reference internal" href="#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.constants">dice_ml.constants module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.counterfactual_explanations">dice_ml.counterfactual_explanations module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.data">dice_ml.data module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.dice">dice_ml.dice module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.diverse_counterfactuals">dice_ml.diverse_counterfactuals module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.model">dice_ml.model module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml">Module contents</a></li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.constants">dice_ml.constants module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.constants.BackEndTypes"><code class="docutils literal notranslate"><span class="pre">BackEndTypes</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.BackEndTypes.ALL"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.ALL</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.BackEndTypes.Pytorch"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Pytorch</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.BackEndTypes.Sklearn"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Sklearn</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.BackEndTypes.Tensorflow1"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Tensorflow1</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.BackEndTypes.Tensorflow2"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Tensorflow2</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.constants.ModelTypes"><code class="docutils literal notranslate"><span class="pre">ModelTypes</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.ModelTypes.ALL"><code class="docutils literal notranslate"><span class="pre">ModelTypes.ALL</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.ModelTypes.Classifier"><code class="docutils literal notranslate"><span class="pre">ModelTypes.Classifier</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.ModelTypes.Regressor"><code class="docutils literal notranslate"><span class="pre">ModelTypes.Regressor</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.constants.SamplingStrategy"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.SamplingStrategy.Genetic"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Genetic</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.SamplingStrategy.Gradient"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Gradient</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.SamplingStrategy.KdTree"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.KdTree</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.constants.SamplingStrategy.Random"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Random</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.counterfactual_explanations">dice_ml.counterfactual_explanations module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.cf_examples_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.cf_examples_list</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.from_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.from_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.local_importance"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.local_importance</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.metadata"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.metadata</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.summary_importance"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.summary_importance</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.to_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.to_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_dataframe"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.visualize_as_dataframe()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.visualize_as_list()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.data">dice_ml.data module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.data.Data"><code class="docutils literal notranslate"><span class="pre">Data</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.data.Data.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Data.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.data.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.dice">dice_ml.dice module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.dice.Dice"><code class="docutils literal notranslate"><span class="pre">Dice</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.dice.Dice.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Dice.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.dice.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.diverse_counterfactuals">dice_ml.diverse_counterfactuals module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.display_df"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.display_df()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.from_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.from_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.print_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.print_list()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.to_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.to_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_dataframe"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.visualize_as_dataframe()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.visualize_as_list()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.diverse_counterfactuals.json_converter"><code class="docutils literal notranslate"><span class="pre">json_converter()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml.model">dice_ml.model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.model.Model"><code class="docutils literal notranslate"><span class="pre">Model</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.model.Model.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Model.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.model.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#module-dice_ml">Module contents</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.Data"><code class="docutils literal notranslate"><span class="pre">Data</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.Data.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Data.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.Dice"><code class="docutils literal notranslate"><span class="pre">Dice</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.Dice.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Dice.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="#dice_ml.Model"><code class="docutils literal notranslate"><span class="pre">Model</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="#dice_ml.Model.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Model.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -126,38 +211,275 @@
 }
 </style>
 <section id="dice-ml-package">
-<h1>dice_ml package<a class="headerlink" href="#dice-ml-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml package<a class="headerlink" href="#dice-ml-package" title="Permalink to this heading"></a></h1>
 <section id="subpackages">
-<h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to this headline"></a></h2>
+<h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to this heading"></a></h2>
 <div class="toctree-wrapper compound">
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="dice_ml.data_interfaces.html">dice_ml.data_interfaces package</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#submodules">Submodules</a></li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces.base_data_interface">dice_ml.data_interfaces.base_data_interface module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces.private_data_interface">dice_ml.data_interfaces.private_data_interface module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces.public_data_interface">dice_ml.data_interfaces.public_data_interface module</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces.private_data_interface">dice_ml.data_interfaces.private_data_interface module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData"><code class="docutils literal notranslate"><span class="pre">PrivateData</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params"><code class="docutils literal notranslate"><span class="pre">PrivateData.create_ohe_params()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.de_normalize_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.de_normalize_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders"><code class="docutils literal notranslate"><span class="pre">PrivateData.fit_label_encoders()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.from_dummies"><code class="docutils literal notranslate"><span class="pre">PrivateData.from_dummies()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.from_label"><code class="docutils literal notranslate"><span class="pre">PrivateData.from_label()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_all_dummy_colnames()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_data_params_for_gradient_dice"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_data_params_for_gradient_dice()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_decimal_precisions()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_decoded_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_decoded_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_encoded_categorical_feature_indexes"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_encoded_categorical_feature_indexes()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_features_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_indexes_of_features_to_vary"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_indexes_of_features_to_vary()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_inverse_ohe_min_max_normalized_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_inverse_ohe_min_max_normalized_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_mads"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_mads()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_minx_maxx"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_minx_maxx()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_ohe_min_max_normalized_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_ohe_min_max_normalized_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_valid_feature_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_mads"><code class="docutils literal notranslate"><span class="pre">PrivateData.get_valid_mads()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.normalize_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.one_hot_encode_data"><code class="docutils literal notranslate"><span class="pre">PrivateData.one_hot_encode_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.prepare_df_for_ohe_encoding"><code class="docutils literal notranslate"><span class="pre">PrivateData.prepare_df_for_ohe_encoding()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.prepare_query_instance"><code class="docutils literal notranslate"><span class="pre">PrivateData.prepare_query_instance()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces.public_data_interface">dice_ml.data_interfaces.public_data_interface module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData"><code class="docutils literal notranslate"><span class="pre">PublicData</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params"><code class="docutils literal notranslate"><span class="pre">PublicData.create_ohe_params()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.de_normalize_data"><code class="docutils literal notranslate"><span class="pre">PublicData.de_normalize_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders"><code class="docutils literal notranslate"><span class="pre">PublicData.fit_label_encoders()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.from_dummies"><code class="docutils literal notranslate"><span class="pre">PublicData.from_dummies()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.from_label"><code class="docutils literal notranslate"><span class="pre">PublicData.from_label()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames"><code class="docutils literal notranslate"><span class="pre">PublicData.get_all_dummy_colnames()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_data_params_for_gradient_dice"><code class="docutils literal notranslate"><span class="pre">PublicData.get_data_params_for_gradient_dice()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_data_type"><code class="docutils literal notranslate"><span class="pre">PublicData.get_data_type()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_decimal_precisions"><code class="docutils literal notranslate"><span class="pre">PublicData.get_decimal_precisions()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_decoded_data"><code class="docutils literal notranslate"><span class="pre">PublicData.get_decoded_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_encoded_categorical_feature_indexes"><code class="docutils literal notranslate"><span class="pre">PublicData.get_encoded_categorical_feature_indexes()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range"><code class="docutils literal notranslate"><span class="pre">PublicData.get_features_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_indexes_of_features_to_vary"><code class="docutils literal notranslate"><span class="pre">PublicData.get_indexes_of_features_to_vary()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_inverse_ohe_min_max_normalized_data"><code class="docutils literal notranslate"><span class="pre">PublicData.get_inverse_ohe_min_max_normalized_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_mads"><code class="docutils literal notranslate"><span class="pre">PublicData.get_mads()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_minx_maxx"><code class="docutils literal notranslate"><span class="pre">PublicData.get_minx_maxx()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_ohe_min_max_normalized_data"><code class="docutils literal notranslate"><span class="pre">PublicData.get_ohe_min_max_normalized_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_quantiles_from_training_data"><code class="docutils literal notranslate"><span class="pre">PublicData.get_quantiles_from_training_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_feature_range"><code class="docutils literal notranslate"><span class="pre">PublicData.get_valid_feature_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_mads"><code class="docutils literal notranslate"><span class="pre">PublicData.get_valid_mads()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.normalize_data"><code class="docutils literal notranslate"><span class="pre">PublicData.normalize_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.one_hot_encode_data"><code class="docutils literal notranslate"><span class="pre">PublicData.one_hot_encode_data()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.prepare_df_for_ohe_encoding"><code class="docutils literal notranslate"><span class="pre">PublicData.prepare_df_for_ohe_encoding()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.prepare_query_instance"><code class="docutils literal notranslate"><span class="pre">PublicData.prepare_query_instance()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.data_interfaces.html#module-dice_ml.data_interfaces">Module contents</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="dice_ml.explainer_interfaces.html">dice_ml.explainer_interfaces package</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_KD">dice_ml.explainer_interfaces.dice_KD module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_genetic">dice_ml.explainer_interfaces.dice_genetic module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_pytorch">dice_ml.explainer_interfaces.dice_pytorch module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_random">dice_ml.explainer_interfaces.dice_random module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_tensorflow1">dice_ml.explainer_interfaces.dice_tensorflow1 module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_tensorflow2">dice_ml.explainer_interfaces.dice_tensorflow2 module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.explainer_base">dice_ml.explainer_interfaces.explainer_base module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.feasible_base_vae">dice_ml.explainer_interfaces.feasible_base_vae module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.feasible_model_approx">dice_ml.explainer_interfaces.feasible_model_approx module</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_KD">dice_ml.explainer_interfaces.dice_KD module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD"><code class="docutils literal notranslate"><span class="pre">DiceKD</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.do_sparsity_check"><code class="docutils literal notranslate"><span class="pre">DiceKD.do_sparsity_check()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.duplicates"><code class="docutils literal notranslate"><span class="pre">DiceKD.duplicates()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceKD.find_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.predict_fn"><code class="docutils literal notranslate"><span class="pre">DiceKD.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_KD.DiceKD.vary_valid"><code class="docutils literal notranslate"><span class="pre">DiceKD.vary_valid()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_genetic">dice_ml.explainer_interfaces.dice_genetic module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic"><code class="docutils literal notranslate"><span class="pre">DiceGenetic</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_loss"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.compute_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_proximity_loss"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.compute_proximity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_sparsity_loss"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.compute_sparsity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_yloss"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.compute_yloss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_KD_init"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.do_KD_init()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_cf_initializations"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.do_cf_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_loss_initializations"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.do_loss_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_param_initializations"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.do_param_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_random_init"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.do_random_init()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.find_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.find_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.get_valid_feature_range"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.get_valid_feature_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_decode"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.label_decode()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_decode_cfs"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.label_decode_cfs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_encode"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.label_encode()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.mate"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.mate()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn_scores"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.predict_fn_scores()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.update_hyperparameters"><code class="docutils literal notranslate"><span class="pre">DiceGenetic.update_hyperparameters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_pytorch">dice_ml.explainer_interfaces.dice_pytorch module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch"><code class="docutils literal notranslate"><span class="pre">DicePyTorch</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_dist"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_dist()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_diversity_loss"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_diversity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_loss"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_proximity_loss"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_proximity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_regularization_loss"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_regularization_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_yloss"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.compute_yloss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_cf_initializations"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.do_cf_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_loss_initializations"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.do_loss_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_optimizer_initializations"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.do_optimizer_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.dpp_style"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.dpp_style()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.find_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.get_model_output()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.initialize_CFs"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.initialize_CFs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn_for_sparsity"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.predict_fn_for_sparsity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.round_off_cfs"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.round_off_cfs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.stop_loop"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.stop_loop()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.update_hyperparameters"><code class="docutils literal notranslate"><span class="pre">DicePyTorch.update_hyperparameters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_random">dice_ml.explainer_interfaces.dice_random module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_random.DiceRandom"><code class="docutils literal notranslate"><span class="pre">DiceRandom</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_random.DiceRandom.get_continuous_samples"><code class="docutils literal notranslate"><span class="pre">DiceRandom.get_continuous_samples()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_random.DiceRandom.get_samples"><code class="docutils literal notranslate"><span class="pre">DiceRandom.get_samples()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_tensorflow1">dice_ml.explainer_interfaces.dice_tensorflow1 module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_dist"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.compute_dist()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_diversity_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.compute_diversity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_proximity_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.compute_proximity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_regularization_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.compute_regularization_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_yloss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.compute_yloss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_cf_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.do_cf_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_loss_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.do_loss_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_optimizer_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.do_optimizer_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.dpp_style"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.dpp_style()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.find_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.generate_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.initialize_CFs"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.initialize_CFs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.predict_fn"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.predict_fn_for_sparsity"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.predict_fn_for_sparsity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.round_off_cfs"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.round_off_cfs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.scipy_optimizers"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.scipy_optimizers()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.stop_loop"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.stop_loop()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.tensorflow_optimizers"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.tensorflow_optimizers()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.update_hyperparameters"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow1.update_hyperparameters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.dice_tensorflow2">dice_ml.explainer_interfaces.dice_tensorflow2 module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_dist"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_dist()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_diversity_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_diversity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_proximity_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_proximity_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_regularization_loss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_regularization_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_yloss"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.compute_yloss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_cf_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.do_cf_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_loss_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.do_loss_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_optimizer_initializations"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.do_optimizer_initializations()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.dpp_style"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.dpp_style()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.find_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.generate_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.initialize_CFs"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.initialize_CFs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.predict_fn"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.predict_fn_for_sparsity"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.predict_fn_for_sparsity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.round_off_cfs"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.round_off_cfs()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.stop_loop"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.stop_loop()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.update_hyperparameters"><code class="docutils literal notranslate"><span class="pre">DiceTensorFlow2.update_hyperparameters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.explainer_base">dice_ml.explainer_interfaces.explainer_base module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.build_KD_tree"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.build_KD_tree()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_permitted_range"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.check_permitted_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_query_instance_validity"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.check_query_instance_validity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.decide_cf_validity"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.decide_cf_validity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.deserialize_explainer"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.deserialize_explainer()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_binary_search"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.do_binary_search()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.do_linear_search()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.do_posthoc_sparsity_enhancement()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.feature_importance"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.feature_importance()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.generate_counterfactuals"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.generate_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.get_model_output_from_scores"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.get_model_output_from_scores()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.global_feature_importance"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.global_feature_importance()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.infer_target_cfs_class"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.infer_target_cfs_class()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.infer_target_cfs_range"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.infer_target_cfs_range()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.is_cf_valid"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.is_cf_valid()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.local_feature_importance"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.local_feature_importance()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.misc_init"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.misc_init()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.predict_fn()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn_for_sparsity"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.predict_fn_for_sparsity()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.round_to_precision"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.round_to_precision()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.serialize_explainer"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.serialize_explainer()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.setup"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.setup()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.sigmoid"><code class="docutils literal notranslate"><span class="pre">ExplainerBase.sigmoid()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.feasible_base_vae">dice_ml.explainer_interfaces.feasible_base_vae module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE"><code class="docutils literal notranslate"><span class="pre">FeasibleBaseVAE</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.compute_loss"><code class="docutils literal notranslate"><span class="pre">FeasibleBaseVAE.compute_loss()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.generate_counterfactuals"><code class="docutils literal notranslate"><span class="pre">FeasibleBaseVAE.generate_counterfactuals()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.train"><code class="docutils literal notranslate"><span class="pre">FeasibleBaseVAE.train()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces.feasible_model_approx">dice_ml.explainer_interfaces.feasible_model_approx module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox"><code class="docutils literal notranslate"><span class="pre">FeasibleModelApprox</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox.train"><code class="docutils literal notranslate"><span class="pre">FeasibleModelApprox.train()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.explainer_interfaces.html#module-dice_ml.explainer_interfaces">Module contents</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="dice_ml.model_interfaces.html">dice_ml.model_interfaces package</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.base_model">dice_ml.model_interfaces.base_model module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.keras_tensorflow_model">dice_ml.model_interfaces.keras_tensorflow_model module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.pytorch_model">dice_ml.model_interfaces.pytorch_model module</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.base_model">dice_ml.model_interfaces.base_model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel"><code class="docutils literal notranslate"><span class="pre">BaseModel</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.get_gradient"><code class="docutils literal notranslate"><span class="pre">BaseModel.get_gradient()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.get_num_output_nodes"><code class="docutils literal notranslate"><span class="pre">BaseModel.get_num_output_nodes()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.get_num_output_nodes2"><code class="docutils literal notranslate"><span class="pre">BaseModel.get_num_output_nodes2()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.get_output"><code class="docutils literal notranslate"><span class="pre">BaseModel.get_output()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.load_model"><code class="docutils literal notranslate"><span class="pre">BaseModel.load_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.keras_tensorflow_model">dice_ml.model_interfaces.keras_tensorflow_model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel"><code class="docutils literal notranslate"><span class="pre">KerasTensorFlowModel</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_gradient"><code class="docutils literal notranslate"><span class="pre">KerasTensorFlowModel.get_gradient()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_num_output_nodes"><code class="docutils literal notranslate"><span class="pre">KerasTensorFlowModel.get_num_output_nodes()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_output"><code class="docutils literal notranslate"><span class="pre">KerasTensorFlowModel.get_output()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.load_model"><code class="docutils literal notranslate"><span class="pre">KerasTensorFlowModel.load_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces.pytorch_model">dice_ml.model_interfaces.pytorch_model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel"><code class="docutils literal notranslate"><span class="pre">PyTorchModel</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_gradient"><code class="docutils literal notranslate"><span class="pre">PyTorchModel.get_gradient()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_num_output_nodes"><code class="docutils literal notranslate"><span class="pre">PyTorchModel.get_num_output_nodes()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output"><code class="docutils literal notranslate"><span class="pre">PyTorchModel.get_output()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.load_model"><code class="docutils literal notranslate"><span class="pre">PyTorchModel.load_model()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.set_eval_mode"><code class="docutils literal notranslate"><span class="pre">PyTorchModel.set_eval_mode()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.model_interfaces.html#module-dice_ml.model_interfaces">Module contents</a></li>
 </ul>
 </li>
@@ -176,9 +498,53 @@ <h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to thi
 </ul>
 </li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.exception">dice_ml.utils.exception module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.helpers">dice_ml.utils.helpers module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.serialize">dice_ml.utils.serialize module</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.exception">dice_ml.utils.exception module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.exception.SystemException"><code class="docutils literal notranslate"><span class="pre">SystemException</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.exception.UserConfigValidationException"><code class="docutils literal notranslate"><span class="pre">UserConfigValidationException</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.helpers">dice_ml.utils.helpers module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer"><code class="docutils literal notranslate"><span class="pre">DataTransfomer</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.feed_data_params"><code class="docutils literal notranslate"><span class="pre">DataTransfomer.feed_data_params()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.initialize_transform_func"><code class="docutils literal notranslate"><span class="pre">DataTransfomer.initialize_transform_func()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.inverse_transform"><code class="docutils literal notranslate"><span class="pre">DataTransfomer.inverse_transform()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.transform"><code class="docutils literal notranslate"><span class="pre">DataTransfomer.transform()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_adult_data_info"><code class="docutils literal notranslate"><span class="pre">get_adult_data_info()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_adult_income_modelpath"><code class="docutils literal notranslate"><span class="pre">get_adult_income_modelpath()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_base_gen_cf_initialization"><code class="docutils literal notranslate"><span class="pre">get_base_gen_cf_initialization()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline"><code class="docutils literal notranslate"><span class="pre">get_custom_dataset_modelpath_pipeline()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_binary"><code class="docutils literal notranslate"><span class="pre">get_custom_dataset_modelpath_pipeline_binary()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_multiclass"><code class="docutils literal notranslate"><span class="pre">get_custom_dataset_modelpath_pipeline_multiclass()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_regression"><code class="docutils literal notranslate"><span class="pre">get_custom_dataset_modelpath_pipeline_regression()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.get_custom_vars_dataset_modelpath_pipeline"><code class="docutils literal notranslate"><span class="pre">get_custom_vars_dataset_modelpath_pipeline()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.inverse_ohe_min_max_transformation"><code class="docutils literal notranslate"><span class="pre">inverse_ohe_min_max_transformation()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_adult_income_dataset"><code class="docutils literal notranslate"><span class="pre">load_adult_income_dataset()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_custom_testing_dataset"><code class="docutils literal notranslate"><span class="pre">load_custom_testing_dataset()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_custom_testing_dataset_binary"><code class="docutils literal notranslate"><span class="pre">load_custom_testing_dataset_binary()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_custom_testing_dataset_multiclass"><code class="docutils literal notranslate"><span class="pre">load_custom_testing_dataset_multiclass()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_custom_testing_dataset_regression"><code class="docutils literal notranslate"><span class="pre">load_custom_testing_dataset_regression()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_min_max_equal_dataset"><code class="docutils literal notranslate"><span class="pre">load_min_max_equal_dataset()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.load_outcome_not_last_column_dataset"><code class="docutils literal notranslate"><span class="pre">load_outcome_not_last_column_dataset()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.ohe_min_max_transformation"><code class="docutils literal notranslate"><span class="pre">ohe_min_max_transformation()</span></code></a></li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.helpers.save_adult_income_model"><code class="docutils literal notranslate"><span class="pre">save_adult_income_model()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks">dice_ml.utils.neuralnetworks module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.neuralnetworks.FFNetwork"><code class="docutils literal notranslate"><span class="pre">FFNetwork</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.neuralnetworks.FFNetwork.forward"><code class="docutils literal notranslate"><span class="pre">FFNetwork.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.serialize">dice_ml.utils.serialize module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.serialize.DummyDataInterface"><code class="docutils literal notranslate"><span class="pre">DummyDataInterface</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#dice_ml.utils.serialize.DummyDataInterface.to_json"><code class="docutils literal notranslate"><span class="pre">DummyDataInterface.to_json()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils">Module contents</a></li>
 </ul>
 </li>
@@ -186,10 +552,10 @@ <h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to thi
 </div>
 </section>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.constants">
-<span id="dice-ml-constants-module"></span><h2>dice_ml.constants module<a class="headerlink" href="#module-dice_ml.constants" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-constants-module"></span><h2>dice_ml.constants module<a class="headerlink" href="#module-dice_ml.constants" title="Permalink to this heading"></a></h2>
 <p>Constants for dice-ml package.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.constants.BackEndTypes">
@@ -252,6 +618,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <span class="sig-name descname"><span class="pre">Genetic</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'genetic'</span></em><a class="headerlink" href="#dice_ml.constants.SamplingStrategy.Genetic" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
+<dl class="py attribute">
+<dt class="sig sig-object py" id="dice_ml.constants.SamplingStrategy.Gradient">
+<span class="sig-name descname"><span class="pre">Gradient</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'gradient'</span></em><a class="headerlink" href="#dice_ml.constants.SamplingStrategy.Gradient" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py attribute">
 <dt class="sig sig-object py" id="dice_ml.constants.SamplingStrategy.KdTree">
 <span class="sig-name descname"><span class="pre">KdTree</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'kdtree'</span></em><a class="headerlink" href="#dice_ml.constants.SamplingStrategy.KdTree" title="Permalink to this definition"></a></dt>
@@ -266,7 +637,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.counterfactual_explanations">
-<span id="dice-ml-counterfactual-explanations-module"></span><h2>dice_ml.counterfactual_explanations module<a class="headerlink" href="#module-dice_ml.counterfactual_explanations" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-counterfactual-explanations-module"></span><h2>dice_ml.counterfactual_explanations module<a class="headerlink" href="#module-dice_ml.counterfactual_explanations" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.counterfactual_explanations.CounterfactualExplanations">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.counterfactual_explanations.</span></span><span class="sig-name descname"><span class="pre">CounterfactualExplanations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cf_examples_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_importance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">summary_importance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/counterfactual_explanations.html#CounterfactualExplanations"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.counterfactual_explanations.CounterfactualExplanations" title="Permalink to this definition"></a></dt>
@@ -331,7 +702,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.data">
-<span id="dice-ml-data-module"></span><h2>dice_ml.data module<a class="headerlink" href="#module-dice_ml.data" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-data-module"></span><h2>dice_ml.data module<a class="headerlink" href="#module-dice_ml.data" title="Permalink to this heading"></a></h2>
 <p>Module pointing to different implementations of Data class</p>
 <p>DiCE requires only few parameters about the data such as the range of continuous
 features and the levels of categorical features. Hence, DiCE can be used for a
@@ -340,7 +711,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.data.Data">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.data.</span></span><span class="sig-name descname"><span class="pre">Data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data.html#Data"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.data.Data" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.data_interfaces.base_data_interface._BaseData</span></code></p>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">_BaseData</span></code></p>
 <p>Class containing all required information about the data for DiCE.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.data.Data.decide_implementation_type">
@@ -361,14 +732,14 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.dice">
-<span id="dice-ml-dice-module"></span><h2>dice_ml.dice module<a class="headerlink" href="#module-dice_ml.dice" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-dice-module"></span><h2>dice_ml.dice module<a class="headerlink" href="#module-dice_ml.dice" title="Permalink to this heading"></a></h2>
 <p>Module pointing to different implementations of DiCE based on different
 frameworks such as Tensorflow or PyTorch or sklearn, and different methods
 such as RandomSampling, DiCEKD or DiCEGenetic</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.dice.Dice">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.dice.</span></span><span class="sig-name descname"><span class="pre">Dice</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'random'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/dice.html#Dice"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.dice.Dice" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <p>An interface class to different DiCE implementations.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.dice.Dice.decide_implementation_type">
@@ -389,7 +760,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.diverse_counterfactuals">
-<span id="dice-ml-diverse-counterfactuals-module"></span><h2>dice_ml.diverse_counterfactuals module<a class="headerlink" href="#module-dice_ml.diverse_counterfactuals" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-diverse-counterfactuals-module"></span><h2>dice_ml.diverse_counterfactuals module<a class="headerlink" href="#module-dice_ml.diverse_counterfactuals" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.diverse_counterfactuals.CounterfactualExamples">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.diverse_counterfactuals.</span></span><span class="sig-name descname"><span class="pre">CounterfactualExamples</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_cfs_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_instance_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_cfs_df_sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">posthoc_sparsity_param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_class</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'opposite'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'classifier'</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/diverse_counterfactuals.html#CounterfactualExamples"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.diverse_counterfactuals.CounterfactualExamples" title="Permalink to this definition"></a></dt>
@@ -435,7 +806,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.model">
-<span id="dice-ml-model-module"></span><h2>dice_ml.model module<a class="headerlink" href="#module-dice_ml.model" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-model-module"></span><h2>dice_ml.model module<a class="headerlink" href="#module-dice_ml.model" title="Permalink to this heading"></a></h2>
 <p>Module pointing to different implementations of Model class</p>
 <p>The implementations contain methods to access the output or gradients of ML models trained based on different
 frameworks such as Tensorflow or PyTorch.</p>
@@ -462,11 +833,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.Data">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.</span></span><span class="sig-name descname"><span class="pre">Data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/data.html#Data"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.Data" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.data_interfaces.base_data_interface._BaseData</span></code></p>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">_BaseData</span></code></p>
 <p>Class containing all required information about the data for DiCE.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.Data.decide_implementation_type">
@@ -479,7 +850,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.Dice">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.</span></span><span class="sig-name descname"><span class="pre">Dice</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_interface</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'random'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/dice.html#Dice"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.Dice" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.explainer_interfaces.explainer_base.ExplainerBase</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase" title="dice_ml.explainer_interfaces.explainer_base.ExplainerBase"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExplainerBase</span></code></a></p>
 <p>An interface class to different DiCE implementations.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.Dice.decide_implementation_type">
diff --git a/docs/dice_ml.model_interfaces.html b/docs/dice_ml.model_interfaces.html
index 7e436f06..8027bdc9 100644
--- a/docs/dice_ml.model_interfaces.html
+++ b/docs/dice_ml.model_interfaces.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.model_interfaces package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.model_interfaces package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -134,12 +136,12 @@
 }
 </style>
 <section id="dice-ml-model-interfaces-package">
-<h1>dice_ml.model_interfaces package<a class="headerlink" href="#dice-ml-model-interfaces-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.model_interfaces package<a class="headerlink" href="#dice-ml-model-interfaces-package" title="Permalink to this heading"></a></h1>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.model_interfaces.base_model">
-<span id="dice-ml-model-interfaces-base-model-module"></span><h2>dice_ml.model_interfaces.base_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.base_model" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-model-interfaces-base-model-module"></span><h2>dice_ml.model_interfaces.base_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.base_model" title="Permalink to this heading"></a></h2>
 <p>Module containing a template class as an interface to ML model.
 Subclasses implement model interfaces for different ML frameworks such as TensorFlow, PyTorch OR Sklearn.
 All model interface methods are in dice_ml.model_interfaces</p>
@@ -183,12 +185,12 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.model_interfaces.keras_tensorflow_model">
-<span id="dice-ml-model-interfaces-keras-tensorflow-model-module"></span><h2>dice_ml.model_interfaces.keras_tensorflow_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.keras_tensorflow_model" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-model-interfaces-keras-tensorflow-model-module"></span><h2>dice_ml.model_interfaces.keras_tensorflow_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.keras_tensorflow_model" title="Permalink to this heading"></a></h2>
 <p>Module containing an interface to trained Keras Tensorflow model.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.model_interfaces.keras_tensorflow_model.</span></span><span class="sig-name descname"><span class="pre">KerasTensorFlowModel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'TF1'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kw_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/keras_tensorflow_model.html#KerasTensorFlowModel"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.model_interfaces.base_model.BaseModel" title="dice_ml.model_interfaces.base_model.BaseModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.model_interfaces.base_model.BaseModel</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.model_interfaces.base_model.BaseModel" title="dice_ml.model_interfaces.base_model.BaseModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">BaseModel</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_gradient">
 <span class="sig-name descname"><span class="pre">get_gradient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_instance</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/keras_tensorflow_model.html#KerasTensorFlowModel.get_gradient"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_gradient" title="Permalink to this definition"></a></dt>
@@ -223,12 +225,12 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.model_interfaces.pytorch_model">
-<span id="dice-ml-model-interfaces-pytorch-model-module"></span><h2>dice_ml.model_interfaces.pytorch_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.pytorch_model" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-model-interfaces-pytorch-model-module"></span><h2>dice_ml.model_interfaces.pytorch_model module<a class="headerlink" href="#module-dice_ml.model_interfaces.pytorch_model" title="Permalink to this heading"></a></h2>
 <p>Module containing an interface to trained PyTorch model.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.model_interfaces.pytorch_model.PyTorchModel">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.model_interfaces.pytorch_model.</span></span><span class="sig-name descname"><span class="pre">PyTorchModel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'PYT'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kw_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/pytorch_model.html#PyTorchModel"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.pytorch_model.PyTorchModel" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <a class="reference internal" href="#dice_ml.model_interfaces.base_model.BaseModel" title="dice_ml.model_interfaces.base_model.BaseModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">dice_ml.model_interfaces.base_model.BaseModel</span></code></a></p>
+<dd><p>Bases: <a class="reference internal" href="#dice_ml.model_interfaces.base_model.BaseModel" title="dice_ml.model_interfaces.base_model.BaseModel"><code class="xref py py-class docutils literal notranslate"><span class="pre">BaseModel</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_gradient">
 <span class="sig-name descname"><span class="pre">get_gradient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_instance</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/pytorch_model.html#PyTorchModel.get_gradient"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_gradient" title="Permalink to this definition"></a></dt>
@@ -241,7 +243,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output">
-<span class="sig-name descname"><span class="pre">get_output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transform_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/pytorch_model.html#PyTorchModel.get_output"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">get_output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_instance</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_score</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transform_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/model_interfaces/pytorch_model.html#PyTorchModel.get_output"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output" title="Permalink to this definition"></a></dt>
 <dd><p>returns prediction probabilities</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -267,7 +269,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.model_interfaces">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.model_interfaces" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.model_interfaces" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/dice_ml.schema.html b/docs/dice_ml.schema.html
index 58907b77..ad28bc43 100644
--- a/docs/dice_ml.schema.html
+++ b/docs/dice_ml.schema.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.schema package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.schema package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -130,9 +132,9 @@
 }
 </style>
 <section id="dice-ml-schema-package">
-<h1>dice_ml.schema package<a class="headerlink" href="#dice-ml-schema-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.schema package<a class="headerlink" href="#dice-ml-schema-package" title="Permalink to this heading"></a></h1>
 <section id="module-dice_ml.schema">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.schema" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.schema" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/dice_ml.utils.html b/docs/dice_ml.utils.html
index 87dceb57..37521df1 100644
--- a/docs/dice_ml.utils.html
+++ b/docs/dice_ml.utils.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -67,6 +69,7 @@
 <li class="toctree-l4"><a class="reference internal" href="#submodules">Submodules</a></li>
 <li class="toctree-l4"><a class="reference internal" href="#module-dice_ml.utils.exception">dice_ml.utils.exception module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="#module-dice_ml.utils.helpers">dice_ml.utils.helpers module</a></li>
+<li class="toctree-l4"><a class="reference internal" href="#module-dice_ml.utils.neuralnetworks">dice_ml.utils.neuralnetworks module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="#module-dice_ml.utils.serialize">dice_ml.utils.serialize module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="#module-dice_ml.utils">Module contents</a></li>
 </ul>
@@ -135,14 +138,35 @@
 }
 </style>
 <section id="dice-ml-utils-package">
-<h1>dice_ml.utils package<a class="headerlink" href="#dice-ml-utils-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.utils package<a class="headerlink" href="#dice-ml-utils-package" title="Permalink to this heading"></a></h1>
 <section id="subpackages">
-<h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to this headline"></a></h2>
+<h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to this heading"></a></h2>
 <div class="toctree-wrapper compound">
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="dice_ml.utils.sample_architecture.html">dice_ml.utils.sample_architecture package</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#module-dice_ml.utils.sample_architecture.vae_model">dice_ml.utils.sample_architecture.vae_model module</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#module-dice_ml.utils.sample_architecture.vae_model">dice_ml.utils.sample_architecture.vae_model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder"><code class="docutils literal notranslate"><span class="pre">AutoEncoder</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.decoder"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.decoder()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.encoder"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.encoder()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.forward()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.normal_likelihood"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.normal_likelihood()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.sample_latent_code"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.sample_latent_code()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.training"><code class="docutils literal notranslate"><span class="pre">AutoEncoder.training</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE"><code class="docutils literal notranslate"><span class="pre">CF_VAE</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.compute_elbo"><code class="docutils literal notranslate"><span class="pre">CF_VAE.compute_elbo()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.decoder"><code class="docutils literal notranslate"><span class="pre">CF_VAE.decoder()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.encoder"><code class="docutils literal notranslate"><span class="pre">CF_VAE.encoder()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.forward"><code class="docutils literal notranslate"><span class="pre">CF_VAE.forward()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.normal_likelihood"><code class="docutils literal notranslate"><span class="pre">CF_VAE.normal_likelihood()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.sample_latent_code"><code class="docutils literal notranslate"><span class="pre">CF_VAE.sample_latent_code()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.training"><code class="docutils literal notranslate"><span class="pre">CF_VAE.training</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.utils.sample_architecture.html#module-dice_ml.utils.sample_architecture">Module contents</a></li>
 </ul>
 </li>
@@ -150,10 +174,10 @@ <h2>Subpackages<a class="headerlink" href="#subpackages" title="Permalink to thi
 </div>
 </section>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.utils.exception">
-<span id="dice-ml-utils-exception-module"></span><h2>dice_ml.utils.exception module<a class="headerlink" href="#module-dice_ml.utils.exception" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-utils-exception-module"></span><h2>dice_ml.utils.exception module<a class="headerlink" href="#module-dice_ml.utils.exception" title="Permalink to this heading"></a></h2>
 <p>Exceptions for the package.</p>
 <dl class="py exception">
 <dt class="sig sig-object py" id="dice_ml.utils.exception.SystemException">
@@ -181,7 +205,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.utils.helpers">
-<span id="dice-ml-utils-helpers-module"></span><h2>dice_ml.utils.helpers module<a class="headerlink" href="#module-dice_ml.utils.helpers" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-utils-helpers-module"></span><h2>dice_ml.utils.helpers module<a class="headerlink" href="#module-dice_ml.utils.helpers" title="Permalink to this heading"></a></h2>
 <p>This module containts helper functions to load data and get meta deta.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.utils.helpers.DataTransfomer">
@@ -252,6 +276,11 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <span class="sig-prename descclassname"><span class="pre">dice_ml.utils.helpers.</span></span><span class="sig-name descname"><span class="pre">get_custom_vars_dataset_modelpath_pipeline</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/helpers.html#get_custom_vars_dataset_modelpath_pipeline"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.helpers.get_custom_vars_dataset_modelpath_pipeline" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="dice_ml.utils.helpers.inverse_ohe_min_max_transformation">
+<span class="sig-prename descclassname"><span class="pre">dice_ml.utils.helpers.</span></span><span class="sig-name descname"><span class="pre">inverse_ohe_min_max_transformation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_interface</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/helpers.html#inverse_ohe_min_max_transformation"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.helpers.inverse_ohe_min_max_transformation" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 <dl class="py function">
 <dt class="sig sig-object py" id="dice_ml.utils.helpers.load_adult_income_dataset">
 <span class="sig-prename descclassname"><span class="pre">dice_ml.utils.helpers.</span></span><span class="sig-name descname"><span class="pre">load_adult_income_dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">only_train</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/helpers.html#load_adult_income_dataset"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.helpers.load_adult_income_dataset" title="Permalink to this definition"></a></dt>
@@ -302,9 +331,28 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dd><p>the data is one-hot-encoded and min-max normalized and fed to the ML model</p>
 </dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="dice_ml.utils.helpers.save_adult_income_model">
+<span class="sig-prename descclassname"><span class="pre">dice_ml.utils.helpers.</span></span><span class="sig-name descname"><span class="pre">save_adult_income_model</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modelpath</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_fraction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_state</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/helpers.html#save_adult_income_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.helpers.save_adult_income_model" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
+</section>
+<section id="module-dice_ml.utils.neuralnetworks">
+<span id="dice-ml-utils-neuralnetworks-module"></span><h2>dice_ml.utils.neuralnetworks module<a class="headerlink" href="#module-dice_ml.utils.neuralnetworks" title="Permalink to this heading"></a></h2>
+<dl class="py class">
+<dt class="sig sig-object py" id="dice_ml.utils.neuralnetworks.FFNetwork">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.neuralnetworks.</span></span><span class="sig-name descname"><span class="pre">FFNetwork</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/neuralnetworks.html#FFNetwork"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.neuralnetworks.FFNetwork" title="Permalink to this definition"></a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code></p>
+<dl class="py method">
+<dt class="sig sig-object py" id="dice_ml.utils.neuralnetworks.FFNetwork.forward">
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/neuralnetworks.html#FFNetwork.forward"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.neuralnetworks.FFNetwork.forward" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
+</dd></dl>
+
 </section>
 <section id="module-dice_ml.utils.serialize">
-<span id="dice-ml-utils-serialize-module"></span><h2>dice_ml.utils.serialize module<a class="headerlink" href="#module-dice_ml.utils.serialize" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-utils-serialize-module"></span><h2>dice_ml.utils.serialize module<a class="headerlink" href="#module-dice_ml.utils.serialize" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.utils.serialize.DummyDataInterface">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.serialize.</span></span><span class="sig-name descname"><span class="pre">DummyDataInterface</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">outcome_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data_df</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/serialize.html#DummyDataInterface"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.serialize.DummyDataInterface" title="Permalink to this definition"></a></dt>
@@ -318,7 +366,7 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 </section>
 <section id="module-dice_ml.utils">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.utils" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.utils" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/dice_ml.utils.sample_architecture.html b/docs/dice_ml.utils.sample_architecture.html
index 8ff72da0..aa2a48a7 100644
--- a/docs/dice_ml.utils.sample_architecture.html
+++ b/docs/dice_ml.utils.sample_architecture.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml.utils.sample_architecture package &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml.utils.sample_architecture package &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -48,7 +50,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -66,6 +68,7 @@
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#submodules">Submodules</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.exception">dice_ml.utils.exception module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.helpers">dice_ml.utils.helpers module</a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks">dice_ml.utils.neuralnetworks module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.serialize">dice_ml.utils.serialize module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils">Module contents</a></li>
 </ul>
@@ -135,16 +138,16 @@
 }
 </style>
 <section id="dice-ml-utils-sample-architecture-package">
-<h1>dice_ml.utils.sample_architecture package<a class="headerlink" href="#dice-ml-utils-sample-architecture-package" title="Permalink to this headline"></a></h1>
+<h1>dice_ml.utils.sample_architecture package<a class="headerlink" href="#dice-ml-utils-sample-architecture-package" title="Permalink to this heading"></a></h1>
 <section id="submodules">
-<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
+<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this heading"></a></h2>
 </section>
 <section id="module-dice_ml.utils.sample_architecture.vae_model">
-<span id="dice-ml-utils-sample-architecture-vae-model-module"></span><h2>dice_ml.utils.sample_architecture.vae_model module<a class="headerlink" href="#module-dice_ml.utils.sample_architecture.vae_model" title="Permalink to this headline"></a></h2>
+<span id="dice-ml-utils-sample-architecture-vae-model-module"></span><h2>dice_ml.utils.sample_architecture.vae_model module<a class="headerlink" href="#module-dice_ml.utils.sample_architecture.vae_model" title="Permalink to this heading"></a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.AutoEncoder">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.sample_architecture.vae_model.</span></span><span class="sig-name descname"><span class="pre">AutoEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#AutoEncoder"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Module</span></code></p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.sample_architecture.vae_model.</span></span><span class="sig-name descname"><span class="pre">AutoEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoded_size</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#AutoEncoder"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder" title="Permalink to this definition"></a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.AutoEncoder.decoder">
 <span class="sig-name descname"><span class="pre">decoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">z</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#AutoEncoder.decoder"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.decoder" title="Permalink to this definition"></a></dt>
@@ -158,7 +161,16 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward">
 <span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#AutoEncoder.forward"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward" title="Permalink to this definition"></a></dt>
-<dd></dd></dl>
+<dd><p>Defines the computation performed at every call.</p>
+<p>Should be overridden by all subclasses.</p>
+<div class="admonition note">
+<p class="admonition-title">Note</p>
+<p>Although the recipe for forward pass needs to be defined within
+this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
+instead of this since the former takes care of running the
+registered hooks while the latter silently ignores them.</p>
+</div>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.AutoEncoder.normal_likelihood">
@@ -170,12 +182,17 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <span class="sig-name descname"><span class="pre">sample_latent_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mean</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logvar</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#AutoEncoder.sample_latent_code"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.sample_latent_code" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
+<dl class="py attribute">
+<dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.AutoEncoder.training">
+<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.training" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.CF_VAE">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.sample_architecture.vae_model.</span></span><span class="sig-name descname"><span class="pre">CF_VAE</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#CF_VAE"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE" title="Permalink to this definition"></a></dt>
-<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Module</span></code></p>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">dice_ml.utils.sample_architecture.vae_model.</span></span><span class="sig-name descname"><span class="pre">CF_VAE</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoded_size</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#CF_VAE"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE" title="Permalink to this definition"></a></dt>
+<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.CF_VAE.compute_elbo">
 <span class="sig-name descname"><span class="pre">compute_elbo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">c</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pred_model</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#CF_VAE.compute_elbo"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE.compute_elbo" title="Permalink to this definition"></a></dt>
@@ -194,7 +211,16 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.CF_VAE.forward">
 <span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">c</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#CF_VAE.forward"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE.forward" title="Permalink to this definition"></a></dt>
-<dd></dd></dl>
+<dd><p>Defines the computation performed at every call.</p>
+<p>Should be overridden by all subclasses.</p>
+<div class="admonition note">
+<p class="admonition-title">Note</p>
+<p>Although the recipe for forward pass needs to be defined within
+this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
+instead of this since the former takes care of running the
+registered hooks while the latter silently ignores them.</p>
+</div>
+</dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.CF_VAE.normal_likelihood">
@@ -206,11 +232,16 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 <span class="sig-name descname"><span class="pre">sample_latent_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mean</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logvar</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/dice_ml/utils/sample_architecture/vae_model.html#CF_VAE.sample_latent_code"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE.sample_latent_code" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
+<dl class="py attribute">
+<dt class="sig sig-object py" id="dice_ml.utils.sample_architecture.vae_model.CF_VAE.training">
+<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#dice_ml.utils.sample_architecture.vae_model.CF_VAE.training" title="Permalink to this definition"></a></dt>
+<dd></dd></dl>
+
 </dd></dl>
 
 </section>
 <section id="module-dice_ml.utils.sample_architecture">
-<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.utils.sample_architecture" title="Permalink to this headline"></a></h2>
+<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-dice_ml.utils.sample_architecture" title="Permalink to this heading"></a></h2>
 </section>
 </section>
 
diff --git a/docs/genindex.html b/docs/genindex.html
index 7f38acbc..c6d5dd9d 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Index &mdash; DiCE 0.8 documentation</title>
+  <title>Index &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="#" />
@@ -46,7 +48,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -142,16 +144,8 @@ <h2 id="C">C</h2>
 </li>
       <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE">CF_VAE (class in dice_ml.utils.sample_architecture.vae_model)</a>
 </li>
-      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_features_to_vary">check_features_to_vary() (dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+      <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_permitted_range">check_permitted_range() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
-      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_mad_validity">check_mad_validity() (dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
-</li>
-      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.check_permitted_range">check_permitted_range() (dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
-
-      <ul>
-        <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_permitted_range">(dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
-</li>
-      </ul></li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_query_instance_validity">check_query_instance_validity() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
       <li><a href="dice_ml.html#dice_ml.constants.ModelTypes.Classifier">Classifier (dice_ml.constants.ModelTypes attribute)</a>
@@ -487,6 +481,13 @@ <h2 id="D">D</h2>
 
       <ul>
         <li><a href="dice_ml.utils.html#module-dice_ml.utils.helpers">module</a>
+</li>
+      </ul></li>
+      <li>
+    dice_ml.utils.neuralnetworks
+
+      <ul>
+        <li><a href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks">module</a>
 </li>
       </ul></li>
       <li>
@@ -607,6 +608,8 @@ <h2 id="F">F</h2>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.feature_importance">feature_importance() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.feed_data_params">feed_data_params() (dice_ml.utils.helpers.DataTransfomer method)</a>
+</li>
+      <li><a href="dice_ml.utils.html#dice_ml.utils.neuralnetworks.FFNetwork">FFNetwork (class in dice_ml.utils.neuralnetworks)</a>
 </li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.find_counterfactuals">find_counterfactuals() (dice_ml.explainer_interfaces.dice_genetic.DiceGenetic method)</a>
 
@@ -622,9 +625,17 @@ <h2 id="F">F</h2>
       </ul></li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward">forward() (dice_ml.utils.sample_architecture.vae_model.AutoEncoder method)</a>
+      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders">fit_label_encoders() (dice_ml.data_interfaces.private_data_interface.PrivateData method)</a>
+
+      <ul>
+        <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders">(dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+</li>
+      </ul></li>
+      <li><a href="dice_ml.utils.html#dice_ml.utils.neuralnetworks.FFNetwork.forward">forward() (dice_ml.utils.neuralnetworks.FFNetwork method)</a>
 
       <ul>
+        <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward">(dice_ml.utils.sample_architecture.vae_model.AutoEncoder method)</a>
+</li>
         <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.forward">(dice_ml.utils.sample_architecture.vae_model.CF_VAE method)</a>
 </li>
       </ul></li>
@@ -652,11 +663,9 @@ <h2 id="F">F</h2>
 <h2 id="G">G</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.generate_counterfactuals">generate_counterfactuals() (dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch method)</a>
+      <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals">generate_counterfactuals() (dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1 method)</a>
 
       <ul>
-        <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals">(dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1 method)</a>
-</li>
         <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals">(dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2 method)</a>
 </li>
         <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.generate_counterfactuals">(dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
@@ -670,6 +679,12 @@ <h2 id="G">G</h2>
 </li>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.get_adult_income_modelpath">get_adult_income_modelpath() (in module dice_ml.utils.helpers)</a>
 </li>
+      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames">get_all_dummy_colnames() (dice_ml.data_interfaces.private_data_interface.PrivateData method)</a>
+
+      <ul>
+        <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames">(dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+</li>
+      </ul></li>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.get_base_gen_cf_initialization">get_base_gen_cf_initialization() (in module dice_ml.utils.helpers)</a>
 </li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_random.DiceRandom.get_continuous_samples">get_continuous_samples() (dice_ml.explainer_interfaces.dice_random.DiceRandom method)</a>
@@ -710,8 +725,12 @@ <h2 id="G">G</h2>
         <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_encoded_categorical_feature_indexes">(dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
 </li>
       </ul></li>
-      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range">get_features_range() (dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range">get_features_range() (dice_ml.data_interfaces.private_data_interface.PrivateData method)</a>
+
+      <ul>
+        <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range">(dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
 </li>
+      </ul></li>
       <li><a href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.base_model.BaseModel.get_gradient">get_gradient() (dice_ml.model_interfaces.base_model.BaseModel method)</a>
 
       <ul>
@@ -778,9 +797,11 @@ <h2 id="G">G</h2>
 </li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_random.DiceRandom.get_samples">get_samples() (dice_ml.explainer_interfaces.dice_random.DiceRandom method)</a>
 </li>
-      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_feature_range">get_valid_feature_range() (dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+      <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range">get_valid_feature_range() (dice_ml.data_interfaces.private_data_interface.PrivateData method)</a>
 
       <ul>
+        <li><a href="dice_ml.data_interfaces.html#dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_feature_range">(dice_ml.data_interfaces.public_data_interface.PublicData method)</a>
+</li>
         <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.get_valid_feature_range">(dice_ml.explainer_interfaces.dice_genetic.DiceGenetic method)</a>
 </li>
       </ul></li>
@@ -791,6 +812,8 @@ <h2 id="G">G</h2>
 </li>
       </ul></li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.global_feature_importance">global_feature_importance() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
+</li>
+      <li><a href="dice_ml.html#dice_ml.constants.SamplingStrategy.Gradient">Gradient (dice_ml.constants.SamplingStrategy attribute)</a>
 </li>
   </ul></td>
 </tr></table>
@@ -813,6 +836,8 @@ <h2 id="I">I</h2>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.initialize_transform_func">initialize_transform_func() (dice_ml.utils.helpers.DataTransfomer method)</a>
+</li>
+      <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.inverse_ohe_min_max_transformation">inverse_ohe_min_max_transformation() (in module dice_ml.utils.helpers)</a>
 </li>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.inverse_transform">inverse_transform() (dice_ml.utils.helpers.DataTransfomer method)</a>
 </li>
@@ -959,6 +984,8 @@ <h2 id="M">M</h2>
         <li><a href="dice_ml.utils.html#module-dice_ml.utils.exception">dice_ml.utils.exception</a>
 </li>
         <li><a href="dice_ml.utils.html#module-dice_ml.utils.helpers">dice_ml.utils.helpers</a>
+</li>
+        <li><a href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks">dice_ml.utils.neuralnetworks</a>
 </li>
         <li><a href="dice_ml.utils.sample_architecture.html#module-dice_ml.utils.sample_architecture">dice_ml.utils.sample_architecture</a>
 </li>
@@ -1094,17 +1121,19 @@ <h2 id="S">S</h2>
 </li>
       </ul></li>
       <li><a href="dice_ml.html#dice_ml.constants.SamplingStrategy">SamplingStrategy (class in dice_ml.constants)</a>
+</li>
+      <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.save_adult_income_model">save_adult_income_model() (in module dice_ml.utils.helpers)</a>
 </li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.scipy_optimizers">scipy_optimizers() (dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1 method)</a>
 </li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.serialize_explainer">serialize_explainer() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
       <li><a href="dice_ml.model_interfaces.html#dice_ml.model_interfaces.pytorch_model.PyTorchModel.set_eval_mode">set_eval_mode() (dice_ml.model_interfaces.pytorch_model.PyTorchModel method)</a>
-</li>
-      <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.setup">setup() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.setup">setup() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
+</li>
       <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.explainer_base.ExplainerBase.sigmoid">sigmoid() (dice_ml.explainer_interfaces.explainer_base.ExplainerBase method)</a>
 </li>
       <li><a href="dice_ml.html#dice_ml.constants.BackEndTypes.Sklearn">Sklearn (dice_ml.constants.BackEndTypes attribute)</a>
@@ -1147,6 +1176,12 @@ <h2 id="T">T</h2>
 
       <ul>
         <li><a href="dice_ml.explainer_interfaces.html#dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox.train">(dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox method)</a>
+</li>
+      </ul></li>
+      <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.AutoEncoder.training">training (dice_ml.utils.sample_architecture.vae_model.AutoEncoder attribute)</a>
+
+      <ul>
+        <li><a href="dice_ml.utils.sample_architecture.html#dice_ml.utils.sample_architecture.vae_model.CF_VAE.training">(dice_ml.utils.sample_architecture.vae_model.CF_VAE attribute)</a>
 </li>
       </ul></li>
       <li><a href="dice_ml.utils.html#dice_ml.utils.helpers.DataTransfomer.transform">transform() (dice_ml.utils.helpers.DataTransfomer method)</a>
diff --git a/docs/index.html b/docs/index.html
index 4eb98b54..38990471 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Diverse Counterfactual Explanations (DiCE) for ML &mdash; DiCE 0.8 documentation</title>
+  <title>Diverse Counterfactual Explanations (DiCE) for ML &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -48,7 +50,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -106,9 +108,9 @@
     text-align: unset;
 }
 </style>
-<p><a class="reference external" href="https://github.com/interpretml/dice/actions?query=workflow%3A%22Python+package%22"><img alt="BuildStatus" src="https://github.com/interpretml/dice/workflows/Python%20package/badge.svg" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PyPiVersion" src="https://img.shields.io/pypi/v/dice-ml" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PythonSupport" src="https://img.shields.io/pypi/pyversions/dice-ml" /></a></p>
+<p><a class="reference external" href="https://github.com/interpretml/dice/actions?query=workflow%3A%22Python+package%22"><img alt="BuildStatus" src="https://github.com/interpretml/dice/workflows/Python%20package/badge.svg" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PyPiVersion" src="https://img.shields.io/pypi/v/dice-ml" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PythonSupport" src="https://img.shields.io/pypi/pyversions/dice-ml" /></a> <a class="reference external" href="https://anaconda.org/conda-forge/dice-ml"><img alt="CondaVersion" src="https://anaconda.org/conda-forge/dice-ml/badges/version.svg" /></a></p>
 <section id="diverse-counterfactual-explanations-dice-for-ml">
-<h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href="#diverse-counterfactual-explanations-dice-for-ml" title="Permalink to this headline"></a></h1>
+<h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href="#diverse-counterfactual-explanations-dice-for-ml" title="Permalink to this heading"></a></h1>
 <p><em>How to explain a machine learning model such that the explanation is truthful to the model and yet interpretable to people?</em></p>
 <p><a class="reference external" href="https://raam93.github.io/">Ramaravind K. Mothilal</a>, <a class="reference external" href="http://www.amitsharma.in/">Amit Sharma</a>, <a class="reference external" href="https://chenhaot.com/">Chenhao Tan</a></p>
 <p><a class="reference external" href="https://arxiv.org/abs/1905.07697">FAT* ‘20 paper</a> | <a class="reference external" href="https://interpretml.github.io/DiCE/">Docs</a> | <a class="reference external" href="https://github.com/interpretml/DiCE/tree/master/docs/source/notebooks">Example Notebooks</a> | Live Jupyter notebook <a class="reference external" href="https://mybinder.org/v2/gh/interpretML/DiCE/master?filepath=docs/source/notebooks"><img alt="Binder" src="https://mybinder.org/badge_logo.svg" /></a></p>
@@ -124,11 +126,15 @@ <h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href=
 <p>DiCE implements <a class="reference external" href="https://arxiv.org/abs/1711.00399">counterfactual (CF) explanations</a>  that provide this information by showing feature-perturbed versions of the same person who would have received the loan, e.g., <code class="docutils literal notranslate"><span class="pre">you</span> <span class="pre">would</span> <span class="pre">have</span> <span class="pre">received</span> <span class="pre">the</span> <span class="pre">loan</span> <span class="pre">if</span> <span class="pre">your</span> <span class="pre">income</span> <span class="pre">was</span> <span class="pre">higher</span> <span class="pre">by</span> <span class="pre">$10,000</span></code>. In other words, it provides “what-if” explanations for model output and can be a useful complement to other explanation methods, both for end-users and model developers.</p>
 <p>Barring simple linear models, however, it is difficult to generate CF examples that work for any machine learning model. DiCE is based on <a class="reference external" href="https://arxiv.org/abs/1905.07697">recent research</a> that generates CF explanations for any ML model. The core idea is to setup finding such explanations as an optimization problem, similar to finding adversarial examples. The critical difference is that for explanations, we need perturbations that change the output of a machine learning model, but are also diverse and feasible to change. Therefore, DiCE supports generating a set of counterfactual explanations  and has tunable parameters for diversity and proximity of the explanations to the original input. It also supports simple constraints on features to ensure feasibility of the generated counterfactual examples.</p>
 <section id="installing-dice">
-<h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalink to this headline"></a></h2>
+<h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalink to this heading"></a></h2>
 <p>DiCE supports Python 3+. The stable version of DiCE is available on <a class="reference external" href="https://pypi.org/project/dice-ml/">PyPI</a>.</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip install dice-ml
 </pre></div>
 </div>
+<p>DiCE is also available on <a class="reference external" href="https://anaconda.org/conda-forge/dice-ml">conda-forge</a>.</p>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>conda install -c conda-forge dice-ml
+</pre></div>
+</div>
 <p>To install the latest (dev) version of DiCE and its dependencies, clone this repo and run <cite>pip install</cite> from the top-most folder of the repo:</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip install -e .
 </pre></div>
@@ -153,7 +159,7 @@ <h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalin
 </ul>
 </section>
 <section id="getting-started-with-dice">
-<h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-dice" title="Permalink to this headline"></a></h2>
+<h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-dice" title="Permalink to this heading"></a></h2>
 <p>With DiCE, generating explanations is a simple three-step  process: train
 mode and then invoke DiCE to generate counterfactual examples for any input.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">dice_ml</span>
@@ -206,7 +212,7 @@ <h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-d
 </ul>
 </section>
 <section id="supported-methods-for-generating-counterfactuals">
-<h2>Supported methods for generating counterfactuals<a class="headerlink" href="#supported-methods-for-generating-counterfactuals" title="Permalink to this headline"></a></h2>
+<h2>Supported methods for generating counterfactuals<a class="headerlink" href="#supported-methods-for-generating-counterfactuals" title="Permalink to this heading"></a></h2>
 <p>DiCE can generate counterfactual examples using the following methods.</p>
 <p><strong>Model-agnostic methods</strong></p>
 <ul class="simple">
@@ -223,7 +229,7 @@ <h2>Supported methods for generating counterfactuals<a class="headerlink" href="
 <p>The last two methods require a differentiable model, such as a neural network. If you are interested in a specific method, do raise an issue <a class="reference external" href="https://github.com/interpretml/DiCE/issues">here</a>.</p>
 </section>
 <section id="supported-use-cases">
-<h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="Permalink to this headline"></a></h2>
+<h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="Permalink to this heading"></a></h2>
 <p><strong>Data</strong></p>
 <p>DiCE does not need access to the full dataset. It only requires metadata properties for each feature (min, max for continuous features and levels for categorical features). Thus, for sensitive data, the dataset can be provided as:</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">d</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">Data</span><span class="p">(</span><span class="n">features</span><span class="o">=</span><span class="p">{</span>
@@ -261,7 +267,7 @@ <h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="
 <p>We visualize explanations through a table highlighting the change in features. We plan to support an English language explanation too!</p>
 </section>
 <section id="feasibility-of-counterfactual-explanations">
-<h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasibility-of-counterfactual-explanations" title="Permalink to this headline"></a></h2>
+<h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasibility-of-counterfactual-explanations" title="Permalink to this heading"></a></h2>
 <p>We acknowledge that not all counterfactual explanations may be feasible for a
 user. In general, counterfactuals closer to an individual’s profile will be
 more feasible. Diversity is also important to help an individual choose between
@@ -296,7 +302,7 @@ <h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasi
 <p>For more details, check out <a class="reference external" href="https://github.com/interpretml/DiCE/blob/master/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb">this</a> notebook.</p>
 </section>
 <section id="the-promise-of-counterfactual-explanations">
-<h2>The promise of counterfactual explanations<a class="headerlink" href="#the-promise-of-counterfactual-explanations" title="Permalink to this headline"></a></h2>
+<h2>The promise of counterfactual explanations<a class="headerlink" href="#the-promise-of-counterfactual-explanations" title="Permalink to this heading"></a></h2>
 <p>Being truthful to the model, counterfactual explanations can be useful to all stakeholders for a decision made by a machine learning model that makes decisions.</p>
 <ul class="simple">
 <li><p><strong>Decision subjects</strong>: Counterfactual explanations can be used to explore actionable recourse for a person based on a decision received by a ML model. DiCE shows decision outcomes with <em>actionable</em> alternative profiles, to help people understand what they could have done to change their model outcome.</p></li>
@@ -309,7 +315,7 @@ <h2>The promise of counterfactual explanations<a class="headerlink" href="#the-p
 </ul>
 </section>
 <section id="roadmap">
-<h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this headline"></a></h2>
+<h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this heading"></a></h2>
 <p>Ideally, counterfactual explanations should balance between a wide range of suggested changes (<em>diversity</em>), and the relative ease of adopting those changes (<em>proximity</em> to the original input), and also follow the causal laws of the world, e.g., one can hardly lower their educational degree or change their race.</p>
 <p>We are working on adding the following features to DiCE:</p>
 <ul class="simple">
@@ -321,7 +327,7 @@ <h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this headli
 </ul>
 </section>
 <section id="citing">
-<h2>Citing<a class="headerlink" href="#citing" title="Permalink to this headline"></a></h2>
+<h2>Citing<a class="headerlink" href="#citing" title="Permalink to this heading"></a></h2>
 <p>If you find DiCE useful for your research work, please cite it as follows.</p>
 <p>Ramaravind K. Mothilal, Amit Sharma, and Chenhao Tan (2020). <strong>Explaining machine learning classifiers through diverse counterfactual explanations</strong>. <em>Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency</em>.</p>
 <p>Bibtex:</p>
@@ -336,7 +342,7 @@ <h2>Citing<a class="headerlink" href="#citing" title="Permalink to this headline
 </div>
 </section>
 <section id="contributing">
-<h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to this headline"></a></h2>
+<h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to this heading"></a></h2>
 <p>This project welcomes contributions and suggestions.  Most contributions require you to agree to a
 Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
 the rights to use your contribution. For details, visit <a class="reference external" href="https://cla.microsoft.com">https://cla.microsoft.com</a>.</p>
@@ -371,7 +377,7 @@ <h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to t
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_getting_started.html#Generating-counterfactual-examples-using-DiCE">Generating counterfactual examples using DiCE</a></li>
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_getting_started.html#Generating-feature-attributions-(local-and-global)-using-DiCE">Generating feature attributions (local and global) using DiCE</a></li>
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_getting_started.html#Working-with-deep-learning-models-(TensorFlow-and-PyTorch)">Working with deep learning models (TensorFlow and PyTorch)</a></li>
-<li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_getting_started.html#More-resources:-What's-next?">More resources: What’s next?</a></li>
+<li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_getting_started.html#More-resources:-What’s-next?">More resources: What’s next?</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_feature_importances.html">Estimating local and global feature importance scores using DiCE</a><ul>
@@ -393,10 +399,10 @@ <h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to t
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html#3.-Querying-a-KD-Tree">3. Querying a KD Tree</a></li>
 </ul>
 </li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a><ul>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_with_private_data.html#Defining-meta-data">Defining meta data</a></li>
-<li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_with_private_data.html#Loading-trained-ML-model">Loading trained ML model</a></li>
 <li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_with_private_data.html#Generate-diverse-counterfactuals">Generate diverse counterfactuals</a></li>
+<li class="toctree-l2"><a class="reference internal" href="notebooks/DiCE_with_private_data.html#id1">Generate diverse counterfactuals</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a><ul>
@@ -440,7 +446,7 @@ <h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to t
 </section>
 </section>
 <section id="indices-and-tables">
-<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Permalink to this headline"></a></h1>
+<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Permalink to this heading"></a></h1>
 <ul class="simple">
 <li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
 <li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
diff --git a/docs/modules.html b/docs/modules.html
index f45ee8a0..eab52274 100644
--- a/docs/modules.html
+++ b/docs/modules.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>dice_ml &mdash; DiCE 0.8 documentation</title>
+  <title>dice_ml &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -47,7 +49,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -106,7 +108,7 @@
 }
 </style>
 <section id="dice-ml">
-<h1>dice_ml<a class="headerlink" href="#dice-ml" title="Permalink to this headline"></a></h1>
+<h1>dice_ml<a class="headerlink" href="#dice-ml" title="Permalink to this heading"></a></h1>
 <div class="toctree-wrapper compound">
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="dice_ml.html">dice_ml package</a><ul>
@@ -150,6 +152,7 @@ <h1>dice_ml<a class="headerlink" href="#dice-ml" title="Permalink to this headli
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#submodules">Submodules</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.exception">dice_ml.utils.exception module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.helpers">dice_ml.utils.helpers module</a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks">dice_ml.utils.neuralnetworks module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils.serialize">dice_ml.utils.serialize module</a></li>
 <li class="toctree-l4"><a class="reference internal" href="dice_ml.utils.html#module-dice_ml.utils">Module contents</a></li>
 </ul>
@@ -157,13 +160,96 @@ <h1>dice_ml<a class="headerlink" href="#dice-ml" title="Permalink to this headli
 </ul>
 </li>
 <li class="toctree-l2"><a class="reference internal" href="dice_ml.html#submodules">Submodules</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.constants">dice_ml.constants module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.counterfactual_explanations">dice_ml.counterfactual_explanations module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.data">dice_ml.data module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.dice">dice_ml.dice module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.diverse_counterfactuals">dice_ml.diverse_counterfactuals module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.model">dice_ml.model module</a></li>
-<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml">Module contents</a></li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.constants">dice_ml.constants module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes"><code class="docutils literal notranslate"><span class="pre">BackEndTypes</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes.ALL"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.ALL</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes.Pytorch"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Pytorch</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes.Sklearn"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Sklearn</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes.Tensorflow1"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Tensorflow1</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.BackEndTypes.Tensorflow2"><code class="docutils literal notranslate"><span class="pre">BackEndTypes.Tensorflow2</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.constants.ModelTypes"><code class="docutils literal notranslate"><span class="pre">ModelTypes</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.ModelTypes.ALL"><code class="docutils literal notranslate"><span class="pre">ModelTypes.ALL</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.ModelTypes.Classifier"><code class="docutils literal notranslate"><span class="pre">ModelTypes.Classifier</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.ModelTypes.Regressor"><code class="docutils literal notranslate"><span class="pre">ModelTypes.Regressor</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.constants.SamplingStrategy"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.SamplingStrategy.Genetic"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Genetic</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.SamplingStrategy.Gradient"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Gradient</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.SamplingStrategy.KdTree"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.KdTree</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.constants.SamplingStrategy.Random"><code class="docutils literal notranslate"><span class="pre">SamplingStrategy.Random</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.counterfactual_explanations">dice_ml.counterfactual_explanations module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.cf_examples_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.cf_examples_list</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.from_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.from_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.local_importance"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.local_importance</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.metadata"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.metadata</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.summary_importance"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.summary_importance</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.to_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.to_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_dataframe"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.visualize_as_dataframe()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExplanations.visualize_as_list()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.data">dice_ml.data module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.data.Data"><code class="docutils literal notranslate"><span class="pre">Data</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.data.Data.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Data.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.data.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.dice">dice_ml.dice module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.dice.Dice"><code class="docutils literal notranslate"><span class="pre">Dice</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.dice.Dice.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Dice.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.dice.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.diverse_counterfactuals">dice_ml.diverse_counterfactuals module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.display_df"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.display_df()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.from_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.from_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.print_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.print_list()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.to_json"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.to_json()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_dataframe"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.visualize_as_dataframe()</span></code></a></li>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_list"><code class="docutils literal notranslate"><span class="pre">CounterfactualExamples.visualize_as_list()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.diverse_counterfactuals.json_converter"><code class="docutils literal notranslate"><span class="pre">json_converter()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml.model">dice_ml.model module</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.model.Model"><code class="docutils literal notranslate"><span class="pre">Model</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.model.Model.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Model.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.model.decide"><code class="docutils literal notranslate"><span class="pre">decide()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="dice_ml.html#module-dice_ml">Module contents</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.Data"><code class="docutils literal notranslate"><span class="pre">Data</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.Data.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Data.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.Dice"><code class="docutils literal notranslate"><span class="pre">Dice</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.Dice.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Dice.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="dice_ml.html#dice_ml.Model"><code class="docutils literal notranslate"><span class="pre">Model</span></code></a><ul>
+<li class="toctree-l4"><a class="reference internal" href="dice_ml.html#dice_ml.Model.decide_implementation_type"><code class="docutils literal notranslate"><span class="pre">Model.decide_implementation_type()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
diff --git a/docs/notebooks/Benchmarking_different_CF_explanation_methods.html b/docs/notebooks/Benchmarking_different_CF_explanation_methods.html
index e21fc929..ffbd4a00 100644
--- a/docs/notebooks/Benchmarking_different_CF_explanation_methods.html
+++ b/docs/notebooks/Benchmarking_different_CF_explanation_methods.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Benchmarking different CF explanation methods &mdash; DiCE 0.8 documentation</title>
+  <title>Benchmarking different CF explanation methods &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -298,6 +300,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -306,10 +309,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -321,12 +328,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -354,7 +364,7 @@
 }
 </style>
 <section id="Benchmarking-different-CF-explanation-methods">
-<h1>Benchmarking different CF explanation methods<a class="headerlink" href="#Benchmarking-different-CF-explanation-methods" title="Permalink to this headline"></a></h1>
+<h1>Benchmarking different CF explanation methods<a class="headerlink" href="#Benchmarking-different-CF-explanation-methods" title="Permalink to this heading"></a></h1>
 <p>In this notebook, we show runtimes of different model-agnostic explanation methods. Currently, we support three model-agnostic explanation methods: 1. Random-Sampling 2. Genetic Algorithm 3. Querying a KD tree</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
@@ -386,9 +396,9 @@ <h1>Benchmarking different CF explanation methods<a class="headerlink" href="#Be
 </div>
 </div>
 <section id="Loading-dataset">
-<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this headline"></a></h2>
+<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this heading"></a></h2>
 <p>We use the “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>). For demonstration purposes, we transform the data as described in dice_ml.utils.helpers module.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
 </pre></div>
 </div>
@@ -396,6 +406,56 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">FileNotFoundError</span>                         Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [3]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> dataset <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">helpers</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">load_adult_income_dataset</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/utils/helpers.py:25</span>, in <span class="ansi-cyan-fg">load_adult_income_dataset</span><span class="ansi-blue-fg">(only_train)</span>
+<span class="ansi-green-intense-fg ansi-bold">     19</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">load_adult_income_dataset</span>(only_train<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>):
+<span class="ansi-green-intense-fg ansi-bold">     20</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Loads adult income dataset from https://archive.ics.uci.edu/ml/datasets/Adult and prepares</span>
+<span class="ansi-green-intense-fg ansi-bold">     21</span> <span style="color: rgb(175,0,0)">       the data for data analysis based on https://rpubs.com/H_Zhu/235617</span>
+<span class="ansi-green-intense-fg ansi-bold">     22</span>
+<span class="ansi-green-intense-fg ansi-bold">     23</span> <span style="color: rgb(175,0,0)">    :return adult_data: returns preprocessed adult income dataset.</span>
+<span class="ansi-green-intense-fg ansi-bold">     24</span> <span style="color: rgb(175,0,0)">    &#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 25</span>     raw_data <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">genfromtxt</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">     26</span> <span class="ansi-yellow-bg">                             </span><span class="ansi-yellow-bg">delimiter</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">, </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">dtype</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">str</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">invalid_raise</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg ansi-bold" style="color: rgb(0,135,0)">False</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span>     <span style="color: rgb(95,135,135)">#  column names from &#34;https://archive.ics.uci.edu/ml/datasets/Adult&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     column_names <span style="color: rgb(98,98,98)">=</span> [<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">fnlwgt</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">educational-num</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">marital-status</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     30</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">relationship</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">race</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">gender</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-gain</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-loss</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours-per-week</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">native-country</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>]
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/npyio.py:1934</span>, in <span class="ansi-cyan-fg">genfromtxt</span><span class="ansi-blue-fg">(fname, dtype, comments, delimiter, skip_header, skip_footer, converters, missing_values, filling_values, usecols, names, excludelist, deletechars, replace_space, autostrip, case_sensitive, defaultfmt, unpack, usemask, loose, invalid_raise, max_rows, encoding, ndmin, like)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1932</span>     fname <span style="color: rgb(98,98,98)">=</span> os_fspath(fname)
+<span class="ansi-green-intense-fg ansi-bold">   1933</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span style="color: rgb(0,135,0)">isinstance</span>(fname, <span style="color: rgb(0,135,0)">str</span>):
+<span class="ansi-green-fg">-&gt; 1934</span>     fid <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">lib</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_datasource</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">fname</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">rt</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1935</span>     fid_ctx <span style="color: rgb(98,98,98)">=</span> contextlib<span style="color: rgb(98,98,98)">.</span>closing(fid)
+<span class="ansi-green-intense-fg ansi-bold">   1936</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:193</span>, in <span class="ansi-cyan-fg">open</span><span class="ansi-blue-fg">(path, mode, destpath, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    156</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    157</span> <span style="color: rgb(175,0,0)">Open `path` with `mode` and return the file object.</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    189</span>
+<span class="ansi-green-intense-fg ansi-bold">    190</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    192</span> ds <span style="color: rgb(98,98,98)">=</span> DataSource(destpath)
+<span class="ansi-green-fg">--&gt; 193</span> <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> <span class="ansi-yellow-bg">ds</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">path</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">mode</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:533</span>, in <span class="ansi-cyan-fg">DataSource.open</span><span class="ansi-blue-fg">(self, path, mode, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    530</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> _file_openers[ext](found, mode<span style="color: rgb(98,98,98)">=</span>mode,
+<span class="ansi-green-intense-fg ansi-bold">    531</span>                               encoding<span style="color: rgb(98,98,98)">=</span>encoding, newline<span style="color: rgb(98,98,98)">=</span>newline)
+<span class="ansi-green-intense-fg ansi-bold">    532</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+<span class="ansi-green-fg">--&gt; 533</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">raise</span> <span class="ansi-bold" style="color: rgb(215,95,95)">FileNotFoundError</span>(<span style="color: rgb(175,0,0)">f</span><span style="color: rgb(175,0,0)">&#34;</span><span class="ansi-bold" style="color: rgb(175,95,135)">{</span>path<span class="ansi-bold" style="color: rgb(175,95,135)">}</span><span style="color: rgb(175,0,0)"> not found.</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">FileNotFoundError</span>: https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data not found.
+</pre></div></div>
+</div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
 </pre></div>
@@ -405,105 +465,19 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </div>
 </div>
 <div class="nboutput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
-</pre></div>
+<div class="prompt empty docutils container">
 </div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [4]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dataset</span><span style="color: rgb(98,98,98)">.</span>head()
 
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>28</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>Single</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>60</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>30</td>
-      <td>Self-Employed</td>
-      <td>Assoc</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>65</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>32</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>20</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>35</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>4</th>
-      <td>41</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]:
 </pre></div>
 </div>
@@ -512,11 +486,25 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [5]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> d <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Data(dataframe<span style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">dataset</span>,
+<span class="ansi-green-intense-fg ansi-bold">      2</span>                  continuous_features<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>], outcome_name<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
+</div>
 </section>
 <section id="Training-the-ML-model">
-<h2>Training the ML model<a class="headerlink" href="#Training-the-ML-model" title="Permalink to this headline"></a></h2>
+<h2>Training the ML model<a class="headerlink" href="#Training-the-ML-model" title="Permalink to this heading"></a></h2>
 <p>Currently, the genetic algorithm &amp; KD tree methods work with scikit-learn models. Support for Tensorflow 1&amp;2 and Pytorch will be implemented soon.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[6]:
 </pre></div>
 </div>
@@ -553,7 +541,22 @@ <h2>Training the ML model<a class="headerlink" href="#Training-the-ML-model" tit
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [6]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> target <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">dataset</span>[<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#34;</span>]
+<span class="ansi-green-intense-fg ansi-bold">      3</span> <span style="color: rgb(95,135,135)"># Split data into train and test</span>
+<span class="ansi-green-intense-fg ansi-bold">      4</span> datasetX <span style="color: rgb(98,98,98)">=</span> dataset<span style="color: rgb(98,98,98)">.</span>drop(<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#34;</span>, axis<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[7]:
 </pre></div>
 </div>
@@ -561,11 +564,24 @@ <h2>Training the ML model<a class="headerlink" href="#Training-the-ML-model" tit
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [7]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> m <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Model(model<span style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">model</span>, backend<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">sklearn</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;model&#39; is not defined
+</pre></div></div>
+</div>
 </section>
 <section id="Initialize-counterfactual-generation-methods">
-<h2>Initialize counterfactual generation methods<a class="headerlink" href="#Initialize-counterfactual-generation-methods" title="Permalink to this headline"></a></h2>
+<h2>Initialize counterfactual generation methods<a class="headerlink" href="#Initialize-counterfactual-generation-methods" title="Permalink to this heading"></a></h2>
 <p>We now initialize all three counterfactuals generation methods</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[8]:
 </pre></div>
 </div>
@@ -573,7 +589,20 @@ <h2>Initialize counterfactual generation methods<a class="headerlink" href="#Ini
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [8]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> exp_random <span style="color: rgb(98,98,98)">=</span> Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">random</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[9]:
 </pre></div>
 </div>
@@ -581,7 +610,20 @@ <h2>Initialize counterfactual generation methods<a class="headerlink" href="#Ini
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [9]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> exp_genetic <span style="color: rgb(98,98,98)">=</span> Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">genetic</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]:
 </pre></div>
 </div>
@@ -589,7 +631,20 @@ <h2>Initialize counterfactual generation methods<a class="headerlink" href="#Ini
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [10]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> exp_KD <span style="color: rgb(98,98,98)">=</span> Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">kdtree</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[11]:
 </pre></div>
 </div>
@@ -597,6 +652,19 @@ <h2>Initialize counterfactual generation methods<a class="headerlink" href="#Ini
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [11]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> query_instances <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">x_train</span>[<span style="color: rgb(98,98,98)">4</span>:<span style="color: rgb(98,98,98)">7</span>]
+
+<span class="ansi-red-fg">NameError</span>: name &#39;x_train&#39; is not defined
+</pre></div></div>
+</div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[12]:
 </pre></div>
@@ -606,79 +674,21 @@ <h2>Initialize counterfactual generation methods<a class="headerlink" href="#Ini
 </div>
 </div>
 <div class="nboutput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[12]:
-</pre></div>
+<div class="prompt empty docutils container">
 </div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [12]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">query_instances</span>
 
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>9608</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-    </tr>
-    <tr>
-      <th>22027</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-    </tr>
-    <tr>
-      <th>14296</th>
-      <td>26</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Married</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
+<span class="ansi-red-fg">NameError</span>: name &#39;query_instances&#39; is not defined
+</pre></div></div>
 </div>
 </section>
 <section id="Generate-Counterfactuals">
-<h2>Generate Counterfactuals<a class="headerlink" href="#Generate-Counterfactuals" title="Permalink to this headline"></a></h2>
+<h2>Generate Counterfactuals<a class="headerlink" href="#Generate-Counterfactuals" title="Permalink to this heading"></a></h2>
 <p>We now generate counterfactuals of desired_class=0 using all three different methods and check the runtime. You can modify the number of loops (<code class="docutils literal notranslate"><span class="pre">num_loops</span></code>), and the number of diverse counterfactuals to generate (<code class="docutils literal notranslate"><span class="pre">k</span></code>).</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[13]:
@@ -735,59 +745,22 @@ <h2>Generate Counterfactuals<a class="headerlink" href="#Generate-Counterfactual
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/pandas/core/indexing.py:1676: SettingWithCopyWarning:
-A value is trying to be set on a copy of a slice from a DataFrame.
-Try using .loc[row_indexer,col_indexer] = value instead
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  self._setitem_single_column(ilocs[0], value, pi)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/pandas/core/indexing.py:1738: SettingWithCopyWarning:
-A value is trying to be set on a copy of a slice from a DataFrame.
-Try using .loc[row_indexer,col_indexer] = value instead
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  self._setitem_single_column(loc, value[:, i].tolist(), pi)
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:00&lt;00:00,  4.75it/s]
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:03&lt;00:00,  1.08s/it]
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:02&lt;00:00,  1.14it/s]
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/pandas/core/indexing.py:1676: SettingWithCopyWarning:
-A value is trying to be set on a copy of a slice from a DataFrame.
-Try using .loc[row_indexer,col_indexer] = value instead
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  self._setitem_single_column(ilocs[0], value, pi)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/pandas/core/indexing.py:1738: SettingWithCopyWarning:
-A value is trying to be set on a copy of a slice from a DataFrame.
-Try using .loc[row_indexer,col_indexer] = value instead
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  self._setitem_single_column(loc, value[:, i].tolist(), pi)
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:00&lt;00:00,  4.73it/s]
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:03&lt;00:00,  1.08s/it]
-100%|███████████████████████████████████████████████████████████████████| 3/3 [00:02&lt;00:00,  1.10it/s]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-For Independent random sampling of features: Total time taken to generate 2 sets of 2 counterfactuals each: 00 min 01 sec
-For querying from a KD tree: Total time taken to generate 2 sets of 2 counterfactuals each: 00 min 05 sec
-For genetic algorithm: Total time taken to generate 2 sets of 2 counterfactuals each: 00 min 06 sec
-</pre></div></div>
-</div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [14]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 5&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      3</span> elapsed_genetic <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(98,98,98)">0</span>
+<span class="ansi-green-intense-fg ansi-bold">      5</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> _ <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> <span style="color: rgb(0,135,0)">range</span>(num_loops):
+<span class="ansi-green-fg">----&gt; 6</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> q <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> <span class="ansi-yellow-bg">query_instances</span>:
+<span class="ansi-green-intense-fg ansi-bold">      7</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> q <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> d<span style="color: rgb(98,98,98)">.</span>categorical_feature_names:
+<span class="ansi-green-intense-fg ansi-bold">      8</span>             query_instances<span style="color: rgb(98,98,98)">.</span>loc[:, q] <span style="color: rgb(98,98,98)">=</span> \
+<span class="ansi-green-intense-fg ansi-bold">      9</span>                 [np<span style="color: rgb(98,98,98)">.</span>unique(random<span style="color: rgb(98,98,98)">.</span>choice(dataset[q]<span style="color: rgb(98,98,98)">.</span>values)) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> _ <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> query_instances<span style="color: rgb(98,98,98)">.</span>index]
+
+<span class="ansi-red-fg">NameError</span>: name &#39;query_instances&#39; is not defined
 </pre></div></div>
 </div>
 </section>
diff --git a/docs/notebooks/DiCE_feature_importances.html b/docs/notebooks/DiCE_feature_importances.html
index 38c61d2d..022acfec 100644
--- a/docs/notebooks/DiCE_feature_importances.html
+++ b/docs/notebooks/DiCE_feature_importances.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Estimating local and global feature importance scores using DiCE &mdash; DiCE 0.8 documentation</title>
+  <title>Estimating local and global feature importance scores using DiCE &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -58,7 +60,7 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -308,6 +310,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -316,10 +319,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -331,12 +338,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -364,7 +374,7 @@
 }
 </style>
 <section id="Estimating-local-and-global-feature-importance-scores-using-DiCE">
-<h1>Estimating local and global feature importance scores using DiCE<a class="headerlink" href="#Estimating-local-and-global-feature-importance-scores-using-DiCE" title="Permalink to this headline"></a></h1>
+<h1>Estimating local and global feature importance scores using DiCE<a class="headerlink" href="#Estimating-local-and-global-feature-importance-scores-using-DiCE" title="Permalink to this heading"></a></h1>
 <p>Summaries of counterfactual examples can be used to estimate importance of features. Intuitively, a feature that is changed more often to generate a proximal counterfactual is an important feature. We use this intuition to build a feature importance score.</p>
 <p>This score can be interpreted as a measure of the <strong>necessity</strong> of a feature to cause a particular model output. That is, if the feature’s value changes, then it is likely that the model’s output class will also change (or the model’s output will significantly change in case of regression model).</p>
 <p>Below we show how counterfactuals can be used to provide local feature importance scores for any input, and how those scores can be combined to yield a global importance score for each feature.</p>
@@ -394,7 +404,7 @@ <h1>Estimating local and global feature importance scores using DiCE<a class="he
 </div>
 </div>
 <section id="Preliminaries:-Loading-the-data-and-ML-model">
-<h2>Preliminaries: Loading the data and ML model<a class="headerlink" href="#Preliminaries:-Loading-the-data-and-ML-model" title="Permalink to this headline"></a></h2>
+<h2>Preliminaries: Loading the data and ML model<a class="headerlink" href="#Preliminaries:-Loading-the-data-and-ML-model" title="Permalink to this heading"></a></h2>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
 </pre></div>
@@ -469,7 +479,7 @@ <h2>Preliminaries: Loading the data and ML model<a class="headerlink" href="#Pre
 </div>
 </section>
 <section id="Local-feature-importance">
-<h2>Local feature importance<a class="headerlink" href="#Local-feature-importance" title="Permalink to this headline"></a></h2>
+<h2>Local feature importance<a class="headerlink" href="#Local-feature-importance" title="Permalink to this heading"></a></h2>
 <p>We first generate counterfactuals for a given input point.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[6]:
@@ -489,7 +499,7 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  2.24it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  3.12it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -544,14 +554,14 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
   <tbody>
     <tr>
       <th>0</th>
-      <td>42</td>
+      <td>43</td>
       <td>Private</td>
-      <td>Some-college</td>
+      <td>Bachelors</td>
       <td>Married</td>
-      <td>Blue-Collar</td>
+      <td>White-Collar</td>
       <td>White</td>
       <td>Male</td>
-      <td>89</td>
+      <td>50</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -606,59 +616,59 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Widowed</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>-</td>
+      <td>94.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>1</th>
       <td>-</td>
-      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>67.0</td>
+      <td>-</td>
+      <td>63.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>2</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
+      <td>Widowed</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>-</td>
-      <td>40.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>58.0</td>
+      <td>33.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>65.0</td>
+      <td>15.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>4</th>
+      <td>21.0</td>
       <td>-</td>
-      <td>Other/Unknown</td>
       <td>-</td>
+      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>74.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -667,58 +677,58 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Service</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
-      <td>-</td>
-      <td>28.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>6</th>
       <td>-</td>
+      <td>Government</td>
       <td>-</td>
       <td>-</td>
-      <td>Divorced</td>
+      <td>Professional</td>
       <td>-</td>
       <td>-</td>
-      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
     <tr>
       <th>7</th>
-      <td>28.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>37.0</td>
+      <td>-</td>
+      <td>14.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>8</th>
       <td>-</td>
-      <td>Other/Unknown</td>
       <td>-</td>
-      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
+      <td>77.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>9</th>
       <td>-</td>
-      <td>Government</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>64.0</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -740,7 +750,7 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-[{&#39;hours_per_week&#39;: 0.6, &#39;workclass&#39;: 0.4, &#39;marital_status&#39;: 0.3, &#39;age&#39;: 0.2, &#39;occupation&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;education&#39;: 0.0, &#39;race&#39;: 0.0}]
+[{&#39;hours_per_week&#39;: 0.6, &#39;workclass&#39;: 0.2, &#39;marital_status&#39;: 0.2, &#39;occupation&#39;: 0.2, &#39;gender&#39;: 0.2, &#39;age&#39;: 0.2, &#39;education&#39;: 0.0, &#39;race&#39;: 0.0}]
 </pre></div></div>
 </div>
 <p>Feature importance can also be estimated directly, by leaving the <code class="docutils literal notranslate"><span class="pre">cf_examples_list</span></code> argument blank.</p>
@@ -758,7 +768,7 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  7.09it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00, 12.18it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -766,7 +776,7 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-[{&#39;age&#39;: 0.4, &#39;hours_per_week&#39;: 0.4, &#39;workclass&#39;: 0.2, &#39;education&#39;: 0.2, &#39;marital_status&#39;: 0.2, &#39;occupation&#39;: 0.2, &#39;gender&#39;: 0.2, &#39;race&#39;: 0.0}]
+[{&#39;hours_per_week&#39;: 0.4, &#39;marital_status&#39;: 0.3, &#39;workclass&#39;: 0.2, &#39;education&#39;: 0.2, &#39;gender&#39;: 0.2, &#39;age&#39;: 0.2, &#39;occupation&#39;: 0.1, &#39;race&#39;: 0.0}]
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -779,7 +789,7 @@ <h2>Local feature importance<a class="headerlink" href="#Local-feature-importanc
 </div>
 </section>
 <section id="Global-importance">
-<h2>Global importance<a class="headerlink" href="#Global-importance" title="Permalink to this headline"></a></h2>
+<h2>Global importance<a class="headerlink" href="#Global-importance" title="Permalink to this heading"></a></h2>
 <p>For global importance, we need to generate counterfactuals for a representative sample of the dataset.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[9]:
@@ -795,7 +805,7 @@ <h2>Global importance<a class="headerlink" href="#Global-importance" title="Perm
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|█████████████████████████████████████████████████████████████████| 10/10 [00:01&lt;00:00,  5.27it/s]
+100%|███████████████████████████████████████████████████████████████████████████████| 10/10 [00:00&lt;00:00, 11.57it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -803,7 +813,7 @@ <h2>Global importance<a class="headerlink" href="#Global-importance" title="Perm
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-{&#39;marital_status&#39;: 0.57, &#39;education&#39;: 0.49, &#39;age&#39;: 0.48, &#39;hours_per_week&#39;: 0.42, &#39;occupation&#39;: 0.33, &#39;workclass&#39;: 0.17, &#39;gender&#39;: 0.14, &#39;race&#39;: 0.12}
+{&#39;marital_status&#39;: 0.46, &#39;age&#39;: 0.45, &#39;hours_per_week&#39;: 0.39, &#39;education&#39;: 0.31, &#39;occupation&#39;: 0.28, &#39;workclass&#39;: 0.22, &#39;gender&#39;: 0.17, &#39;race&#39;: 0.1}
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -816,7 +826,7 @@ <h2>Global importance<a class="headerlink" href="#Global-importance" title="Perm
 </div>
 </section>
 <section id="Convert-the-counterfactual-output-to-json">
-<h2>Convert the counterfactual output to json<a class="headerlink" href="#Convert-the-counterfactual-output-to-json" title="Permalink to this headline"></a></h2>
+<h2>Convert the counterfactual output to json<a class="headerlink" href="#Convert-the-counterfactual-output-to-json" title="Permalink to this heading"></a></h2>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]:
 </pre></div>
@@ -831,12 +841,12 @@ <h2>Convert the counterfactual output to json<a class="headerlink" href="#Conver
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-{&#34;test_data&#34;: [[[44, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0]], [[42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 89, 1]], [[21, &#34;Self-Employed&#34;, &#34;Some-college&#34;, &#34;Single&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 0]], [[24, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0]], [[60, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1]], [[51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0]], [[23, &#34;Private&#34;, &#34;School&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 0]], [[19, &#34;Other/Unknown&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;Other/Unknown&#34;, &#34;Other&#34;, &#34;Female&#34;, 40, 0]], [[28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1]], [[34, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1]]], &#34;cfs_list&#34;: [[[44, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [44, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [44, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 85.0, 1], [59.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 71.0, 1], [44, &#34;Government&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [44, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Male&#34;, 93.0, 1], [44, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 92.0, 1], [44, &#34;Private&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Male&#34;, 40, 1], [56.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 52.0, 1], [44, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 23.0, 1]], [[42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 50.0, 0], [42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;Other&#34;, &#34;Male&#34;, 1.0, 0], [42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 6.0, 0], [19.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 68.0, 0], [42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 46.0, 0], [42, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Widowed&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 89, 0], [42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 4.0, 0], [42, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 12.0, 0], [42, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Separated&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 49.0, 0], [68.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Widowed&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 89, 0]], [[43.0, &#34;Self-Employed&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1], [44.0, &#34;Private&#34;, &#34;Masters&#34;, &#34;Single&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1], [55.0, &#34;Self-Employed&#34;, &#34;Masters&#34;, &#34;Divorced&#34;, &#34;Service&#34;, &#34;Other&#34;, &#34;Male&#34;, 95.0, 1], [62.0, &#34;Self-Employed&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 93.0, 1], [49.0, &#34;Self-Employed&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1], [73.0, &#34;Self-Employed&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 82.0, 1], [53.0, &#34;Self-Employed&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1], [40.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1], [67.0, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 57.0, 1], [62.0, &#34;Self-Employed&#34;, &#34;Assoc&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 30, 1]], [[43.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 86.0, 1], [33.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 49.0, 1], [47.0, &#34;Private&#34;, &#34;Masters&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [47.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [34.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [37.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [43.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [34.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [38.0, &#34;Private&#34;, &#34;Masters&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [38.0, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0]], [[60, &#34;Self-Employed&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [40.0, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [60, &#34;Other/Unknown&#34;, &#34;School&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [60, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Male&#34;, 45.0, 0], [60, &#34;Private&#34;, &#34;School&#34;, &#34;Separated&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [37.0, &#34;Private&#34;, &#34;School&#34;, &#34;Divorced&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [60, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [24.0, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [60, &#34;Private&#34;, &#34;Masters&#34;, &#34;Widowed&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [60, &#34;Private&#34;, &#34;School&#34;, &#34;Single&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0]], [[51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 69.0, 0], [51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;Other&#34;, &#34;Male&#34;, 40, 1], [51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 42.0, 1], [51, &#34;Private&#34;, &#34;Doctorate&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 71.0, 1], [51, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [46.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [51, &#34;Private&#34;, &#34;Doctorate&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 77.0, 1], [51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 90.0, 1], [51, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [51, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 78.0, 1]], [[80.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 1], [35.0, &#34;Self-Employed&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 1], [46.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 38, 1], [47.0, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 1], [80.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 38, 1], [47.0, &#34;Other/Unknown&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 1], [53.0, &#34;Private&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 1], [71.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 59.0, 1], [23, &#34;Self-Employed&#34;, &#34;Doctorate&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;Other&#34;, &#34;Female&#34;, 38, 1], [50.0, &#34;Private&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 46.0, 1]], [[19, &#34;Other/Unknown&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;Other&#34;, &#34;Male&#34;, 90.0, 1], [85.0, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;Other&#34;, &#34;Female&#34;, 53.0, 1], [19, &#34;Government&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;Other&#34;, &#34;Female&#34;, 84.0, 1], [19, &#34;Other/Unknown&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;Other&#34;, &#34;Male&#34;, 90.0, 0], [54.0, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;Other&#34;, &#34;Male&#34;, 96.0, 1], [86.0, &#34;Other/Unknown&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [75.0, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;Other&#34;, &#34;Male&#34;, 92.0, 1], [88.0, &#34;Other/Unknown&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [78.0, &#34;Other/Unknown&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [19.0, &#34;Other/Unknown&#34;, &#34;Masters&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1]], [[28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Separated&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 79.0, 0], [28, &#34;Other/Unknown&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [65.0, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Widowed&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Separated&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 8.0, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 91.0, 0], [28, &#34;Other/Unknown&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Divorced&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 79.0, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;Other&#34;, &#34;Female&#34;, 40, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [28, &#34;Other/Unknown&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 1.0, 0]], [[34, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 7.0, 0], [34, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [34, &#34;Self-Employed&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [34, &#34;Self-Employed&#34;, &#34;Bachelors&#34;, &#34;Widowed&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [77.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [68.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [38.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [34, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [89.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 21.0, 0], [34, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;Other&#34;, &#34;Male&#34;, 40, 0]]], &#34;local_importance&#34;: [[0.2, 0.1, 0.4, 0.0, 0.4, 0.2, 0.0, 0.6], [0.2, 0.0, 0.2, 0.5, 0.0, 0.1, 0.0, 0.8], [1.0, 0.3, 0.6, 0.8, 0.3, 0.1, 0.0, 0.4], [1.0, 0.1, 0.7, 0.6, 0.2, 0.0, 0.3, 0.2], [0.3, 0.2, 0.1, 0.5, 0.4, 0.0, 0.1, 0.1], [0.1, 0.0, 0.4, 0.5, 0.3, 0.1, 0.0, 0.6], [0.9, 0.5, 1.0, 1.0, 0.6, 0.1, 0.3, 0.2], [0.6, 0.2, 1.0, 0.9, 0.5, 0.4, 0.4, 0.6], [0.1, 0.0, 0.2, 0.5, 0.4, 0.1, 0.2, 0.5], [0.4, 0.3, 0.3, 0.4, 0.2, 0.1, 0.1, 0.2]], &#34;summary_importance&#34;: [0.48, 0.17, 0.49, 0.57, 0.33, 0.12, 0.14, 0.42], &#34;data_interface&#34;: {&#34;outcome_name&#34;: &#34;income&#34;, &#34;data_df&#34;: &#34;dummy_data&#34;}, &#34;feature_names&#34;: [&#34;age&#34;, &#34;workclass&#34;, &#34;education&#34;, &#34;marital_status&#34;, &#34;occupation&#34;, &#34;race&#34;, &#34;gender&#34;, &#34;hours_per_week&#34;], &#34;feature_names_including_target&#34;: [&#34;age&#34;, &#34;workclass&#34;, &#34;education&#34;, &#34;marital_status&#34;, &#34;occupation&#34;, &#34;race&#34;, &#34;gender&#34;, &#34;hours_per_week&#34;, &#34;income&#34;], &#34;model_type&#34;: &#34;classifier&#34;, &#34;desired_class&#34;: &#34;opposite&#34;, &#34;desired_range&#34;: null, &#34;metadata&#34;: {&#34;version&#34;: &#34;2.0&#34;}}
+{&#34;test_data&#34;: [[[37, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 0]], [[43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 50, 1]], [[25, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0]], [[44, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 25, 0]], [[30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1]], [[33, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 0]], [[41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Divorced&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 0]], [[20, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0]], [[53, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1]], [[46, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 38, 1]]], &#34;cfs_list&#34;: [[[37, &#34;Private&#34;, &#34;Masters&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [73.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [46.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [37, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 88.0, 1], [37, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [42.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 83.0, 1], [37, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 77.0, 1], [59.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [37, &#34;Private&#34;, &#34;Masters&#34;, &#34;Separated&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [55.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1]], [[43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 2.0, 0], [43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Widowed&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 50, 0], [43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 90.0, 0], [22.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;Other&#34;, &#34;Male&#34;, 50, 0], [27.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 38.0, 0], [43, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 50, 0], [43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 80.0, 0], [19.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 83.0, 0], [43, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Separated&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 50, 0], [43, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 50, 0]], [[81.0, &#34;Other/Unknown&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Female&#34;, 40, 1], [36.0, &#34;Government&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Female&#34;, 40, 1], [44.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [31.0, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [38.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 47.0, 1], [47.0, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [67.0, &#34;Government&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [52.0, &#34;Government&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Female&#34;, 40, 1], [84.0, &#34;Self-Employed&#34;, &#34;Prof-school&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 93.0, 1], [25, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 57.0, 1]], [[44, &#34;Government&#34;, &#34;Prof-school&#34;, &#34;Widowed&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 78.0, 1], [44, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 25, 1], [44, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Male&#34;, 50.0, 1], [44, &#34;Other/Unknown&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 25, 1], [44, &#34;Government&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 82.0, 0], [44, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;Other&#34;, &#34;Male&#34;, 84.0, 1], [44, &#34;Private&#34;, &#34;Masters&#34;, &#34;Single&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 51.0, 1], [44, &#34;Government&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 98.0, 1], [44, &#34;Government&#34;, &#34;Prof-school&#34;, &#34;Single&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 25, 1], [57.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 72.0, 1]], [[30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45.0, 0], [30, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [57.0, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Widowed&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 91.0, 0], [30, &#34;Self-Employed&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 7.0, 0], [30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 56.0, 0], [30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;Other&#34;, &#34;Male&#34;, 40, 0], [30, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [29.0, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 66.0, 0], [30, &#34;Government&#34;, &#34;HS-grad&#34;, &#34;Widowed&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0]], [[67.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [69.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [33, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [75.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [69.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [33, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;Other&#34;, &#34;Male&#34;, 45, 1], [66.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [33, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 97.0, 1], [77.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [90.0, &#34;Private&#34;, &#34;HS-grad&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1]], [[41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Other/Unknown&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Doctorate&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 0], [41, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 0], [41, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Prof-school&#34;, &#34;Divorced&#34;, &#34;Service&#34;, &#34;White&#34;, &#34;Male&#34;, 45, 0], [41, &#34;Government&#34;, &#34;Prof-school&#34;, &#34;Divorced&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1], [41, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 45, 1]], [[70.0, &#34;Private&#34;, &#34;Doctorate&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 69.0, 0], [75.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 65.0, 1], [68.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 54.0, 1], [65.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 1], [83.0, &#34;Private&#34;, &#34;Prof-school&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [40.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 48.0, 1], [66.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 67.0, 0], [63.0, &#34;Private&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 79.0, 0], [44.0, &#34;Self-Employed&#34;, &#34;Assoc&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 1], [45.0, &#34;Private&#34;, &#34;Bachelors&#34;, &#34;Single&#34;, &#34;Sales&#34;, &#34;Other&#34;, &#34;Female&#34;, 74.0, 1]], [[53, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 33.0, 0], [89.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [53, &#34;Private&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 71.0, 0], [53, &#34;Self-Employed&#34;, &#34;Some-college&#34;, &#34;Divorced&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [53, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [53, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Single&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [53, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Blue-Collar&#34;, &#34;White&#34;, &#34;Female&#34;, 40, 0], [23.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;Sales&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0], [53, &#34;Government&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 7.0, 0], [42.0, &#34;Private&#34;, &#34;Some-college&#34;, &#34;Married&#34;, &#34;White-Collar&#34;, &#34;White&#34;, &#34;Male&#34;, 40, 0]], [[46, &#34;Self-Employed&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;Other&#34;, &#34;Male&#34;, 38, 0], [88.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;Other&#34;, &#34;Male&#34;, 38, 0], [46, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Separated&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 77.0, 0], [36.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 62.0, 0], [59.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 6.0, 0], [59.0, &#34;Self-Employed&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 38, 0], [46, &#34;Government&#34;, &#34;School&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Female&#34;, 38, 0], [46, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Separated&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 63.0, 0], [17.0, &#34;Government&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 38, 0], [46, &#34;Self-Employed&#34;, &#34;Bachelors&#34;, &#34;Married&#34;, &#34;Professional&#34;, &#34;White&#34;, &#34;Male&#34;, 7.0, 0]]], &#34;local_importance&#34;: [[0.5, 0.0, 0.3, 0.7, 0.2, 0.0, 0.0, 0.3], [0.3, 0.0, 0.2, 0.3, 0.0, 0.1, 0.4, 0.5], [0.9, 0.6, 0.8, 0.4, 0.3, 0.3, 0.2, 0.3], [0.1, 0.5, 0.6, 0.6, 0.6, 0.1, 0.2, 0.7], [0.2, 0.3, 0.2, 0.3, 0.0, 0.1, 0.1, 0.5], [0.7, 0.0, 0.1, 0.5, 0.5, 0.1, 0.1, 0.1], [0.0, 0.1, 0.4, 0.7, 0.6, 0.0, 0.2, 0.0], [1.0, 0.1, 0.3, 0.7, 0.3, 0.1, 0.2, 0.7], [0.3, 0.3, 0.1, 0.2, 0.3, 0.0, 0.2, 0.3], [0.5, 0.3, 0.1, 0.2, 0.0, 0.2, 0.1, 0.5]], &#34;summary_importance&#34;: [0.45, 0.22, 0.31, 0.46, 0.28, 0.1, 0.17, 0.39], &#34;data_interface&#34;: {&#34;outcome_name&#34;: &#34;income&#34;, &#34;data_df&#34;: &#34;dummy_data&#34;}, &#34;feature_names&#34;: [&#34;age&#34;, &#34;workclass&#34;, &#34;education&#34;, &#34;marital_status&#34;, &#34;occupation&#34;, &#34;race&#34;, &#34;gender&#34;, &#34;hours_per_week&#34;], &#34;feature_names_including_target&#34;: [&#34;age&#34;, &#34;workclass&#34;, &#34;education&#34;, &#34;marital_status&#34;, &#34;occupation&#34;, &#34;race&#34;, &#34;gender&#34;, &#34;hours_per_week&#34;, &#34;income&#34;], &#34;model_type&#34;: &#34;classifier&#34;, &#34;desired_class&#34;: &#34;opposite&#34;, &#34;desired_range&#34;: null, &#34;metadata&#34;: {&#34;version&#34;: &#34;2.0&#34;}}
 </pre></div></div>
 </div>
 </section>
 <section id="Convert-the-json-output-to-a-counterfactual-object">
-<h2>Convert the json output to a counterfactual object<a class="headerlink" href="#Convert-the-json-output-to-a-counterfactual-object" title="Permalink to this headline"></a></h2>
+<h2>Convert the json output to a counterfactual object<a class="headerlink" href="#Convert-the-json-output-to-a-counterfactual-object" title="Permalink to this heading"></a></h2>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[11]:
 </pre></div>
@@ -892,14 +902,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>44</td>
+      <td>37</td>
       <td>Private</td>
       <td>HS-grad</td>
-      <td>Married</td>
-      <td>Sales</td>
+      <td>Divorced</td>
+      <td>Blue-Collar</td>
       <td>White</td>
       <td>Male</td>
-      <td>40</td>
+      <td>45</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -953,9 +963,9 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <th>0</th>
       <td>-</td>
       <td>-</td>
-      <td>Assoc</td>
+      <td>Masters</td>
+      <td>Single</td>
       <td>-</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -963,11 +973,11 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>1</th>
+      <td>73.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Bachelors</td>
+      <td>Married</td>
       <td>-</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -975,34 +985,34 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>2</th>
+      <td>46.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>-</td>
-      <td>85.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>59.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>71.0</td>
+      <td>88.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>4</th>
       <td>-</td>
-      <td>Government</td>
-      <td>Masters</td>
       <td>-</td>
+      <td>Bachelors</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1011,14 +1021,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>5</th>
+      <td>42.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Other</td>
       <td>-</td>
-      <td>93.0</td>
+      <td>83.0</td>
       <td>1</td>
     </tr>
     <tr>
@@ -1026,47 +1036,47 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
       <td>-</td>
-      <td>Blue-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>92.0</td>
+      <td>77.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>7</th>
+      <td>59.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Masters</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>8</th>
-      <td>56.0</td>
       <td>-</td>
       <td>-</td>
+      <td>Masters</td>
+      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>52.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>9</th>
-      <td>-</td>
+      <td>55.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>23.0</td>
+      <td>-</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -1117,14 +1127,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>42</td>
+      <td>43</td>
       <td>Private</td>
-      <td>Some-college</td>
+      <td>Bachelors</td>
       <td>Married</td>
-      <td>Blue-Collar</td>
+      <td>White-Collar</td>
       <td>White</td>
       <td>Male</td>
-      <td>89</td>
+      <td>50</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -1183,7 +1193,7 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>50.0</td>
+      <td>2.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -1191,11 +1201,11 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Widowed</td>
       <td>-</td>
       <td>-</td>
-      <td>Other</td>
+      <td>Female</td>
       <td>-</td>
-      <td>1.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -1207,42 +1217,42 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>6.0</td>
+      <td>90.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>19.0</td>
+      <td>22.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
-      <td>68.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>4</th>
+      <td>27.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>-</td>
-      <td>46.0</td>
+      <td>38.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>5</th>
       <td>-</td>
       <td>-</td>
-      <td>Assoc</td>
-      <td>Widowed</td>
+      <td>HS-grad</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
@@ -1251,23 +1261,23 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Divorced</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>4.0</td>
+      <td>Female</td>
+      <td>80.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>7</th>
+      <td>19.0</td>
       <td>-</td>
       <td>-</td>
-      <td>HS-grad</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>12.0</td>
+      <td>83.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -1278,16 +1288,16 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>Separated</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
-      <td>49.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>9</th>
-      <td>68.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Widowed</td>
+      <td>HS-grad</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1342,14 +1352,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>21</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
+      <td>25</td>
+      <td>Private</td>
+      <td>HS-grad</td>
       <td>Single</td>
-      <td>Service</td>
+      <td>Sales</td>
       <td>White</td>
-      <td>Male</td>
-      <td>30</td>
+      <td>Female</td>
+      <td>40</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -1401,82 +1411,82 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>43.0</td>
-      <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
+      <td>81.0</td>
+      <td>Other/Unknown</td>
+      <td>Doctorate</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>44.0</td>
-      <td>Private</td>
-      <td>Masters</td>
-      <td>-</td>
+      <td>36.0</td>
+      <td>Government</td>
+      <td>Doctorate</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>55.0</td>
+      <td>44.0</td>
+      <td>-</td>
+      <td>Assoc</td>
+      <td>Married</td>
+      <td>White-Collar</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Divorced</td>
       <td>-</td>
-      <td>Other</td>
       <td>-</td>
-      <td>95.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>62.0</td>
-      <td>-</td>
+      <td>31.0</td>
+      <td>Government</td>
       <td>-</td>
       <td>Married</td>
+      <td>Other/Unknown</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>93.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>49.0</td>
+      <td>38.0</td>
       <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
-      <td>White-Collar</td>
       <td>-</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
+      <td>Male</td>
+      <td>47.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>73.0</td>
+      <td>47.0</td>
       <td>-</td>
+      <td>Prof-school</td>
       <td>-</td>
-      <td>Married</td>
-      <td>Sales</td>
+      <td>Professional</td>
       <td>-</td>
+      <td>Male</td>
       <td>-</td>
-      <td>82.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>6</th>
-      <td>53.0</td>
+      <td>67.0</td>
+      <td>Government</td>
+      <td>Doctorate</td>
       <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1485,38 +1495,38 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>7</th>
-      <td>40.0</td>
-      <td>Private</td>
-      <td>-</td>
-      <td>Married</td>
+      <td>52.0</td>
+      <td>Government</td>
+      <td>Doctorate</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>8</th>
-      <td>67.0</td>
-      <td>Government</td>
+      <td>84.0</td>
+      <td>Self-Employed</td>
+      <td>Prof-school</td>
       <td>-</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>57.0</td>
+      <td>93.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>9</th>
-      <td>62.0</td>
       <td>-</td>
-      <td>Assoc</td>
       <td>-</td>
-      <td>White-Collar</td>
+      <td>Bachelors</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>57.0</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -1567,14 +1577,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>24</td>
+      <td>44</td>
       <td>Private</td>
-      <td>HS-grad</td>
+      <td>Assoc</td>
       <td>Single</td>
-      <td>White-Collar</td>
+      <td>Blue-Collar</td>
       <td>White</td>
-      <td>Female</td>
-      <td>40</td>
+      <td>Male</td>
+      <td>25</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -1626,123 +1636,123 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>43.0</td>
       <td>-</td>
-      <td>Some-college</td>
-      <td>Married</td>
+      <td>Government</td>
+      <td>Prof-school</td>
+      <td>Widowed</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>86.0</td>
+      <td>78.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>33.0</td>
       <td>-</td>
-      <td>Assoc</td>
-      <td>Married</td>
+      <td>-</td>
+      <td>Prof-school</td>
+      <td>-</td>
+      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>49.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>47.0</td>
-      <td>-</td>
-      <td>Masters</td>
       <td>-</td>
       <td>-</td>
+      <td>Some-college</td>
+      <td>Married</td>
+      <td>Other/Unknown</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
+      <td>50.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>47.0</td>
       <td>-</td>
+      <td>Other/Unknown</td>
       <td>-</td>
       <td>Married</td>
+      <td>Professional</td>
       <td>-</td>
-      <td>-</td>
-      <td>-</td>
+      <td>Female</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>34.0</td>
       <td>-</td>
-      <td>Some-college</td>
-      <td>Married</td>
+      <td>Government</td>
+      <td>Doctorate</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
+      <td>82.0</td>
       <td>-</td>
-      <td>1</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>37.0</td>
-      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
+      <td>White-Collar</td>
+      <td>Other</td>
       <td>-</td>
-      <td>Male</td>
-      <td>-</td>
+      <td>84.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>6</th>
-      <td>43.0</td>
       <td>-</td>
-      <td>Some-college</td>
-      <td>Married</td>
+      <td>-</td>
+      <td>Masters</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>51.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>7</th>
-      <td>34.0</td>
       <td>-</td>
-      <td>Some-college</td>
+      <td>Government</td>
+      <td>-</td>
       <td>Married</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>98.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>8</th>
-      <td>38.0</td>
       <td>-</td>
-      <td>Masters</td>
+      <td>Government</td>
+      <td>Prof-school</td>
       <td>-</td>
+      <td>Professional</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>9</th>
-      <td>38.0</td>
-      <td>Government</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Blue-Collar</td>
+      <td>57.0</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
+      <td>72.0</td>
+      <td>1</td>
     </tr>
   </tbody>
 </table>
@@ -1792,11 +1802,11 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>60</td>
-      <td>Private</td>
-      <td>School</td>
+      <td>30</td>
+      <td>Government</td>
+      <td>HS-grad</td>
       <td>Married</td>
-      <td>Sales</td>
+      <td>White-Collar</td>
       <td>White</td>
       <td>Male</td>
       <td>40</td>
@@ -1852,20 +1862,20 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     <tr>
       <th>0</th>
       <td>-</td>
-      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
-      <td>Service</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>-</td>
+      <td>45.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>40.0</td>
-      <td>-</td>
       <td>-</td>
+      <td>Private</td>
+      <td>School</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1875,13 +1885,13 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>2</th>
+      <td>57.0</td>
       <td>-</td>
-      <td>Other/Unknown</td>
       <td>-</td>
-      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
@@ -1890,35 +1900,35 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Widowed</td>
       <td>-</td>
-      <td>Other/Unknown</td>
       <td>-</td>
       <td>-</td>
-      <td>45.0</td>
+      <td>91.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>4</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
-      <td>Separated</td>
-      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>7.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>37.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Divorced</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>-</td>
+      <td>56.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -1926,18 +1936,18 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Single</td>
       <td>-</td>
-      <td>White-Collar</td>
+      <td>Other</td>
       <td>-</td>
-      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
     <tr>
       <th>7</th>
-      <td>24.0</td>
-      <td>-</td>
       <td>-</td>
+      <td>Private</td>
+      <td>Assoc</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1947,14 +1957,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>8</th>
+      <td>29.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Widowed</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>66.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -1962,8 +1972,8 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Single</td>
-      <td>Service</td>
+      <td>Widowed</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -2017,14 +2027,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>51</td>
+      <td>33</td>
       <td>Private</td>
       <td>HS-grad</td>
       <td>Divorced</td>
       <td>Blue-Collar</td>
       <td>White</td>
       <td>Male</td>
-      <td>40</td>
+      <td>45</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -2076,24 +2086,24 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
+      <td>67.0</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Professional</td>
-      <td>-</td>
       <td>-</td>
-      <td>69.0</td>
       <td>-</td>
+      <td>1</td>
     </tr>
     <tr>
       <th>1</th>
+      <td>69.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Married</td>
+      <td>White-Collar</td>
       <td>-</td>
-      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
@@ -2106,29 +2116,29 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>Married</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
-      <td>42.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>3</th>
+      <td>75.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Doctorate</td>
       <td>-</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>71.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>4</th>
+      <td>69.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Assoc</td>
+      <td>Married</td>
       <td>-</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -2136,26 +2146,26 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>5</th>
-      <td>46.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Married</td>
-      <td>-</td>
+      <td>Bachelors</td>
       <td>-</td>
+      <td>Professional</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>6</th>
+      <td>66.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Doctorate</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>77.0</td>
       <td>1</td>
     </tr>
     <tr>
@@ -2163,20 +2173,20 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
       <td>-</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
-      <td>90.0</td>
+      <td>97.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>8</th>
+      <td>77.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
       <td>-</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -2184,14 +2194,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>9</th>
+      <td>90.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Married</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>78.0</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -2242,14 +2252,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>23</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
+      <td>41</td>
+      <td>Government</td>
+      <td>Some-college</td>
+      <td>Divorced</td>
+      <td>Service</td>
       <td>White</td>
       <td>Female</td>
-      <td>38</td>
+      <td>45</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -2301,122 +2311,122 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>80.0</td>
-      <td>Government</td>
-      <td>Bachelors</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
+      <td>Professional</td>
+      <td>-</td>
+      <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>35.0</td>
-      <td>Self-Employed</td>
-      <td>Prof-school</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Married</td>
+      <td>Other/Unknown</td>
+      <td>-</td>
+      <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>46.0</td>
       <td>-</td>
-      <td>Assoc</td>
+      <td>-</td>
+      <td>Doctorate</td>
       <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
-      <td>1</td>
+      <td>-</td>
+      <td>-</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>47.0</td>
       <td>-</td>
-      <td>Prof-school</td>
+      <td>-</td>
+      <td>Bachelors</td>
       <td>Married</td>
-      <td>Sales</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>1</td>
+      <td>-</td>
+      <td>-</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>80.0</td>
-      <td>Government</td>
-      <td>Bachelors</td>
-      <td>Married</td>
+      <td>-</td>
+      <td>Private</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Professional</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>47.0</td>
-      <td>Other/Unknown</td>
-      <td>Prof-school</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
       <td>Married</td>
-      <td>Sales</td>
       <td>-</td>
       <td>-</td>
+      <td>Male</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>6</th>
-      <td>53.0</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
-      <td>White-Collar</td>
       <td>-</td>
+      <td>Prof-school</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Male</td>
       <td>-</td>
       <td>-</td>
-      <td>1</td>
     </tr>
     <tr>
       <th>7</th>
-      <td>71.0</td>
       <td>-</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
       <td>-</td>
-      <td>Male</td>
-      <td>59.0</td>
+      <td>Prof-school</td>
+      <td>-</td>
+      <td>Professional</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>8</th>
       <td>-</td>
-      <td>Self-Employed</td>
-      <td>Doctorate</td>
+      <td>-</td>
+      <td>-</td>
       <td>Married</td>
-      <td>Professional</td>
-      <td>Other</td>
+      <td>Sales</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>9</th>
-      <td>50.0</td>
       <td>-</td>
-      <td>Masters</td>
+      <td>-</td>
+      <td>-</td>
       <td>Married</td>
       <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>46.0</td>
+      <td>-</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -2467,12 +2477,12 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>19</td>
-      <td>Other/Unknown</td>
-      <td>HS-grad</td>
+      <td>20</td>
+      <td>Private</td>
+      <td>Assoc</td>
       <td>Single</td>
-      <td>Other/Unknown</td>
-      <td>Other</td>
+      <td>Sales</td>
+      <td>White</td>
       <td>Female</td>
       <td>40</td>
       <td>0</td>
@@ -2526,122 +2536,122 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
+      <td>70.0</td>
       <td>-</td>
+      <td>Doctorate</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
-      <td>90.0</td>
-      <td>1</td>
+      <td>-</td>
+      <td>69.0</td>
+      <td>-</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>85.0</td>
-      <td>Government</td>
-      <td>Some-college</td>
-      <td>Married</td>
+      <td>75.0</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>White-Collar</td>
       <td>-</td>
-      <td>53.0</td>
+      <td>Male</td>
+      <td>65.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>2</th>
+      <td>68.0</td>
+      <td>-</td>
       <td>-</td>
-      <td>Government</td>
-      <td>Prof-school</td>
       <td>Married</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>84.0</td>
+      <td>-</td>
+      <td>54.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>3</th>
+      <td>65.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Masters</td>
       <td>Married</td>
-      <td>Service</td>
+      <td>Blue-Collar</td>
       <td>-</td>
       <td>Male</td>
-      <td>90.0</td>
       <td>-</td>
+      <td>1</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>54.0</td>
+      <td>83.0</td>
       <td>-</td>
-      <td>Some-college</td>
+      <td>Prof-school</td>
       <td>Married</td>
+      <td>White-Collar</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
-      <td>96.0</td>
       <td>1</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>86.0</td>
+      <td>40.0</td>
+      <td>-</td>
       <td>-</td>
-      <td>School</td>
       <td>Married</td>
-      <td>Professional</td>
-      <td>White</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>48.0</td>
+      <td>1</td>
     </tr>
     <tr>
       <th>6</th>
-      <td>75.0</td>
+      <td>66.0</td>
+      <td>-</td>
       <td>-</td>
-      <td>Some-college</td>
       <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
-      <td>92.0</td>
-      <td>1</td>
+      <td>-</td>
+      <td>67.0</td>
+      <td>-</td>
     </tr>
     <tr>
       <th>7</th>
-      <td>88.0</td>
+      <td>63.0</td>
       <td>-</td>
-      <td>Doctorate</td>
       <td>-</td>
-      <td>Professional</td>
-      <td>White</td>
+      <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>1</td>
+      <td>-</td>
+      <td>79.0</td>
+      <td>-</td>
     </tr>
     <tr>
       <th>8</th>
-      <td>78.0</td>
+      <td>44.0</td>
+      <td>Self-Employed</td>
       <td>-</td>
-      <td>Bachelors</td>
       <td>Married</td>
       <td>-</td>
-      <td>White</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>1</td>
     </tr>
     <tr>
       <th>9</th>
+      <td>45.0</td>
       <td>-</td>
+      <td>Bachelors</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>White</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
+      <td>74.0</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -2692,13 +2702,13 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>28</td>
-      <td>Other/Unknown</td>
+      <td>53</td>
+      <td>Private</td>
       <td>Some-college</td>
       <td>Married</td>
-      <td>Other/Unknown</td>
+      <td>White-Collar</td>
       <td>White</td>
-      <td>Female</td>
+      <td>Male</td>
       <td>40</td>
       <td>1</td>
     </tr>
@@ -2754,47 +2764,47 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>79.0</td>
+      <td>-</td>
+      <td>33.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>1</th>
+      <td>89.0</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Assoc</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
       <td>0</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>65.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Widowed</td>
+      <td>School</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>71.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>3</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
+      <td>Divorced</td>
       <td>-</td>
-      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>8.0</td>
       <td>0</td>
     </tr>
     <tr>
@@ -2803,21 +2813,21 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Blue-Collar</td>
+      <td>Sales</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
-      <td>91.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>5</th>
       <td>-</td>
+      <td>Government</td>
       <td>-</td>
-      <td>School</td>
+      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
       <td>0</td>
     </tr>
@@ -2826,21 +2836,21 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Divorced</td>
       <td>-</td>
+      <td>Blue-Collar</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
-      <td>79.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>7</th>
+      <td>23.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Sales</td>
       <td>-</td>
-      <td>Blue-Collar</td>
-      <td>Other</td>
       <td>-</td>
       <td>-</td>
       <td>0</td>
@@ -2848,25 +2858,25 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     <tr>
       <th>8</th>
       <td>-</td>
+      <td>Government</td>
       <td>-</td>
       <td>-</td>
-      <td>Single</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>7.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>9</th>
+      <td>42.0</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Blue-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>1.0</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -2917,14 +2927,14 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
   <tbody>
     <tr>
       <th>0</th>
-      <td>34</td>
-      <td>Private</td>
+      <td>46</td>
+      <td>Government</td>
       <td>Bachelors</td>
       <td>Married</td>
       <td>Professional</td>
       <td>White</td>
       <td>Male</td>
-      <td>40</td>
+      <td>38</td>
       <td>1</td>
     </tr>
   </tbody>
@@ -2977,69 +2987,69 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     <tr>
       <th>0</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
-      <td>Prof-school</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
       <td>-</td>
-      <td>7.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>1</th>
+      <td>88.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Sales</td>
+      <td>Other</td>
       <td>-</td>
-      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
     <tr>
       <th>2</th>
       <td>-</td>
-      <td>Self-Employed</td>
-      <td>School</td>
       <td>-</td>
       <td>-</td>
+      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>77.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>3</th>
+      <td>36.0</td>
       <td>-</td>
-      <td>Self-Employed</td>
       <td>-</td>
-      <td>Widowed</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>62.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>77.0</td>
+      <td>59.0</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>Service</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>6.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>5</th>
-      <td>68.0</td>
+      <td>59.0</td>
+      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
-      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -3048,13 +3058,13 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
     </tr>
     <tr>
       <th>6</th>
-      <td>38.0</td>
-      <td>Government</td>
       <td>-</td>
       <td>-</td>
+      <td>School</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Female</td>
       <td>-</td>
       <td>0</td>
     </tr>
@@ -3062,36 +3072,36 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
       <th>7</th>
       <td>-</td>
       <td>-</td>
-      <td>Some-college</td>
-      <td>Single</td>
       <td>-</td>
+      <td>Separated</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>63.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>8</th>
-      <td>89.0</td>
+      <td>17.0</td>
+      <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>21.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>9</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
-      <td>Divorced</td>
       <td>-</td>
-      <td>Other</td>
       <td>-</td>
       <td>-</td>
+      <td>7.0</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -3104,8 +3114,8 @@ <h2>Convert the json output to a counterfactual object<a class="headerlink" href
 <div class="output_area docutils container">
 <div class="highlight"><pre>
 [None, None, None, None, None, None, None, None, None, None]
-[{&#39;hours_per_week&#39;: 0.6, &#39;education&#39;: 0.4, &#39;occupation&#39;: 0.4, &#39;age&#39;: 0.2, &#39;race&#39;: 0.2, &#39;workclass&#39;: 0.1, &#39;marital_status&#39;: 0.0, &#39;gender&#39;: 0.0}, {&#39;hours_per_week&#39;: 0.8, &#39;marital_status&#39;: 0.5, &#39;age&#39;: 0.2, &#39;education&#39;: 0.2, &#39;race&#39;: 0.1, &#39;workclass&#39;: 0.0, &#39;occupation&#39;: 0.0, &#39;gender&#39;: 0.0}, {&#39;age&#39;: 1.0, &#39;marital_status&#39;: 0.8, &#39;education&#39;: 0.6, &#39;hours_per_week&#39;: 0.4, &#39;workclass&#39;: 0.3, &#39;occupation&#39;: 0.3, &#39;race&#39;: 0.1, &#39;gender&#39;: 0.0}, {&#39;age&#39;: 1.0, &#39;education&#39;: 0.7, &#39;marital_status&#39;: 0.6, &#39;gender&#39;: 0.3, &#39;occupation&#39;: 0.2, &#39;hours_per_week&#39;: 0.2, &#39;workclass&#39;: 0.1, &#39;race&#39;: 0.0}, {&#39;marital_status&#39;: 0.5, &#39;occupation&#39;: 0.4, &#39;age&#39;: 0.3, &#39;workclass&#39;: 0.2, &#39;education&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;hours_per_week&#39;: 0.1, &#39;race&#39;: 0.0}, {&#39;hours_per_week&#39;: 0.6, &#39;marital_status&#39;: 0.5, &#39;education&#39;: 0.4, &#39;occupation&#39;: 0.3, &#39;age&#39;: 0.1, &#39;race&#39;: 0.1, &#39;workclass&#39;: 0.0, &#39;gender&#39;: 0.0}, {&#39;education&#39;: 1.0, &#39;marital_status&#39;: 1.0, &#39;age&#39;: 0.9, &#39;occupation&#39;: 0.6, &#39;workclass&#39;: 0.5, &#39;gender&#39;: 0.3, &#39;hours_per_week&#39;: 0.2, &#39;race&#39;: 0.1}, {&#39;education&#39;: 1.0, &#39;marital_status&#39;: 0.9, &#39;age&#39;: 0.6, &#39;hours_per_week&#39;: 0.6, &#39;occupation&#39;: 0.5, &#39;race&#39;: 0.4, &#39;gender&#39;: 0.4, &#39;workclass&#39;: 0.2}, {&#39;marital_status&#39;: 0.5, &#39;hours_per_week&#39;: 0.5, &#39;occupation&#39;: 0.4, &#39;education&#39;: 0.2, &#39;gender&#39;: 0.2, &#39;age&#39;: 0.1, &#39;race&#39;: 0.1, &#39;workclass&#39;: 0.0}, {&#39;age&#39;: 0.4, &#39;marital_status&#39;: 0.4, &#39;workclass&#39;: 0.3, &#39;education&#39;: 0.3, &#39;occupation&#39;: 0.2, &#39;hours_per_week&#39;: 0.2, &#39;race&#39;: 0.1, &#39;gender&#39;: 0.1}]
-{&#39;marital_status&#39;: 0.57, &#39;education&#39;: 0.49, &#39;age&#39;: 0.48, &#39;hours_per_week&#39;: 0.42, &#39;occupation&#39;: 0.33, &#39;workclass&#39;: 0.17, &#39;gender&#39;: 0.14, &#39;race&#39;: 0.12}
+[{&#39;marital_status&#39;: 0.7, &#39;age&#39;: 0.5, &#39;education&#39;: 0.3, &#39;hours_per_week&#39;: 0.3, &#39;occupation&#39;: 0.2, &#39;workclass&#39;: 0.0, &#39;race&#39;: 0.0, &#39;gender&#39;: 0.0}, {&#39;hours_per_week&#39;: 0.5, &#39;gender&#39;: 0.4, &#39;age&#39;: 0.3, &#39;marital_status&#39;: 0.3, &#39;education&#39;: 0.2, &#39;race&#39;: 0.1, &#39;workclass&#39;: 0.0, &#39;occupation&#39;: 0.0}, {&#39;age&#39;: 0.9, &#39;education&#39;: 0.8, &#39;workclass&#39;: 0.6, &#39;marital_status&#39;: 0.4, &#39;occupation&#39;: 0.3, &#39;race&#39;: 0.3, &#39;hours_per_week&#39;: 0.3, &#39;gender&#39;: 0.2}, {&#39;hours_per_week&#39;: 0.7, &#39;education&#39;: 0.6, &#39;marital_status&#39;: 0.6, &#39;occupation&#39;: 0.6, &#39;workclass&#39;: 0.5, &#39;gender&#39;: 0.2, &#39;age&#39;: 0.1, &#39;race&#39;: 0.1}, {&#39;hours_per_week&#39;: 0.5, &#39;workclass&#39;: 0.3, &#39;marital_status&#39;: 0.3, &#39;age&#39;: 0.2, &#39;education&#39;: 0.2, &#39;race&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;occupation&#39;: 0.0}, {&#39;age&#39;: 0.7, &#39;marital_status&#39;: 0.5, &#39;occupation&#39;: 0.5, &#39;education&#39;: 0.1, &#39;race&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;hours_per_week&#39;: 0.1, &#39;workclass&#39;: 0.0}, {&#39;marital_status&#39;: 0.7, &#39;occupation&#39;: 0.6, &#39;education&#39;: 0.4, &#39;gender&#39;: 0.2, &#39;workclass&#39;: 0.1, &#39;age&#39;: 0.0, &#39;race&#39;: 0.0, &#39;hours_per_week&#39;: 0.0}, {&#39;age&#39;: 1.0, &#39;marital_status&#39;: 0.7, &#39;hours_per_week&#39;: 0.7, &#39;education&#39;: 0.3, &#39;occupation&#39;: 0.3, &#39;gender&#39;: 0.2, &#39;workclass&#39;: 0.1, &#39;race&#39;: 0.1}, {&#39;age&#39;: 0.3, &#39;workclass&#39;: 0.3, &#39;occupation&#39;: 0.3, &#39;hours_per_week&#39;: 0.3, &#39;marital_status&#39;: 0.2, &#39;gender&#39;: 0.2, &#39;education&#39;: 0.1, &#39;race&#39;: 0.0}, {&#39;age&#39;: 0.5, &#39;hours_per_week&#39;: 0.5, &#39;workclass&#39;: 0.3, &#39;marital_status&#39;: 0.2, &#39;race&#39;: 0.2, &#39;education&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;occupation&#39;: 0.0}]
+{&#39;marital_status&#39;: 0.46, &#39;age&#39;: 0.45, &#39;hours_per_week&#39;: 0.39, &#39;education&#39;: 0.31, &#39;occupation&#39;: 0.28, &#39;workclass&#39;: 0.22, &#39;gender&#39;: 0.17, &#39;race&#39;: 0.1}
 </pre></div></div>
 </div>
 </section>
diff --git a/docs/notebooks/DiCE_getting_started.html b/docs/notebooks/DiCE_getting_started.html
index 12bbf737..38d91292 100644
--- a/docs/notebooks/DiCE_getting_started.html
+++ b/docs/notebooks/DiCE_getting_started.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Quick introduction to generating counterfactual explanations using DiCE &mdash; DiCE 0.8 documentation</title>
+  <title>Quick introduction to generating counterfactual explanations using DiCE &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -63,14 +65,14 @@
 <li class="toctree-l3"><a class="reference internal" href="#Explaining-a-Pytorch-model">Explaining a Pytorch model</a></li>
 </ul>
 </li>
-<li class="toctree-l2"><a class="reference internal" href="#More-resources:-What's-next?">More resources: What’s next?</a></li>
+<li class="toctree-l2"><a class="reference internal" href="#More-resources:-What’s-next?">More resources: What’s next?</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_feature_importances.html">Estimating local and global feature importance scores using DiCE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -320,6 +322,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -328,10 +331,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -343,12 +350,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -376,12 +386,12 @@
 }
 </style>
 <section id="Quick-introduction-to-generating-counterfactual-explanations-using-DiCE">
-<h1>Quick introduction to generating counterfactual explanations using DiCE<a class="headerlink" href="#Quick-introduction-to-generating-counterfactual-explanations-using-DiCE" title="Permalink to this headline"></a></h1>
+<h1>Quick introduction to generating counterfactual explanations using DiCE<a class="headerlink" href="#Quick-introduction-to-generating-counterfactual-explanations-using-DiCE" title="Permalink to this heading"></a></h1>
 <p>Exploring “what-if” scenarios is an important way to inspect a machine learning (ML) model. The DiCE library helps you to understand an ML model by generating “what-if” data points that lead to the desired model output. Formally, such “what-if” data points are known as <em>counterfactuals</em>, described by the following question: &gt; Given that the model’s output for input <span class="math notranslate nohighlight">\(x\)</span> is <span class="math notranslate nohighlight">\(y\)</span>, what would be the output if input <span class="math notranslate nohighlight">\(x\)</span> is changed to <span class="math notranslate nohighlight">\(x'\)</span>?</p>
 <p>The answer to the above question can be obtained by simply inputting <span class="math notranslate nohighlight">\(x'\)</span> to the ML model. However, in many cases, we are interested in the reverse question: what changes to <span class="math notranslate nohighlight">\(x\)</span> would lead to a desired change in model’s output? When inspecting a classifier, for instance, we are often interested in knowing the changes to <span class="math notranslate nohighlight">\(x\)</span> that will lead to a desired predicted class. For a regressor, we may be interested in the changes to <span class="math notranslate nohighlight">\(x\)</span> that lead to a desired output range. Ideally,
 these changes should be <em>proximal</em> to bring out the local decision logic of the classifier, <em>sparse</em> to highlight a limited set of features, and <em>diverse</em> to show the different ways in which the same outcome can be achieved. The DiCE library provides an easy interface to generate such counterfactual examples for any ML model.</p>
 <p>In addition to proximity (minimal changes) and diversity, another important metric for counterfactual examples is their <strong>feasibility</strong>. If the changes in a counterfactual example are not feasible (e.g., outside the possible range of a particular feature), then the example is less useful. Specifying the possible ranges for continuous features (and possible values for categorical features) is one of the simplest forms of feasibility. DiCE allows you to customize the permitted values for features
-through the <code class="docutils literal notranslate"><span class="pre">permitted_range</span></code> parameter. In general, feasibility is a complex concept based on whether the <a class="reference external" href="https://arxiv.org/abs/1912.03277">*changes* indicated by a counterfactual are feasible</a> for the individual, not just that certain values are feasible (e.g., 20 years may be a feasible value for Age feature, but changing a person’s age from 22 to 20 is not feasible). DiCE will support such constraints in a future release.</p>
+through the <code class="docutils literal notranslate"><span class="pre">permitted_range</span></code> parameter. In general, feasibility is a complex concept based on whether the <a class="reference external" href="https://arxiv.org/abs/1912.03277">changes indicated by a counterfactual are feasible</a> for the individual, not just that certain values are feasible (e.g., 20 years may be a feasible value for Age feature, but changing a person’s age from 22 to 20 is not feasible). DiCE will support such constraints in a future release.</p>
 <p>Counterfactual examples generated by DiCE are closely related to <strong>necessity</strong> and <strong>sufficiency</strong> conditions for causing a given model output. Necessity and sufficiency provide an intuitive way to explain a model’s output. Given an input <span class="math notranslate nohighlight">\(x\)</span> and the model output <span class="math notranslate nohighlight">\(y\)</span>, a feature value <span class="math notranslate nohighlight">\(x_i\)</span> is <em>necessary</em> for causing the model output <span class="math notranslate nohighlight">\(y\)</span> if changing <span class="math notranslate nohighlight">\(x_i\)</span> changes the model output, while keeping every other feature constant. Similarly, a feature value <span class="math notranslate nohighlight">\(x_i\)</span> is
 <em>sufficient</em> for causing the model output <span class="math notranslate nohighlight">\(y\)</span> if it is impossible to change the model output while keeping <span class="math notranslate nohighlight">\(x_i\)</span> constant. DiCE allows inspecting necessity and sufficiency by setting the <code class="docutils literal notranslate"><span class="pre">features_to_vary</span></code> parameter. If <code class="docutils literal notranslate"><span class="pre">features_to_vary</span></code> is set to <span class="math notranslate nohighlight">\(x_i\)</span>, then the generated counterfactuals demonstrate the necessity of the feature. If <code class="docutils literal notranslate"><span class="pre">features_to_vary</span></code> is set to all features except <span class="math notranslate nohighlight">\(x_i\)</span>, then the absence of any counterfactuals demonstrates the sufficiency of the
 feature. In practice, a single feature may be neither sufficient nor necessary—the formal definitions and the <code class="docutils literal notranslate"><span class="pre">features_to_vary</span></code> parameter translate easily to sets of features.</p>
@@ -400,7 +410,7 @@ <h1>Quick introduction to generating counterfactual explanations using DiCE<a cl
 </ul>
 <p><img alt="DiCE API" src="../_images/dice_getting_started_api.png" /></p>
 <p>DiCE requires two inputs: a training dataset and a pre-trained ML model. When the training dataset is unknown (e.g., for privacy reasons), it can also work without access to the full dataset (see this <a class="reference internal" href="DiCE_with_private_data.html"><span class="doc">notebook</span></a> for an example). Below we show a simple example.</p>
-<div class="nbinput docutils container">
+<div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
 </pre></div>
 </div>
@@ -411,25 +421,12 @@ <h1>Quick introduction to generating counterfactual explanations using DiCE<a cl
 <span class="kn">from</span> <span class="nn">sklearn.preprocessing</span> <span class="kn">import</span> <span class="n">OneHotEncoder</span>
 <span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <span class="n">RandomForestClassifier</span>
 
-<span class="c1"># Tensorflow import</span>
-<span class="kn">import</span> <span class="nn">tensorflow</span> <span class="k">as</span> <span class="nn">tf</span>
-
-
 <span class="c1"># DiCE imports</span>
 <span class="kn">import</span> <span class="nn">dice_ml</span>
 <span class="kn">from</span> <span class="nn">dice_ml.utils</span> <span class="kn">import</span> <span class="n">helpers</span>  <span class="c1"># helper functions</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-2022-05-29 12:05:01.466381: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
-2022-05-29 12:05:01.466596: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
-</pre></div></div>
-</div>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[2]:
 </pre></div>
@@ -440,9 +437,9 @@ <h1>Quick introduction to generating counterfactual explanations using DiCE<a cl
 </div>
 </div>
 <section id="Preliminaries:-Loading-a-dataset-and-a-ML-model-trained-over-it">
-<h2>Preliminaries: Loading a dataset and a ML model trained over it<a class="headerlink" href="#Preliminaries:-Loading-a-dataset-and-a-ML-model-trained-over-it" title="Permalink to this headline"></a></h2>
+<h2>Preliminaries: Loading a dataset and a ML model trained over it<a class="headerlink" href="#Preliminaries:-Loading-a-dataset-and-a-ML-model-trained-over-it" title="Permalink to this heading"></a></h2>
 <section id="Loading-the-Adult-dataset">
-<h3>Loading the <code class="docutils literal notranslate"><span class="pre">Adult</span></code> dataset<a class="headerlink" href="#Loading-the-Adult-dataset" title="Permalink to this headline"></a></h3>
+<h3>Loading the <code class="docutils literal notranslate"><span class="pre">Adult</span></code> dataset<a class="headerlink" href="#Loading-the-Adult-dataset" title="Permalink to this heading"></a></h3>
 <p>We use the “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>). For demonstration purposes, we transform the data as described in <strong>dice_ml.utils.helpers</strong> module.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
@@ -615,9 +612,9 @@ <h3>Loading the <code class="docutils literal notranslate"><span class="pre">Adu
 </div>
 </section>
 <section id="Loading-the-ML-model">
-<h3>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title="Permalink to this headline"></a></h3>
+<h3>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title="Permalink to this heading"></a></h3>
 <p>DiCE supports sklearn, tensorflow and pytorch models.</p>
-<p>The variable <em>backend</em> below indicates the implementation type of DiCE we want to use. Four backends are supported: sklearn, TensorFlow 1.x with backend=’TF1’, Tensorflow 2.x with backend=’TF2’, and PyTorch with backend=’PYT’.</p>
+<p>The variable <em>backend</em> below indicates the implementation type of DiCE we want to use. Four backends are supported: sklearn, TensorFlow 1.x with backend=‘TF1’, Tensorflow 2.x with backend=‘TF2’, and PyTorch with backend=‘PYT’.</p>
 <p>Below we show use a trained classification model using sklearn.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[8]:
@@ -644,7 +641,7 @@ <h3>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title
 </section>
 </section>
 <section id="Generating-counterfactual-examples-using-DiCE">
-<h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Generating-counterfactual-examples-using-DiCE" title="Permalink to this headline"></a></h2>
+<h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Generating-counterfactual-examples-using-DiCE" title="Permalink to this heading"></a></h2>
 <p>We now initialize the DiCE explainer, which needs a dataset and a model. DiCE provides local explanation for the model <em>m</em> and requires an query input whose outcome needs to be explained.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[9]:
@@ -674,7 +671,7 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  5.33it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  9.38it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -789,10 +786,10 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
     <tr>
       <th>0</th>
       <td>-</td>
+      <td>Government</td>
+      <td>Assoc</td>
       <td>-</td>
-      <td>School</td>
       <td>-</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -801,10 +798,10 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
     <tr>
       <th>1</th>
       <td>-</td>
-      <td>Government</td>
-      <td>Assoc</td>
+      <td>Self-Employed</td>
       <td>-</td>
       <td>-</td>
+      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -927,10 +924,10 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
     <tr>
       <th>0</th>
       <td>29</td>
-      <td>Private</td>
-      <td>School</td>
+      <td>Government</td>
+      <td>Assoc</td>
       <td>Married</td>
-      <td>Professional</td>
+      <td>Blue-Collar</td>
       <td>White</td>
       <td>Female</td>
       <td>38</td>
@@ -939,10 +936,10 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
     <tr>
       <th>1</th>
       <td>29</td>
-      <td>Government</td>
-      <td>Assoc</td>
+      <td>Self-Employed</td>
+      <td>HS-grad</td>
       <td>Married</td>
-      <td>Blue-Collar</td>
+      <td>White-Collar</td>
       <td>White</td>
       <td>Female</td>
       <td>38</td>
@@ -972,7 +969,7 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  5.34it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00, 10.58it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1088,9 +1085,9 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
       <th>0</th>
       <td>-</td>
       <td>-</td>
-      <td>Prof-school</td>
+      <td>Masters</td>
       <td>-</td>
-      <td>White-Collar</td>
+      <td>Sales</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1100,7 +1097,7 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
       <th>1</th>
       <td>-</td>
       <td>-</td>
-      <td>Bachelors</td>
+      <td>Prof-school</td>
       <td>-</td>
       <td>Professional</td>
       <td>-</td>
@@ -1130,7 +1127,7 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  5.09it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  9.72it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1245,12 +1242,12 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
     <tr>
       <th>0</th>
       <td>-</td>
+      <td>Self-Employed</td>
       <td>-</td>
-      <td>Prof-school</td>
       <td>-</td>
+      <td>Professional</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
       <td>1</td>
     </tr>
@@ -1259,8 +1256,8 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
       <td>-</td>
       <td>Government</td>
       <td>-</td>
+      <td>Single</td>
       <td>-</td>
-      <td>Professional</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1272,11 +1269,11 @@ <h2>Generating counterfactual examples using DiCE<a class="headerlink" href="#Ge
 </div>
 </section>
 <section id="Generating-feature-attributions-(local-and-global)-using-DiCE">
-<h2>Generating feature attributions (local and global) using DiCE<a class="headerlink" href="#Generating-feature-attributions-(local-and-global)-using-DiCE" title="Permalink to this headline"></a></h2>
+<h2>Generating feature attributions (local and global) using DiCE<a class="headerlink" href="#Generating-feature-attributions-(local-and-global)-using-DiCE" title="Permalink to this heading"></a></h2>
 <p>DiCE can generate feature importance scores using a summary of the counterfactuals generated. Intuitively, a feature that is changed more often when generating proximal counterfactuals for an input is locally important for causing the model’s prediction at the input. Formally, counterfactuals operationalize the <strong>necessity</strong> criterion for a model explanation: <em>is the feature value necessary for the given model output?</em></p>
 <p>For more details, refer to the paper, <a class="reference external" href="https://arxiv.org/abs/2011.04917">Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End</a>.</p>
 <section id="Local-feature-importance-scores">
-<h3>Local feature importance scores<a class="headerlink" href="#Local-feature-importance-scores" title="Permalink to this headline"></a></h3>
+<h3>Local feature importance scores<a class="headerlink" href="#Local-feature-importance-scores" title="Permalink to this heading"></a></h3>
 <p>These scores are computed for a given query instance (input point) by summarizing a set of counterfactual examples around the point.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[14]:
@@ -1293,7 +1290,7 @@ <h3>Local feature importance scores<a class="headerlink" href="#Local-feature-im
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  2.55it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  5.12it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1301,7 +1298,7 @@ <h3>Local feature importance scores<a class="headerlink" href="#Local-feature-im
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-[{&#39;occupation&#39;: 0.8, &#39;education&#39;: 0.7, &#39;workclass&#39;: 0.3, &#39;marital_status&#39;: 0.1, &#39;gender&#39;: 0.1, &#39;race&#39;: 0.0, &#39;age&#39;: 0.0, &#39;hours_per_week&#39;: 0.0}]
+[{&#39;education&#39;: 0.8, &#39;occupation&#39;: 0.6, &#39;workclass&#39;: 0.3, &#39;gender&#39;: 0.2, &#39;marital_status&#39;: 0.1, &#39;race&#39;: 0.0, &#39;age&#39;: 0.0, &#39;hours_per_week&#39;: 0.0}]
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -1315,7 +1312,7 @@ <h3>Local feature importance scores<a class="headerlink" href="#Local-feature-im
 <p>The <code class="docutils literal notranslate"><span class="pre">total_CFs</span></code> parameter denotes the number of counterfactuals that are used to create the local importance. More the better.</p>
 </section>
 <section id="Global-feature-importance-scores">
-<h3>Global feature importance scores<a class="headerlink" href="#Global-feature-importance-scores" title="Permalink to this headline"></a></h3>
+<h3>Global feature importance scores<a class="headerlink" href="#Global-feature-importance-scores" title="Permalink to this heading"></a></h3>
 <p>A global importance score per feature can be estimated by aggregating the scores over individual inputs. The more the inputs, the better the estimate for global importance of a feature.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[15]:
@@ -1332,7 +1329,7 @@ <h3>Global feature importance scores<a class="headerlink" href="#Global-feature-
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|█████████████████████████████████████████████████████████████████| 20/20 [00:08&lt;00:00,  2.39it/s]
+100%|███████████████████████████████████████████████████████████████████████████████| 20/20 [00:04&lt;00:00,  4.83it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1340,7 +1337,7 @@ <h3>Global feature importance scores<a class="headerlink" href="#Global-feature-
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-{&#39;education&#39;: 0.64, &#39;occupation&#39;: 0.31, &#39;marital_status&#39;: 0.295, &#39;age&#39;: 0.23, &#39;hours_per_week&#39;: 0.2, &#39;workclass&#39;: 0.155, &#39;race&#39;: 0.155, &#39;gender&#39;: 0.11}
+{&#39;education&#39;: 0.68, &#39;occupation&#39;: 0.32, &#39;marital_status&#39;: 0.275, &#39;hours_per_week&#39;: 0.235, &#39;workclass&#39;: 0.2, &#39;age&#39;: 0.175, &#39;race&#39;: 0.155, &#39;gender&#39;: 0.09}
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -1354,34 +1351,20 @@ <h3>Global feature importance scores<a class="headerlink" href="#Global-feature-
 </section>
 </section>
 <section id="Working-with-deep-learning-models-(TensorFlow-and-PyTorch)">
-<h2>Working with deep learning models (TensorFlow and PyTorch)<a class="headerlink" href="#Working-with-deep-learning-models-(TensorFlow-and-PyTorch)" title="Permalink to this headline"></a></h2>
+<h2>Working with deep learning models (TensorFlow and PyTorch)<a class="headerlink" href="#Working-with-deep-learning-models-(TensorFlow-and-PyTorch)" title="Permalink to this heading"></a></h2>
 <p>We now show examples of gradient-based methods with Tensorflow and Pytorch models. Since the gradient-based methods <em>optimize</em> the loss rather than simply sampling some points, they can be slower to generate counterfactuals. The loss is defined by three component: <strong>validity</strong> (does the CF have the desired model output), <strong>proximity</strong> (distance of CF from original point should be low), and <strong>diversity</strong> (multiple CFs should change different features). The DiCE loss formulation is described in
 the paper, <a class="reference external" href="https://arxiv.org/abs/1905.07697">Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations</a>.</p>
 <p>Below, we use a pre-trained ML model which produces high accuracy comparable to other baselines. For convenience, we include the sample trained model with the DiCE package.</p>
 <section id="Explaining-a-Tensorflow-model">
-<h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tensorflow-model" title="Permalink to this headline"></a></h3>
-<div class="nbinput nblast docutils container">
+<h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tensorflow-model" title="Permalink to this heading"></a></h3>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[16]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># supress deprecation warnings from TF</span>
-<span class="n">tf</span><span class="o">.</span><span class="n">compat</span><span class="o">.</span><span class="n">v1</span><span class="o">.</span><span class="n">logging</span><span class="o">.</span><span class="n">set_verbosity</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">compat</span><span class="o">.</span><span class="n">v1</span><span class="o">.</span><span class="n">logging</span><span class="o">.</span><span class="n">ERROR</span><span class="p">)</span>
-
-<span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;TF&#39;</span><span class="o">+</span><span class="n">tf</span><span class="o">.</span><span class="n">__version__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>  <span class="c1"># TF1</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;TF2&#39;</span>  <span class="c1"># needs tensorflow installed</span>
 <span class="n">ML_modelpath</span> <span class="o">=</span> <span class="n">helpers</span><span class="o">.</span><span class="n">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
 <span class="c1"># Step 2: dice_ml.Model</span>
-<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-<p>We want to note that the time required to find counterfactuals with Tensorflow 2.x’s eager style of execution is significantly greater than that with TensorFlow 1.x’s graph execution.</p>
-<p>Based on the data object <em>d</em> and the model object <em>m</em>, we can now instantiate the DiCE class for generating explanations.</p>
-<div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[17]:
-</pre></div>
-</div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Step 3: initiate DiCE</span>
-<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">)</span>
+<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">,</span> <span class="n">func</span><span class="o">=</span><span class="s2">&quot;ohe-min-max&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
@@ -1390,52 +1373,42 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-2022-05-29 12:05:47.342795: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
-2022-05-29 12:05:47.345915: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
-2022-05-29 12:05:47.346592: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-Z840): /proc/driver/nvidia/version does not exist
-2022-05-29 12:05:47.353536: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
-To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2022-10-19 14:51:46.694158: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
+2022-10-19 14:51:46.698027: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
+2022-10-19 14:51:46.698044: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
 </pre></div></div>
 </div>
-<p>Below we provide query instance as a dict.</p>
-<div class="nbinput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[18]:
-</pre></div>
-</div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># query instance in the form of a dictionary or a dataframe; keys: feature name, values: feature value</span>
-<span class="n">query_instance</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">22</span><span class="p">,</span>
-                  <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="s1">&#39;White&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="s1">&#39;Female&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="mi">45</span><span class="p">}</span>
-</pre></div>
-</div>
-</div>
+<p>We want to note that the time required to find counterfactuals with Tensorflow 2.x’s eager style of execution is significantly greater than that with TensorFlow 1.x’s graph execution.</p>
+<p>Based on the data object <em>d</em> and the model object <em>m</em>, we can now instantiate the DiCE class for generating explanations.</p>
 <div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[19]:
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[17]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
-<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Step 3: initiate DiCE</span>
+<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;gradient&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area docutils container">
+<div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 44 sec
+2022-10-19 14:51:49.357741: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
+2022-10-19 14:51:49.357797: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
+2022-10-19 14:51:49.357820: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-X1): /proc/driver/nvidia/version does not exist
+2022-10-19 14:51:49.358100: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
 </pre></div></div>
 </div>
+<p>Below we provide query instances from <code class="docutils literal notranslate"><span class="pre">x_test</span></code>.</p>
 <div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[20]:
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[18]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># visualize the result, highlight only the changes</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
+<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">x_test</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">2</span><span class="p">],</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="c1"># visualize the result, highlight only the changes</span>
 <span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
@@ -1445,7 +1418,8 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Query instance (original outcome : 0)
+Diverse Counterfactuals found! total time taken: 00 min 34 sec
+Query instance (original outcome : 1)
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1484,15 +1458,15 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
   <tbody>
     <tr>
       <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
+      <td>50.0</td>
+      <td>Other/Unknown</td>
+      <td>Some-college</td>
+      <td>Married</td>
+      <td>Other/Unknown</td>
       <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.019</td>
+      <td>Male</td>
+      <td>40.0</td>
+      <td>0.671</td>
     </tr>
   </tbody>
 </table>
@@ -1504,7 +1478,7 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
 <div class="output_area docutils container">
 <div class="highlight"><pre>
 
-Diverse Counterfactual set (new outcome: 1.0)
+Diverse Counterfactual set (new outcome: 0.0)
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -1543,34 +1517,34 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
   <tbody>
     <tr>
       <th>0</th>
-      <td>70.0</td>
+      <td>23.0</td>
       <td>-</td>
-      <td>Masters</td>
       <td>-</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
-      <td>51.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>13.0</td>
       <td>0</td>
     </tr>
     <tr>
       <th>1</th>
+      <td>17.0</td>
       <td>-</td>
-      <td>Self-Employed</td>
-      <td>Doctorate</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>Other</td>
+      <td>-</td>
       <td>-</td>
       <td>0</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>47.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Married</td>
+      <td>School</td>
+      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
@@ -1579,14 +1553,14 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
     </tr>
     <tr>
       <th>3</th>
-      <td>36.0</td>
+      <td>62.0</td>
       <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
+      <td>-</td>
+      <td>Divorced</td>
+      <td>Blue-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
-      <td>62.0</td>
       <td>0</td>
     </tr>
   </tbody>
@@ -1597,75 +1571,77 @@ <h3>Explaining a Tensorflow model<a class="headerlink" href="#Explaining-a-Tenso
 <a class="reference external" href="https://github.com/interpretml/DiCE/blob/master/dice_ml/dice_interfaces/dice_tensorflow1.py">dice_ml.dice_interfaces.dice_tensorflow.py</a>.</p>
 </section>
 <section id="Explaining-a-Pytorch-model">
-<h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-model" title="Permalink to this headline"></a></h3>
-<p>Just change the backend variable to ‘PYT’ to use DiCE with PyTorch. Below, we use a pre-trained ML model in PyTorch which produces high accuracy comparable to other baselines. For convenience, we include the sample trained model with the DiCE package.</p>
+<h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-model" title="Permalink to this heading"></a></h3>
+<p>Just change the backend variable to ‘PYT’ to use DiCE with PyTorch. Below, we use a pre-trained ML model in PyTorch which produces high accuracy comparable to other baselines. For convenience, we include the sample trained model with the DiCE package. Additionally, we need to provide a data transformer function that converts input dataframe into one-hot encoded/numeric format.</p>
 <div class="nbinput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[21]:
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[19]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;PYT&#39;</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;PYT&#39;</span>  <span class="c1"># needs pytorch installed</span>
 <span class="n">ML_modelpath</span> <span class="o">=</span> <span class="n">helpers</span><span class="o">.</span><span class="n">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
-<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
+<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">,</span>  <span class="n">func</span><span class="o">=</span><span class="s2">&quot;ohe-min-max&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
 <p>Instantiate the DiCE class with the new PyTorch model object <em>m</em>.</p>
 <div class="nbinput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[22]:
-</pre></div>
-</div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-<div class="nbinput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[23]:
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[20]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># query instance in the form of a dictionary; keys: feature name, values: feature value</span>
-<span class="n">query_instance</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">22</span><span class="p">,</span>
-                  <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="s1">&#39;White&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="s1">&#39;Female&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="mi">45</span><span class="p">}</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;gradient&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
 <div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[24]:
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[21]:
 </pre></div>
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
-<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">x_test</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">],</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="c1"># highlight only the changes</span>
+<span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput nblast docutils container">
+<div class="nboutput docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area docutils container">
+<div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 08 sec
+ 50%|████████████████████████████████████████▌                                        | 1/2 [00:03&lt;00:03,  3.37s/it]
 </pre></div></div>
 </div>
-<div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[25]:
-</pre></div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># highlight only the changes</span>
-<span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-</pre></div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+Diverse Counterfactuals found! total time taken: 00 min 03 sec
+</pre></div></div>
 </div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+100%|█████████████████████████████████████████████████████████████████████████████████| 2/2 [00:07&lt;00:00,  3.69s/it]
+</pre></div></div>
 </div>
 <div class="nboutput docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Query instance (original outcome : 0)
+Diverse Counterfactuals found! total time taken: 00 min 03 sec
+Query instance (original outcome : 1)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1704,15 +1680,15 @@ <h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-
   <tbody>
     <tr>
       <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
+      <td>50.0</td>
+      <td>Other/Unknown</td>
+      <td>Some-college</td>
+      <td>Married</td>
+      <td>Other/Unknown</td>
       <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.0</td>
+      <td>Male</td>
+      <td>40.0</td>
+      <td>0.618</td>
     </tr>
   </tbody>
 </table>
@@ -1724,10 +1700,10 @@ <h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-
 <div class="output_area docutils container">
 <div class="highlight"><pre>
 
-Diverse Counterfactual set (new outcome: 1.0)
+Diverse Counterfactual set (new outcome: 0.0)
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
+<div class="nboutput docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area rendered_html docutils container">
@@ -1763,51 +1739,547 @@ <h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-
   <tbody>
     <tr>
       <th>0</th>
-      <td>72.0</td>
+      <td>38.0</td>
       <td>-</td>
       <td>-</td>
-      <td>Married</td>
-      <td>White-Collar</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>26.0</td>
+      <td>0</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>29.0</td>
       <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
       <td>-</td>
       <td>-</td>
-      <td>Male</td>
       <td>-</td>
+      <td>Blue-Collar</td>
+      <td>-</td>
+      <td>Female</td>
       <td>-</td>
+      <td>0</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>52.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
       <td>-</td>
+      <td>Government</td>
+      <td>School</td>
+      <td>Single</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
       <td>-</td>
+      <td>0</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>47.0</td>
+      <td>70.0</td>
       <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
       <td>-</td>
+      <td>Divorced</td>
       <td>-</td>
+      <td>Other</td>
       <td>-</td>
-      <td>73.0</td>
       <td>-</td>
+      <td>0</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+Query instance (original outcome : 1)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>50.0</td>
+      <td>Private</td>
+      <td>Bachelors</td>
+      <td>Married</td>
+      <td>Professional</td>
+      <td>White</td>
+      <td>Male</td>
+      <td>40.0</td>
+      <td>0.968</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+
+Diverse Counterfactual set (new outcome: 0.0)
+</pre></div></div>
+</div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>18.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>35.0</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>1</th>
+      <td>-</td>
+      <td>-</td>
+      <td>Some-college</td>
+      <td>Separated</td>
+      <td>Service</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>2</th>
+      <td>69.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Single</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>3</th>
+      <td>-</td>
+      <td>Other/Unknown</td>
+      <td>School</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Female</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<p>We can also use method-agnostic explainers like “random” or “genetic”.</p>
+<div class="nbinput nblast docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[22]:
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">,</span> <span class="n">func</span><span class="o">=</span><span class="s2">&quot;ohe-min-max&quot;</span><span class="p">)</span>
+<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;random&quot;</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+<div class="nbinput docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[23]:
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
+<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">x_test</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="mi">3</span><span class="p">],</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="c1"># highlight only the changes</span>
+<span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+100%|█████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  4.35it/s]
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+Query instance (original outcome : 1)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>50</td>
+      <td>Other/Unknown</td>
+      <td>Some-college</td>
+      <td>Married</td>
+      <td>Other/Unknown</td>
+      <td>White</td>
+      <td>Male</td>
+      <td>40</td>
+      <td>1</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+
+Diverse Counterfactual set (new outcome: 0.0)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>63.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Female</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>1</th>
+      <td>19.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Single</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>2</th>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Female</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>3</th>
+      <td>65.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Blue-Collar</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+Query instance (original outcome : 1)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>50</td>
+      <td>Private</td>
+      <td>Bachelors</td>
+      <td>Married</td>
+      <td>Professional</td>
+      <td>White</td>
+      <td>Male</td>
+      <td>40</td>
+      <td>1</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+
+Diverse Counterfactual set (new outcome: 0.0)
+</pre></div></div>
+</div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>17.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Divorced</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>1</th>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Separated</td>
+      <td>Sales</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>2</th>
+      <td>65.0</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Separated</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0</td>
+    </tr>
+    <tr>
+      <th>3</th>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>Separated</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>18.0</td>
+      <td>0</td>
     </tr>
   </tbody>
 </table>
@@ -1815,8 +2287,8 @@ <h3>Explaining a Pytorch model<a class="headerlink" href="#Explaining-a-Pytorch-
 </div>
 </section>
 </section>
-<section id="More-resources:-What's-next?">
-<h2>More resources: What’s next?<a class="headerlink" href="#More-resources:-What's-next?" title="Permalink to this headline"></a></h2>
+<section id="More-resources:-What’s-next?">
+<h2>More resources: What’s next?<a class="headerlink" href="#More-resources:-What’s-next?" title="Permalink to this heading"></a></h2>
 <p>DiCE has multiple configurable options and support for different kinds of models. Follow these notebooks to learn more.</p>
 <ol class="arabic simple">
 <li><p>You can constrain the features to vary, weigh the relative importance of different features for computing distance, or specify permitted ranges for each feature. Check out the <a class="reference internal" href="DiCE_with_advanced_options.html"><span class="doc">Customizing Counterfactuals Notebook</span></a>.</p></li>
diff --git a/docs/notebooks/DiCE_getting_started_feasible.html b/docs/notebooks/DiCE_getting_started_feasible.html
index 01f3614b..d06a51bc 100644
--- a/docs/notebooks/DiCE_getting_started_feasible.html
+++ b/docs/notebooks/DiCE_getting_started_feasible.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Generate feasible counterfactual explanations using a VAE &mdash; DiCE 0.8 documentation</title>
+  <title>Generate feasible counterfactual explanations using a VAE &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -51,7 +53,7 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1 current"><a class="current reference internal" href="#">Generate feasible counterfactual explanations using a VAE</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="#Loading-dataset">Loading dataset</a></li>
@@ -310,6 +312,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -318,10 +321,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -333,12 +340,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -366,7 +376,7 @@
 }
 </style>
 <section id="Generate-feasible-counterfactual-explanations-using-a-VAE">
-<h1>Generate feasible counterfactual explanations using a VAE<a class="headerlink" href="#Generate-feasible-counterfactual-explanations-using-a-VAE" title="Permalink to this headline"></a></h1>
+<h1>Generate feasible counterfactual explanations using a VAE<a class="headerlink" href="#Generate-feasible-counterfactual-explanations-using-a-VAE" title="Permalink to this heading"></a></h1>
 <p>This presents the variational inference based approach for generating feasible counterfactuals, where we first train an encoder-decoder framework to generate counterfactuals. More details about our framework can be found here: <a class="reference external" href="https://arxiv.org/abs/1912.03277">https://arxiv.org/abs/1912.03277</a></p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
@@ -383,9 +393,9 @@ <h1>Generate feasible counterfactual explanations using a VAE<a class="headerlin
 </div>
 <p>DiCE requires two inputs: a training dataset and a pre-trained ML model. It can also work without access to the full dataset (see this <a class="reference internal" href="DiCE_with_private_data.html"><span class="doc">notebook</span></a> for advanced examples).</p>
 <section id="Loading-dataset">
-<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this headline"></a></h2>
+<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this heading"></a></h2>
 <p>We use the “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>). For demonstration purposes, we transform the data as described in <strong>dice_ml.utils.helpers</strong> module.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[2]:
 </pre></div>
 </div>
@@ -393,6 +403,134 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">RemoteDisconnected</span>                        Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [2]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> dataset <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">helpers</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">load_adult_income_dataset</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/utils/helpers.py:25</span>, in <span class="ansi-cyan-fg">load_adult_income_dataset</span><span class="ansi-blue-fg">(only_train)</span>
+<span class="ansi-green-intense-fg ansi-bold">     19</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">load_adult_income_dataset</span>(only_train<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>):
+<span class="ansi-green-intense-fg ansi-bold">     20</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Loads adult income dataset from https://archive.ics.uci.edu/ml/datasets/Adult and prepares</span>
+<span class="ansi-green-intense-fg ansi-bold">     21</span> <span style="color: rgb(175,0,0)">       the data for data analysis based on https://rpubs.com/H_Zhu/235617</span>
+<span class="ansi-green-intense-fg ansi-bold">     22</span>
+<span class="ansi-green-intense-fg ansi-bold">     23</span> <span style="color: rgb(175,0,0)">    :return adult_data: returns preprocessed adult income dataset.</span>
+<span class="ansi-green-intense-fg ansi-bold">     24</span> <span style="color: rgb(175,0,0)">    &#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 25</span>     raw_data <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">genfromtxt</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">     26</span> <span class="ansi-yellow-bg">                             </span><span class="ansi-yellow-bg">delimiter</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">, </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">dtype</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">str</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">invalid_raise</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg ansi-bold" style="color: rgb(0,135,0)">False</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span>     <span style="color: rgb(95,135,135)">#  column names from &#34;https://archive.ics.uci.edu/ml/datasets/Adult&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     column_names <span style="color: rgb(98,98,98)">=</span> [<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">fnlwgt</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">educational-num</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">marital-status</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     30</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">relationship</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">race</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">gender</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-gain</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-loss</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours-per-week</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">native-country</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>]
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/npyio.py:1934</span>, in <span class="ansi-cyan-fg">genfromtxt</span><span class="ansi-blue-fg">(fname, dtype, comments, delimiter, skip_header, skip_footer, converters, missing_values, filling_values, usecols, names, excludelist, deletechars, replace_space, autostrip, case_sensitive, defaultfmt, unpack, usemask, loose, invalid_raise, max_rows, encoding, ndmin, like)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1932</span>     fname <span style="color: rgb(98,98,98)">=</span> os_fspath(fname)
+<span class="ansi-green-intense-fg ansi-bold">   1933</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span style="color: rgb(0,135,0)">isinstance</span>(fname, <span style="color: rgb(0,135,0)">str</span>):
+<span class="ansi-green-fg">-&gt; 1934</span>     fid <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">lib</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_datasource</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">fname</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">rt</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1935</span>     fid_ctx <span style="color: rgb(98,98,98)">=</span> contextlib<span style="color: rgb(98,98,98)">.</span>closing(fid)
+<span class="ansi-green-intense-fg ansi-bold">   1936</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:193</span>, in <span class="ansi-cyan-fg">open</span><span class="ansi-blue-fg">(path, mode, destpath, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    156</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    157</span> <span style="color: rgb(175,0,0)">Open `path` with `mode` and return the file object.</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    189</span>
+<span class="ansi-green-intense-fg ansi-bold">    190</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    192</span> ds <span style="color: rgb(98,98,98)">=</span> DataSource(destpath)
+<span class="ansi-green-fg">--&gt; 193</span> <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> <span class="ansi-yellow-bg">ds</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">path</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">mode</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:525</span>, in <span class="ansi-cyan-fg">DataSource.open</span><span class="ansi-blue-fg">(self, path, mode, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    522</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">raise</span> <span class="ansi-bold" style="color: rgb(215,95,95)">ValueError</span>(<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">URLs are not writeable</span><span style="color: rgb(175,0,0)">&#34;</span>)
+<span class="ansi-green-intense-fg ansi-bold">    524</span> <span style="color: rgb(95,135,135)"># NOTE: _findfile will fail on a new file opened for writing.</span>
+<span class="ansi-green-fg">--&gt; 525</span> found <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_findfile</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">path</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    526</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> found:
+<span class="ansi-green-intense-fg ansi-bold">    527</span>     _fname, ext <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_splitzipext(found)
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:369</span>, in <span class="ansi-cyan-fg">DataSource._findfile</span><span class="ansi-blue-fg">(self, path)</span>
+<span class="ansi-green-intense-fg ansi-bold">    366</span>     filelist <span style="color: rgb(98,98,98)">=</span> filelist <span style="color: rgb(98,98,98)">+</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_possible_names(path)
+<span class="ansi-green-intense-fg ansi-bold">    368</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> filelist:
+<span class="ansi-green-fg">--&gt; 369</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">exists</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">name</span><span class="ansi-yellow-bg">)</span>:
+<span class="ansi-green-intense-fg ansi-bold">    370</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_isurl(name):
+<span class="ansi-green-intense-fg ansi-bold">    371</span>             name <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_cache(name)
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:479</span>, in <span class="ansi-cyan-fg">DataSource.exists</span><span class="ansi-blue-fg">(self, path)</span>
+<span class="ansi-green-intense-fg ansi-bold">    477</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_isurl(path):
+<span class="ansi-green-intense-fg ansi-bold">    478</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">try</span>:
+<span class="ansi-green-fg">--&gt; 479</span>         netfile <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">urlopen</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">path</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    480</span>         netfile<span style="color: rgb(98,98,98)">.</span>close()
+<span class="ansi-green-intense-fg ansi-bold">    481</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">del</span>(netfile)
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:222</span>, in <span class="ansi-cyan-fg">urlopen</span><span class="ansi-blue-fg">(url, data, timeout, cafile, capath, cadefault, context)</span>
+<span class="ansi-green-intense-fg ansi-bold">    220</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+<span class="ansi-green-intense-fg ansi-bold">    221</span>     opener <span style="color: rgb(98,98,98)">=</span> _opener
+<span class="ansi-green-fg">--&gt; 222</span> <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> <span class="ansi-yellow-bg">opener</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">url</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">data</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">timeout</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:525</span>, in <span class="ansi-cyan-fg">OpenerDirector.open</span><span class="ansi-blue-fg">(self, fullurl, data, timeout)</span>
+<span class="ansi-green-intense-fg ansi-bold">    522</span>     req <span style="color: rgb(98,98,98)">=</span> meth(req)
+<span class="ansi-green-intense-fg ansi-bold">    524</span> sys<span style="color: rgb(98,98,98)">.</span>audit(<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">urllib.Request</span><span style="color: rgb(175,0,0)">&#39;</span>, req<span style="color: rgb(98,98,98)">.</span>full_url, req<span style="color: rgb(98,98,98)">.</span>data, req<span style="color: rgb(98,98,98)">.</span>headers, req<span style="color: rgb(98,98,98)">.</span>get_method())
+<span class="ansi-green-fg">--&gt; 525</span> response <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">req</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">data</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    527</span> <span style="color: rgb(95,135,135)"># post-process response</span>
+<span class="ansi-green-intense-fg ansi-bold">    528</span> meth_name <span style="color: rgb(98,98,98)">=</span> protocol<span style="color: rgb(98,98,98)">+</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">_response</span><span style="color: rgb(175,0,0)">&#34;</span>
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:542</span>, in <span class="ansi-cyan-fg">OpenerDirector._open</span><span class="ansi-blue-fg">(self, req, data)</span>
+<span class="ansi-green-intense-fg ansi-bold">    539</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> result
+<span class="ansi-green-intense-fg ansi-bold">    541</span> protocol <span style="color: rgb(98,98,98)">=</span> req<span style="color: rgb(98,98,98)">.</span>type
+<span class="ansi-green-fg">--&gt; 542</span> result <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_call_chain</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">handle_open</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">protocol</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">protocol</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">+</span>
+<span class="ansi-green-intense-fg ansi-bold">    543</span> <span class="ansi-yellow-bg">                          </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">_open</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">req</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    544</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> result:
+<span class="ansi-green-intense-fg ansi-bold">    545</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> result
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:502</span>, in <span class="ansi-cyan-fg">OpenerDirector._call_chain</span><span class="ansi-blue-fg">(self, chain, kind, meth_name, *args)</span>
+<span class="ansi-green-intense-fg ansi-bold">    500</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> handler <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> handlers:
+<span class="ansi-green-intense-fg ansi-bold">    501</span>     func <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">getattr</span>(handler, meth_name)
+<span class="ansi-green-fg">--&gt; 502</span>     result <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">func</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">*</span><span class="ansi-yellow-bg">args</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    503</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> result <span class="ansi-bold" style="color: rgb(175,0,255)">is</span> <span class="ansi-bold" style="color: rgb(175,0,255)">not</span> <span class="ansi-bold" style="color: rgb(0,135,0)">None</span>:
+<span class="ansi-green-intense-fg ansi-bold">    504</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> result
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:1397</span>, in <span class="ansi-cyan-fg">HTTPSHandler.https_open</span><span class="ansi-blue-fg">(self, req)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1396</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">https_open</span>(<span style="color: rgb(0,135,0)">self</span>, req):
+<span class="ansi-green-fg">-&gt; 1397</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">do_open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">http</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">client</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">HTTPSConnection</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">req</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">   1398</span> <span class="ansi-yellow-bg">        </span><span class="ansi-yellow-bg">context</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_context</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">check_hostname</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_check_hostname</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/urllib/request.py:1358</span>, in <span class="ansi-cyan-fg">AbstractHTTPHandler.do_open</span><span class="ansi-blue-fg">(self, http_class, req, **http_conn_args)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1356</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">except</span> <span class="ansi-bold" style="color: rgb(215,95,95)">OSError</span> <span class="ansi-bold" style="color: rgb(0,135,0)">as</span> err: <span style="color: rgb(95,135,135)"># timeout error</span>
+<span class="ansi-green-intense-fg ansi-bold">   1357</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">raise</span> URLError(err)
+<span class="ansi-green-fg">-&gt; 1358</span>     r <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">h</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">getresponse</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1359</span> <span class="ansi-bold" style="color: rgb(0,135,0)">except</span>:
+<span class="ansi-green-intense-fg ansi-bold">   1360</span>     h<span style="color: rgb(98,98,98)">.</span>close()
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/http/client.py:1348</span>, in <span class="ansi-cyan-fg">HTTPConnection.getresponse</span><span class="ansi-blue-fg">(self)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1346</span> <span class="ansi-bold" style="color: rgb(0,135,0)">try</span>:
+<span class="ansi-green-intense-fg ansi-bold">   1347</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">try</span>:
+<span class="ansi-green-fg">-&gt; 1348</span>         <span class="ansi-yellow-bg">response</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">begin</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1349</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">except</span> <span class="ansi-bold" style="color: rgb(215,95,95)">ConnectionError</span>:
+<span class="ansi-green-intense-fg ansi-bold">   1350</span>         <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>close()
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/http/client.py:316</span>, in <span class="ansi-cyan-fg">HTTPResponse.begin</span><span class="ansi-blue-fg">(self)</span>
+<span class="ansi-green-intense-fg ansi-bold">    314</span> <span style="color: rgb(95,135,135)"># read until we get a non-100 response</span>
+<span class="ansi-green-intense-fg ansi-bold">    315</span> <span class="ansi-bold" style="color: rgb(0,135,0)">while</span> <span class="ansi-bold" style="color: rgb(0,135,0)">True</span>:
+<span class="ansi-green-fg">--&gt; 316</span>     version, status, reason <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_read_status</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    317</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> status <span style="color: rgb(98,98,98)">!=</span> CONTINUE:
+<span class="ansi-green-intense-fg ansi-bold">    318</span>         <span class="ansi-bold" style="color: rgb(0,135,0)">break</span>
+
+File <span class="ansi-green-fg">/usr/lib/python3.8/http/client.py:285</span>, in <span class="ansi-cyan-fg">HTTPResponse._read_status</span><span class="ansi-blue-fg">(self)</span>
+<span class="ansi-green-intense-fg ansi-bold">    281</span>     <span style="color: rgb(0,135,0)">print</span>(<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">reply:</span><span style="color: rgb(175,0,0)">&#34;</span>, <span style="color: rgb(0,135,0)">repr</span>(line))
+<span class="ansi-green-intense-fg ansi-bold">    282</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span class="ansi-bold" style="color: rgb(175,0,255)">not</span> line:
+<span class="ansi-green-intense-fg ansi-bold">    283</span>     <span style="color: rgb(95,135,135)"># Presumably, the server closed the connection before</span>
+<span class="ansi-green-intense-fg ansi-bold">    284</span>     <span style="color: rgb(95,135,135)"># sending a valid response.</span>
+<span class="ansi-green-fg">--&gt; 285</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">raise</span> RemoteDisconnected(<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">Remote end closed connection without</span><span style="color: rgb(175,0,0)">&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    286</span>                              <span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)"> response</span><span style="color: rgb(175,0,0)">&#34;</span>)
+<span class="ansi-green-intense-fg ansi-bold">    287</span> <span class="ansi-bold" style="color: rgb(0,135,0)">try</span>:
+<span class="ansi-green-intense-fg ansi-bold">    288</span>     version, status, reason <span style="color: rgb(98,98,98)">=</span> line<span style="color: rgb(98,98,98)">.</span>split(<span class="ansi-bold" style="color: rgb(0,135,0)">None</span>, <span style="color: rgb(98,98,98)">2</span>)
+
+<span class="ansi-red-fg">RemoteDisconnected</span>: Remote end closed connection without response
+</pre></div></div>
+</div>
 <p>This dataset has 8 features. The outcome is income which is binarized to 0 (low-income, &lt;=50K) or 1 (high-income, &gt;50K).</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
@@ -403,103 +541,17 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </div>
 </div>
 <div class="nboutput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
-</pre></div>
+<div class="prompt empty docutils container">
 </div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [3]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dataset</span><span style="color: rgb(98,98,98)">.</span>head()
 
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>28</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>Single</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>60</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>30</td>
-      <td>Self-Employed</td>
-      <td>Assoc</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>65</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>32</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>20</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>35</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>4</th>
-      <td>41</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
 </div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
@@ -529,7 +581,7 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div></div>
 </div>
 <p>Given this dataset, we construct a data object for DiCE. Since continuous and discrete features have different ways of perturbation, we need to specify the names of the continuous features. DiCE also requires the name of the output variable that the ML model will predict.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]:
 </pre></div>
 </div>
@@ -538,9 +590,23 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [5]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> d <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Data(dataframe<span style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">dataset</span>, continuous_features<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>],
+<span class="ansi-green-intense-fg ansi-bold">      2</span>                  outcome_name<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>, data_name<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">adult</span><span style="color: rgb(175,0,0)">&#39;</span>, test_size<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">0.1</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
+</div>
 </section>
 <section id="Loading-the-ML-model">
-<h2>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title="Permalink to this headline"></a></h2>
+<h2>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title="Permalink to this heading"></a></h2>
 <p>Below, we use a pre-trained ML model which produces high accuracy comparable to other baselines. For convenience, we include the sample trained model with the DiCE package.</p>
 <p>Note that we need to specify the explainer in the model backend. This is because both model and explainer need to be using the same backend library (pytorch or tensorflow).</p>
 <div class="nbinput docutils container">
@@ -584,19 +650,19 @@ <h2>Loading the ML model<a class="headerlink" href="#Loading-the-ML-model" title
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.container.Sequential&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/torch/serialization.py:786: SourceChangeWarning: source code of class &#39;torch.nn.modules.container.Sequential&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
   warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.linear.Linear&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/torch/serialization.py:786: SourceChangeWarning: source code of class &#39;torch.nn.modules.linear.Linear&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
   warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.ReLU&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/torch/serialization.py:786: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.ReLU&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
   warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.Softmax&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/torch/serialization.py:786: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.Softmax&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
   warnings.warn(msg, SourceChangeWarning)
 </pre></div></div>
 </div>
 </section>
 <section id="Generate-counterfactuals-using-a-VAE-model">
-<h2>Generate counterfactuals using a VAE model<a class="headerlink" href="#Generate-counterfactuals-using-a-VAE-model" title="Permalink to this headline"></a></h2>
+<h2>Generate counterfactuals using a VAE model<a class="headerlink" href="#Generate-counterfactuals-using-a-VAE-model" title="Permalink to this heading"></a></h2>
 <p>Based on the data object <em>d</em> and the model object <em>m</em>, we can now instantiate the DiCE class for generating explanations. We present the variational inference based approach towards generating counterfactuals, where we first train an encoder-decoder framework to generate counterfactuals.</p>
 <p>FeasibleBaseVAE class has an method <code class="docutils literal notranslate"><span class="pre">train()</span></code>, which would train the Variational Encoder Decoder framework on the input dataframe. It has another arugment, <code class="docutils literal notranslate"><span class="pre">pre_trained</span></code>, which if set to 0 would re-train the framework each time while generating CFs. Else, it can be set to 1 to avoid repeated training of the framework and would load the latest fitted VAE model.</p>
 <div class="nbinput docutils container">
@@ -616,19 +682,16 @@ <h2>Generate counterfactuals using a VAE model<a class="headerlink" href="#Gener
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Dataset Shape: (26048, 30)
-Datasets Columns: Index([&#39;age&#39;, &#39;hours_per_week&#39;, &#39;workclass_Government&#39;,
-       &#39;workclass_Other/Unknown&#39;, &#39;workclass_Private&#39;,
-       &#39;workclass_Self-Employed&#39;, &#39;education_Assoc&#39;, &#39;education_Bachelors&#39;,
-       &#39;education_Doctorate&#39;, &#39;education_HS-grad&#39;, &#39;education_Masters&#39;,
-       &#39;education_Prof-school&#39;, &#39;education_School&#39;, &#39;education_Some-college&#39;,
-       &#39;marital_status_Divorced&#39;, &#39;marital_status_Married&#39;,
-       &#39;marital_status_Separated&#39;, &#39;marital_status_Single&#39;,
-       &#39;marital_status_Widowed&#39;, &#39;occupation_Blue-Collar&#39;,
-       &#39;occupation_Other/Unknown&#39;, &#39;occupation_Professional&#39;,
-       &#39;occupation_Sales&#39;, &#39;occupation_Service&#39;, &#39;occupation_White-Collar&#39;,
-       &#39;race_Other&#39;, &#39;race_White&#39;, &#39;gender_Female&#39;, &#39;gender_Male&#39;, &#39;income&#39;],
-      dtype=&#39;object&#39;)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [7]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># initiate DiCE</span>
+<span class="ansi-green-fg">----&gt; 2</span> exp <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Dice(<span class="ansi-yellow-bg">d</span>, m, encoded_size<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">10</span>, lr<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>,
+<span class="ansi-green-intense-fg ansi-bold">      3</span>                    batch_size<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">2048</span>, validity_reg<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">42.0</span>, margin<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">0.165</span>, epochs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">25</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>                    wm1<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>, wm2<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>, wm3<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>)
+<span class="ansi-green-intense-fg ansi-bold">      5</span> exp<span style="color: rgb(98,98,98)">.</span>train(pre_trained<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
 </pre></div></div>
 </div>
 <p>DiCE is a form of a local explanation and requires an query input whose outcome needs to be explained. Below we provide a sample input whose outcome is 0 (low-income) as per the ML model object <em>m</em>.</p>
@@ -660,191 +723,31 @@ <h2>Generate counterfactuals using a VAE model<a class="headerlink" href="#Gener
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/nn/modules/container.py:139: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
-  input = module(input)
-/mnt/c/Users/amshar/code/dice/dice_ml/utils/sample_architecture/vae_model.py:121: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
-  c = torch.tensor(c).float()
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>41.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-
-Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [9]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instance, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">5</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>)
+<span class="ansi-green-intense-fg ansi-bold">      3</span> <span style="color: rgb(95,135,135)"># visualize the results</span>
+<span class="ansi-green-intense-fg ansi-bold">      4</span> dice_exp<span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>40.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>40.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>38.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>4</th>
-      <td>38.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>That’s it! You can try generating counterfactual explanations for other examples using the same code. You can compare the running time of this VAE-based to DiCE’s default method: VAE-based method is super fast!</p>
 </section>
 </section>
 <section id="Adding-feasibility-constraints">
-<h1>Adding feasibility constraints<a class="headerlink" href="#Adding-feasibility-constraints" title="Permalink to this headline"></a></h1>
+<h1>Adding feasibility constraints<a class="headerlink" href="#Adding-feasibility-constraints" title="Permalink to this heading"></a></h1>
 <p>However, you might notice that for some examples, the above method can still return infeasible counterfactuals. This requires our base framework to be adpated for prodcuing feasible counterfactuals. A detailed description of how we adapt the method under different assumptions is provided in <a class="reference external" href="https://arxiv.org/pdf/1912.03277">this paper</a>.</p>
 <p>In the section below, we show an adaptation our base approach for preserving the Age-Ed constraint: Age and Education can never decrease and increasing Education implies increase in Age. This approach is called <strong>ModelApprox</strong>, where we adapt our base approach for simple unary and binary constraints.</p>
 <section id="ModelApprox">
-<h2>ModelApprox<a class="headerlink" href="#ModelApprox" title="Permalink to this headline"></a></h2>
+<h2>ModelApprox<a class="headerlink" href="#ModelApprox" title="Permalink to this heading"></a></h2>
 <p>Similar to the FeasibleBaseVAE class above, FeasibleModelApprox class has a method <code class="docutils literal notranslate"><span class="pre">train()</span></code> with argument <code class="docutils literal notranslate"><span class="pre">pre_trained</span></code>, which determines whether to train the framework again or load the latest optimal model. However, there are additional arguments to the <code class="docutils literal notranslate"><span class="pre">train()</span></code> method:</p>
 <ol class="arabic simple">
 <li><p>The first arugment determines whether the constraint to be preserved is unary or monotonic</p></li>
@@ -854,7 +757,7 @@ <h2>ModelApprox<a class="headerlink" href="#ModelApprox" title="Permalink to thi
 </ol>
 </section>
 <section id="Initilize-the-Model-and-Explainer-for-FeasibleModelApprox">
-<h2>Initilize the Model and Explainer for FeasibleModelApprox<a class="headerlink" href="#Initilize-the-Model-and-Explainer-for-FeasibleModelApprox" title="Permalink to this headline"></a></h2>
+<h2>Initilize the Model and Explainer for FeasibleModelApprox<a class="headerlink" href="#Initilize-the-Model-and-Explainer-for-FeasibleModelApprox" title="Permalink to this heading"></a></h2>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]:
 </pre></div>
@@ -889,14 +792,6 @@ <h2>Initilize the Model and Explainer for FeasibleModelApprox<a class="headerlin
 <div class="highlight"><pre>
 /mnt/c/Users/amshar/code/dice/dice_ml/model.py:34: UserWarning: {&#39;model&#39;: &#39;pytorch_model.PyTorchModel&#39;, &#39;explainer&#39;: &#39;feasible_model_approx.FeasibleModelApprox&#39;} backend not in supported backends sklearn,TF1,TF2,PYT
   warnings.warn(&#39;{0} backend not in supported backends {1}&#39;.format(
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.container.Sequential&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
-  warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.linear.Linear&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
-  warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.ReLU&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
-  warnings.warn(msg, SourceChangeWarning)
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class &#39;torch.nn.modules.activation.Softmax&#39; has changed. you can retrieve the original source code by accessing the object&#39;s source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
-  warnings.warn(msg, SourceChangeWarning)
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -916,19 +811,16 @@ <h2>Initilize the Model and Explainer for FeasibleModelApprox<a class="headerlin
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Dataset Shape: (26048, 30)
-Datasets Columns: Index([&#39;age&#39;, &#39;hours_per_week&#39;, &#39;workclass_Government&#39;,
-       &#39;workclass_Other/Unknown&#39;, &#39;workclass_Private&#39;,
-       &#39;workclass_Self-Employed&#39;, &#39;education_Assoc&#39;, &#39;education_Bachelors&#39;,
-       &#39;education_Doctorate&#39;, &#39;education_HS-grad&#39;, &#39;education_Masters&#39;,
-       &#39;education_Prof-school&#39;, &#39;education_School&#39;, &#39;education_Some-college&#39;,
-       &#39;marital_status_Divorced&#39;, &#39;marital_status_Married&#39;,
-       &#39;marital_status_Separated&#39;, &#39;marital_status_Single&#39;,
-       &#39;marital_status_Widowed&#39;, &#39;occupation_Blue-Collar&#39;,
-       &#39;occupation_Other/Unknown&#39;, &#39;occupation_Professional&#39;,
-       &#39;occupation_Sales&#39;, &#39;occupation_Service&#39;, &#39;occupation_White-Collar&#39;,
-       &#39;race_Other&#39;, &#39;race_White&#39;, &#39;gender_Female&#39;, &#39;gender_Male&#39;, &#39;income&#39;],
-      dtype=&#39;object&#39;)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [11]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># initiate DiCE</span>
+<span class="ansi-green-fg">----&gt; 2</span> exp <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Dice(<span class="ansi-yellow-bg">d</span>, m, encoded_size<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">10</span>, lr<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>, batch_size<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">2048</span>,
+<span class="ansi-green-intense-fg ansi-bold">      3</span>                    validity_reg<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">76.0</span>, margin<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">0.344</span>, epochs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">25</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>                    wm1<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>, wm2<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>, wm3<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1e-2</span>)
+<span class="ansi-green-intense-fg ansi-bold">      5</span> exp<span style="color: rgb(98,98,98)">.</span>train(<span style="color: rgb(98,98,98)">1</span>, [[<span style="color: rgb(98,98,98)">0</span>]], <span style="color: rgb(98,98,98)">1</span>, <span style="color: rgb(98,98,98)">87</span>, pre_trained<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -942,182 +834,22 @@ <h2>Initilize the Model and Explainer for FeasibleModelApprox<a class="headerlin
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-/home/amshar/python-environments/vpy38/lib/python3.8/site-packages/torch/nn/modules/container.py:139: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
-  input = module(input)
-/mnt/c/Users/amshar/code/dice/dice_ml/utils/sample_architecture/vae_model.py:121: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
-  c = torch.tensor(c).float()
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>41.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-
-Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [12]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instance, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">5</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>)
+<span class="ansi-green-intense-fg ansi-bold">      3</span> <span style="color: rgb(95,135,135)"># visualize the results</span>
+<span class="ansi-green-intense-fg ansi-bold">      4</span> dice_exp<span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>45.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>40.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>42.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>44.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>4</th>
-      <td>42.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>Male</td>
-      <td>40.0</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>The results for ModelApprox show that the Age is also increased with increase in Education in counterfactual explanations unlike the BaseVAE method. You can try to experiment with ModelApprox to preserve unary and monotonic constraints for other datasets too. Examples for even more advanced approaches like <strong>SCMGenCF</strong>,<strong>OracleGenCF</strong> would be included soon to this repository, where we learn to generate feasible counterfactuals for complex feasiblity constraints. More details can be found in
 <a class="reference external" href="https://arxiv.org/pdf/1912.03277">our paper</a>.</p>
 </section>
diff --git a/docs/notebooks/DiCE_model_agnostic_CFs.html b/docs/notebooks/DiCE_model_agnostic_CFs.html
index f565e63b..6ab921c1 100644
--- a/docs/notebooks/DiCE_model_agnostic_CFs.html
+++ b/docs/notebooks/DiCE_model_agnostic_CFs.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Generating counterfactual explanations with any ML model &mdash; DiCE 0.8 documentation</title>
+  <title>Generating counterfactual explanations with any ML model &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,14 +14,16 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
     <script src="../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../genindex.html" />
     <link rel="search" title="Search" href="../search.html" />
-    <link rel="next" title="Generating Counterfactual Explanations without access to training data" href="DiCE_with_private_data.html" />
+    <link rel="next" title="Generating counterfactual explanations without access to training data" href="DiCE_with_private_data.html" />
     <link rel="prev" title="Generating counterfactuals for multi-class classification and regression models" href="DiCE_multiclass_classification_and_regression.html" /> 
 </head>
 
@@ -77,7 +79,7 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -327,6 +329,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -335,10 +338,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -350,12 +357,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -383,11 +393,11 @@
 }
 </style>
 <section id="Generating-counterfactual-explanations-with-any-ML-model">
-<h1>Generating counterfactual explanations with any ML model<a class="headerlink" href="#Generating-counterfactual-explanations-with-any-ML-model" title="Permalink to this headline"></a></h1>
+<h1>Generating counterfactual explanations with any ML model<a class="headerlink" href="#Generating-counterfactual-explanations-with-any-ML-model" title="Permalink to this heading"></a></h1>
 <p>The goal of this notebook is to show how to generate CFs for ML models using frameworks other than TensorFlow or PyTorch. We show how to generate diverse CFs by three methods: 1. Independent random sampling of features (<code class="docutils literal notranslate"><span class="pre">method_name='random')</span></code> 2. Genetic algorithm (<code class="docutils literal notranslate"><span class="pre">method_name='genetic')</span></code> 3. Querying a KD tree (<code class="docutils literal notranslate"><span class="pre">method_name='kdtree')</span></code></p>
 <p>We use scikit-learn models for demonstration.</p>
 <section id="1.-Independent-random-sampling-of-features">
-<h2>1. Independent random sampling of features<a class="headerlink" href="#1.-Independent-random-sampling-of-features" title="Permalink to this headline"></a></h2>
+<h2>1. Independent random sampling of features<a class="headerlink" href="#1.-Independent-random-sampling-of-features" title="Permalink to this heading"></a></h2>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
 </pre></div>
@@ -414,9 +424,9 @@ <h2>1. Independent random sampling of features<a class="headerlink" href="#1.-In
 </div>
 </div>
 <section id="Loading-dataset">
-<h3>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this headline"></a></h3>
+<h3>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this heading"></a></h3>
 <p>We use the “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>). We transform the data as described in dice_ml.utils.helpers module.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
 </pre></div>
 </div>
@@ -424,6 +434,56 @@ <h3>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">FileNotFoundError</span>                         Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [3]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> dataset <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">helpers</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">load_adult_income_dataset</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/utils/helpers.py:25</span>, in <span class="ansi-cyan-fg">load_adult_income_dataset</span><span class="ansi-blue-fg">(only_train)</span>
+<span class="ansi-green-intense-fg ansi-bold">     19</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">load_adult_income_dataset</span>(only_train<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>):
+<span class="ansi-green-intense-fg ansi-bold">     20</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Loads adult income dataset from https://archive.ics.uci.edu/ml/datasets/Adult and prepares</span>
+<span class="ansi-green-intense-fg ansi-bold">     21</span> <span style="color: rgb(175,0,0)">       the data for data analysis based on https://rpubs.com/H_Zhu/235617</span>
+<span class="ansi-green-intense-fg ansi-bold">     22</span>
+<span class="ansi-green-intense-fg ansi-bold">     23</span> <span style="color: rgb(175,0,0)">    :return adult_data: returns preprocessed adult income dataset.</span>
+<span class="ansi-green-intense-fg ansi-bold">     24</span> <span style="color: rgb(175,0,0)">    &#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 25</span>     raw_data <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">genfromtxt</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">     26</span> <span class="ansi-yellow-bg">                             </span><span class="ansi-yellow-bg">delimiter</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">, </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">dtype</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(0,135,0)">str</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">invalid_raise</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg ansi-bold" style="color: rgb(0,135,0)">False</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span>     <span style="color: rgb(95,135,135)">#  column names from &#34;https://archive.ics.uci.edu/ml/datasets/Adult&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     column_names <span style="color: rgb(98,98,98)">=</span> [<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">fnlwgt</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">educational-num</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">marital-status</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     30</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">relationship</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">race</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">gender</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-gain</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">capital-loss</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours-per-week</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">native-country</span><span style="color: rgb(175,0,0)">&#39;</span>,
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                     <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>]
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/npyio.py:1934</span>, in <span class="ansi-cyan-fg">genfromtxt</span><span class="ansi-blue-fg">(fname, dtype, comments, delimiter, skip_header, skip_footer, converters, missing_values, filling_values, usecols, names, excludelist, deletechars, replace_space, autostrip, case_sensitive, defaultfmt, unpack, usemask, loose, invalid_raise, max_rows, encoding, ndmin, like)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1932</span>     fname <span style="color: rgb(98,98,98)">=</span> os_fspath(fname)
+<span class="ansi-green-intense-fg ansi-bold">   1933</span> <span class="ansi-bold" style="color: rgb(0,135,0)">if</span> <span style="color: rgb(0,135,0)">isinstance</span>(fname, <span style="color: rgb(0,135,0)">str</span>):
+<span class="ansi-green-fg">-&gt; 1934</span>     fid <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">np</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">lib</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">_datasource</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">fname</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">rt</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#39;</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">   1935</span>     fid_ctx <span style="color: rgb(98,98,98)">=</span> contextlib<span style="color: rgb(98,98,98)">.</span>closing(fid)
+<span class="ansi-green-intense-fg ansi-bold">   1936</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:193</span>, in <span class="ansi-cyan-fg">open</span><span class="ansi-blue-fg">(path, mode, destpath, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    156</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    157</span> <span style="color: rgb(175,0,0)">Open `path` with `mode` and return the file object.</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    189</span>
+<span class="ansi-green-intense-fg ansi-bold">    190</span> <span style="color: rgb(175,0,0)">&#34;&#34;&#34;</span>
+<span class="ansi-green-intense-fg ansi-bold">    192</span> ds <span style="color: rgb(98,98,98)">=</span> DataSource(destpath)
+<span class="ansi-green-fg">--&gt; 193</span> <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> <span class="ansi-yellow-bg">ds</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">open</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">path</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">mode</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">encoding</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">newline</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">~/python-envs/v3.8dowhy/lib/python3.8/site-packages/numpy/lib/_datasource.py:533</span>, in <span class="ansi-cyan-fg">DataSource.open</span><span class="ansi-blue-fg">(self, path, mode, encoding, newline)</span>
+<span class="ansi-green-intense-fg ansi-bold">    530</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">return</span> _file_openers[ext](found, mode<span style="color: rgb(98,98,98)">=</span>mode,
+<span class="ansi-green-intense-fg ansi-bold">    531</span>                               encoding<span style="color: rgb(98,98,98)">=</span>encoding, newline<span style="color: rgb(98,98,98)">=</span>newline)
+<span class="ansi-green-intense-fg ansi-bold">    532</span> <span class="ansi-bold" style="color: rgb(0,135,0)">else</span>:
+<span class="ansi-green-fg">--&gt; 533</span>     <span class="ansi-bold" style="color: rgb(0,135,0)">raise</span> <span class="ansi-bold" style="color: rgb(215,95,95)">FileNotFoundError</span>(<span style="color: rgb(175,0,0)">f</span><span style="color: rgb(175,0,0)">&#34;</span><span class="ansi-bold" style="color: rgb(175,95,135)">{</span>path<span class="ansi-bold" style="color: rgb(175,95,135)">}</span><span style="color: rgb(175,0,0)"> not found.</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">FileNotFoundError</span>: https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data not found.
+</pre></div></div>
+</div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
 </pre></div>
@@ -433,105 +493,19 @@ <h3>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </div>
 </div>
 <div class="nboutput nblast docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
-</pre></div>
+<div class="prompt empty docutils container">
 </div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [4]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dataset</span><span style="color: rgb(98,98,98)">.</span>head()
 
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>28</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>Single</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>60</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>30</td>
-      <td>Self-Employed</td>
-      <td>Assoc</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>65</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>32</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>20</td>
-      <td>Private</td>
-      <td>Some-college</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>35</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>4</th>
-      <td>41</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>50</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]:
 </pre></div>
 </div>
@@ -539,11 +513,24 @@ <h3>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [5]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> d <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Data(dataframe<span style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">dataset</span>, continuous_features<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>], outcome_name<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#39;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
+</div>
 </section>
 <section id="Training-a-custom-ML-model">
-<h3>Training a custom ML model<a class="headerlink" href="#Training-a-custom-ML-model" title="Permalink to this headline"></a></h3>
+<h3>Training a custom ML model<a class="headerlink" href="#Training-a-custom-ML-model" title="Permalink to this heading"></a></h3>
 <p>Below, we build an ML model using scikit-learn to demonstrate how our methods can work with any sklearn model.</p>
-<div class="nbinput nblast docutils container">
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[6]:
 </pre></div>
 </div>
@@ -579,7 +566,22 @@ <h3>Training a custom ML model<a class="headerlink" href="#Training-a-custom-ML-
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [6]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> target <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">dataset</span>[<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#34;</span>]
+<span class="ansi-green-intense-fg ansi-bold">      2</span> <span style="color: rgb(95,135,135)"># Split data into train and test</span>
+<span class="ansi-green-intense-fg ansi-bold">      3</span> datasetX <span style="color: rgb(98,98,98)">=</span> dataset<span style="color: rgb(98,98,98)">.</span>drop(<span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">income</span><span style="color: rgb(175,0,0)">&#34;</span>, axis<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">1</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dataset&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[7]:
 </pre></div>
 </div>
@@ -589,10 +591,25 @@ <h3>Training a custom ML model<a class="headerlink" href="#Training-a-custom-ML-
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [7]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 3&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># provide the trained ML model to DiCE&#39;s model object</span>
+<span class="ansi-green-intense-fg ansi-bold">      2</span> backend <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">sklearn</span><span style="color: rgb(175,0,0)">&#39;</span>
+<span class="ansi-green-fg">----&gt; 3</span> m <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Model(model<span style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">model</span>, backend<span style="color: rgb(98,98,98)">=</span>backend)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;model&#39; is not defined
+</pre></div></div>
+</div>
 </section>
 <section id="Generate-diverse-counterfactuals">
-<h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this headline"></a></h3>
-<div class="nbinput nblast docutils container">
+<h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this heading"></a></h3>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[8]:
 </pre></div>
 </div>
@@ -601,7 +618,21 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
-<div class="nbinput nblast docutils container">
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [8]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># initiate DiCE</span>
+<span class="ansi-green-fg">----&gt; 2</span> exp_random <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">random</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[9]:
 </pre></div>
 </div>
@@ -609,6 +640,19 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [9]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> query_instances <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">x_train</span>[<span style="color: rgb(98,98,98)">4</span>:<span style="color: rgb(98,98,98)">6</span>]
+
+<span class="ansi-red-fg">NameError</span>: name &#39;x_train&#39; is not defined
+</pre></div></div>
+</div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]:
 </pre></div>
@@ -621,9 +665,15 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  4.39it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [10]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_random <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_random</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">2</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>, verbose<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">False</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_random&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -634,264 +684,19 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1.0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>59.0</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>51.0</td>
-      <td>-</td>
-      <td>HS-grad</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [11]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_random</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 0.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_random&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Government</td>
-      <td>HS-grad</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>53.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Divorced</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>It can be observed that the random sampling method produces less sparse CFs in contrast to current DiCE’s implementation. The sparsity issue with random sampling worsens with increasing <em>total_CFs</em></p>
 <p>Further, different sets of counterfactuals can be generated with different random seeds.</p>
 <div class="nbinput docutils container">
@@ -910,9 +715,19 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  3.04it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [12]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 3&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-intense-fg ansi-bold">      2</span> <span style="color: rgb(95,135,135)"># default random seed is 17</span>
+<span class="ansi-green-fg">----&gt; 3</span> dice_exp_random <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_random</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instances,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>                                                       total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>,
+<span class="ansi-green-intense-fg ansi-bold">      5</span>                                                       desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      6</span>                                                       random_seed<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">9</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_random&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -923,314 +738,21 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1.0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>67.0</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>77.0</td>
-      <td>-</td>
-      <td>Some-college</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>70.0</td>
-      <td>-</td>
-      <td>Prof-school</td>
-      <td>-</td>
-      <td>Other/Unknown</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>69.0</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [13]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_random</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 0.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_random&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>87.0</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>71.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Female</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>White</td>
-      <td>-</td>
-      <td>31.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>19.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <section id="Selecting-the-features-to-vary">
-<h4>Selecting the features to vary<a class="headerlink" href="#Selecting-the-features-to-vary" title="Permalink to this headline"></a></h4>
+<h4>Selecting the features to vary<a class="headerlink" href="#Selecting-the-features-to-vary" title="Permalink to this heading"></a></h4>
 <p>Here, you can ensure that DiCE varies only features that it makes sense to vary.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[14]:
@@ -1243,28 +765,20 @@ <h4>Selecting the features to vary<a class="headerlink" href="#Selecting-the-fea
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
- 50%|█████████████████████████████████▌                                 | 1/2 [00:00&lt;00:00,  3.13it/s]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Only 3 (required 4)  Diverse Counterfactuals found for the given configuration, perhaps try with different parameters... ; total time taken: 00 min 00 sec
-</pre></div></div>
-</div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  3.13it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [14]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_random <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_random</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>         query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>         features_to_vary<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>])
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_random&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -1275,303 +789,22 @@ <h4>Selecting the features to vary<a class="headerlink" href="#Selecting-the-fea
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1.0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>Sales</td>
-      <td>-</td>
-      <td>-</td>
-      <td>82.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>85.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>Sales</td>
-      <td>-</td>
-      <td>-</td>
-      <td>70.0</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [15]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_random</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 0.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_random&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>22.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>55.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>-</td>
-      <td>-</td>
-      <td>School</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>87.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>-</td>
-      <td>Government</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 <section id="Choosing-feature-ranges">
-<h4>Choosing feature ranges<a class="headerlink" href="#Choosing-feature-ranges" title="Permalink to this headline"></a></h4>
+<h4>Choosing feature ranges<a class="headerlink" href="#Choosing-feature-ranges" title="Permalink to this heading"></a></h4>
 <p>Since the features are sampled randomly, they can freely vary across their range. In the below example, we show how range of continuous features can be controlled using <em>permitted_range</em> parameter that can now be passed during CF generation.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[16]:
@@ -1587,9 +820,17 @@ <h4>Choosing feature ranges<a class="headerlink" href="#Choosing-feature-ranges"
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  2.73it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [16]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_random <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_random</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>     query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>     permitted_range<span style="color: rgb(98,98,98)">=</span>{<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">22</span>, <span style="color: rgb(98,98,98)">50</span>], <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">40</span>, <span style="color: rgb(98,98,98)">60</span>]})
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_random&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -1600,325 +841,32 @@ <h4>Choosing feature ranges<a class="headerlink" href="#Choosing-feature-ranges"
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Query instance (original outcome : 0)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [17]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_random</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_random&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1.0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>41.0</td>
-      <td>Self-Employed</td>
-      <td>-</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>36.0</td>
-      <td>-</td>
-      <td>Prof-school</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>43.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>-</td>
-      <td>59.0</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>48.0</td>
-      <td>Other/Unknown</td>
-      <td>Prof-school</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0.0)
-</pre></div></div>
-</div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>White</td>
-      <td>-</td>
-      <td>41.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Divorced</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>40.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>-</td>
-      <td>-</td>
-      <td>School</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>42.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 </section>
 </section>
 <section id="2.-Genetic-Algorithm">
-<h2>2. Genetic Algorithm<a class="headerlink" href="#2.-Genetic-Algorithm" title="Permalink to this headline"></a></h2>
+<h2>2. Genetic Algorithm<a class="headerlink" href="#2.-Genetic-Algorithm" title="Permalink to this heading"></a></h2>
 <p>Here, we show how to use DiCE can be used to generate CFs for any ML model by using the genetic algorithm to find the best counterfactuals close to the query point. The genetic algorithm converges quickly, and promotes diverse counterfactuals.</p>
 <section id="id1">
-<h3>Training a custom ML model<a class="headerlink" href="#id1" title="Permalink to this headline"></a></h3>
+<h3>Training a custom ML model<a class="headerlink" href="#id1" title="Permalink to this heading"></a></h3>
 <p>Currently, the genetic algorithm method works with scikit-learn models. We will use the same model as shown previously in the notebook. Support for Tensorflow 1&amp;2 and Pytorch will be implemented soon.</p>
 </section>
 <section id="id2">
-<h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Permalink to this headline"></a></h3>
-<div class="nbinput nblast docutils container">
+<h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Permalink to this heading"></a></h3>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[18]:
 </pre></div>
 </div>
@@ -1927,72 +875,41 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Per
 </pre></div>
 </div>
 </div>
-<div class="nbinput docutils container">
-<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[19]:
-</pre></div>
-</div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
-<span class="n">dice_exp_genetic</span> <span class="o">=</span> <span class="n">exp_genetic</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-  0%|                                                                           | 0/2 [00:00&lt;?, ?it/s]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Initializing initial parameters to the genetic algorithm...
-Initialization complete! Generating counterfactuals...
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
- 50%|█████████████████████████████████▌                                 | 1/2 [00:01&lt;00:01,  1.58s/it]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 01 sec
-Initializing initial parameters to the genetic algorithm...
-Initialization complete! Generating counterfactuals...
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [18]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># initiate DiceGenetic</span>
+<span class="ansi-green-fg">----&gt; 2</span> exp_genetic <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">genetic</span><span style="color: rgb(175,0,0)">&#39;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:02&lt;00:00,  1.42s/it]
-</pre></div></div>
+<div class="nbinput docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[19]:
+</pre></div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
+<span class="n">dice_exp_genetic</span> <span class="o">=</span> <span class="n">exp_genetic</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+</pre></div>
 </div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 01 sec
-</pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [19]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_genetic <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_genetic</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>, verbose<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_genetic&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -2003,312 +920,19 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Per
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Self-Employed</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Other</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [20]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_genetic</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_genetic&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>32.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>School</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>We can also ensure that the genetic algorithm also only varies the features that you wish to vary</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[21]:
@@ -2316,286 +940,29 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Per
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
 <span class="n">dice_exp_genetic</span> <span class="o">=</span> <span class="n">exp_genetic</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span>
-    <span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
+    <span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span>
     <span class="n">features_to_vary</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;workclass&#39;</span><span class="p">,</span> <span class="s1">&#39;education&#39;</span><span class="p">,</span> <span class="s1">&#39;occupation&#39;</span><span class="p">,</span> <span class="s1">&#39;hours_per_week&#39;</span><span class="p">])</span>
 <span class="n">dice_exp_genetic</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:02&lt;00:00,  1.23s/it]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Other/Unknown</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [21]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_genetic <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_genetic</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>     query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">2</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>     features_to_vary<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>])
+<span class="ansi-green-intense-fg ansi-bold">      5</span> dice_exp_genetic<span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_genetic&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>You can also constrain the features to vary only within the permitted range</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[22]:
@@ -2603,298 +970,41 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id2" title="Per
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
 <span class="n">dice_exp_genetic</span> <span class="o">=</span> <span class="n">exp_genetic</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span>
-    <span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
+    <span class="n">query_instances</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span>
     <span class="n">permitted_range</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">22</span><span class="p">,</span> <span class="mi">50</span><span class="p">],</span> <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">40</span><span class="p">,</span> <span class="mi">60</span><span class="p">]})</span>
 <span class="n">dice_exp_genetic</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:02&lt;00:00,  1.11s/it]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>Self-Employed</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 0)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [22]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_genetic <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_genetic</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>     query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">2</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>     permitted_range<span style="color: rgb(98,98,98)">=</span>{<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">22</span>, <span style="color: rgb(98,98,98)">50</span>], <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">40</span>, <span style="color: rgb(98,98,98)">60</span>]})
+<span class="ansi-green-intense-fg ansi-bold">      5</span> dice_exp_genetic<span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_genetic&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>School</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>0</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>Separated</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 </section>
 <section id="3.-Querying-a-KD-Tree">
-<h2>3. Querying a KD Tree<a class="headerlink" href="#3.-Querying-a-KD-Tree" title="Permalink to this headline"></a></h2>
+<h2>3. Querying a KD Tree<a class="headerlink" href="#3.-Querying-a-KD-Tree" title="Permalink to this heading"></a></h2>
 <p>Here, we show how to use DiCE can be used to generate CFs for any ML model by finding the closest points in the dataset that give the output as the desired class. We do this efficiently by building KD trees for each class, and querying the KD tree of the desired class to find the k closest counterfactuals from the dataset. The idea behind finding the closest points from the training data itself is to ensure that the counterfactuals displayed are feasible.</p>
 <section id="id3">
-<h3>Training a custom ML model<a class="headerlink" href="#id3" title="Permalink to this headline"></a></h3>
+<h3>Training a custom ML model<a class="headerlink" href="#id3" title="Permalink to this heading"></a></h3>
 <p>Currently, the KD tree algorithm method works with scikit-learn models. Again, we will use the same model as shown previously in the notebook. Support for Tensorflow 1&amp;2 and Pytorch will be implemented soon.</p>
 </section>
 <section id="id4">
-<h3>Generate diverse counterfactuals<a class="headerlink" href="#id4" title="Permalink to this headline"></a></h3>
-<div class="nbinput nblast docutils container">
+<h3>Generate diverse counterfactuals<a class="headerlink" href="#id4" title="Permalink to this heading"></a></h3>
+<div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[23]:
 </pre></div>
 </div>
@@ -2903,6 +1013,20 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id4" title="Per
 </pre></div>
 </div>
 </div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [23]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># initiate DiceKD</span>
+<span class="ansi-green-fg">----&gt; 2</span> exp_KD <span style="color: rgb(98,98,98)">=</span> dice_ml<span style="color: rgb(98,98,98)">.</span>Dice(<span class="ansi-yellow-bg">d</span>, m, method<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">kdtree</span><span style="color: rgb(175,0,0)">&#39;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;d&#39; is not defined
+</pre></div></div>
+</div>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[24]:
 </pre></div>
@@ -2915,9 +1039,15 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id4" title="Per
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:01&lt;00:00,  1.31it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [24]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_KD <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_KD</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_KD&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -2928,314 +1058,21 @@ <h3>Generate diverse counterfactuals<a class="headerlink" href="#id4" title="Per
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>23580</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>17378</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>20695</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>Female</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-    <tr>
-      <th>23876</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>Married</td>
-      <td>Service</td>
-      <td>-</td>
-      <td>Female</td>
-      <td>-</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [25]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_KD</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_KD&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>22027</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>2457</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>516</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>15831</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <section id="id5">
-<h4>Selecting the features to vary<a class="headerlink" href="#id5" title="Permalink to this headline"></a></h4>
+<h4>Selecting the features to vary<a class="headerlink" href="#id5" title="Permalink to this heading"></a></h4>
 <p>Here, again, you can vary only features that you wish to vary. Please note that the output counterfactuals are only from the training data. If you want other counterfactuals, please use the random or genetic method.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[26]:
@@ -3251,9 +1088,17 @@ <h4>Selecting the features to vary<a class="headerlink" href="#id5" title="Perma
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
-<div class="output_area stderr docutils container">
+<div class="output_area docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:01&lt;00:00,  1.50it/s]
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [26]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_KD <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_KD</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>     query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">4</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>     features_to_vary<span style="color: rgb(98,98,98)">=</span>[<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">workclass</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">education</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">occupation</span><span style="color: rgb(175,0,0)">&#39;</span>, <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>])
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_KD&#39; is not defined
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -3264,198 +1109,22 @@ <h4>Selecting the features to vary<a class="headerlink" href="#id5" title="Perma
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-No counterfactuals found!
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [27]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 1&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-fg">----&gt; 1</span> <span class="ansi-yellow-bg">dice_exp_KD</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp_KD&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>22027</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>15788</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Doctorate</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 <section id="Selecting-the-feature-ranges">
-<h4>Selecting the feature ranges<a class="headerlink" href="#Selecting-the-feature-ranges" title="Permalink to this headline"></a></h4>
+<h4>Selecting the feature ranges<a class="headerlink" href="#Selecting-the-feature-ranges" title="Permalink to this heading"></a></h4>
 <p>Here, you can control the ranges of continuous features.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[28]:
@@ -3469,247 +1138,23 @@ <h4>Selecting the feature ranges<a class="headerlink" href="#Selecting-the-featu
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:01&lt;00:00,  1.41it/s]
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>27</td>
-      <td>Private</td>
-      <td>School</td>
-      <td>Single</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>Male</td>
-      <td>40</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-
-No counterfactuals found!
-Query instance (original outcome : 1)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>31</td>
-      <td>Self-Employed</td>
-      <td>Some-college</td>
-      <td>Married</td>
-      <td>Sales</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>60</td>
-      <td>1</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-
-Diverse Counterfactual set (new outcome: 1)
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [28]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp_KD <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp_KD</span><span style="color: rgb(98,98,98)">.</span>generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">      3</span>     query_instances, total_CFs<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(98,98,98)">5</span>, desired_class<span style="color: rgb(98,98,98)">=</span><span style="color: rgb(175,0,0)">&#34;</span><span style="color: rgb(175,0,0)">opposite</span><span style="color: rgb(175,0,0)">&#34;</span>,
+<span class="ansi-green-intense-fg ansi-bold">      4</span>     permitted_range<span style="color: rgb(98,98,98)">=</span>{<span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">age</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">30</span>, <span style="color: rgb(98,98,98)">50</span>], <span style="color: rgb(175,0,0)">&#39;</span><span style="color: rgb(175,0,0)">hours_per_week</span><span style="color: rgb(175,0,0)">&#39;</span>: [<span style="color: rgb(98,98,98)">40</span>, <span style="color: rgb(98,98,98)">60</span>]})
+<span class="ansi-green-intense-fg ansi-bold">      5</span> dice_exp_KD<span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
+
+<span class="ansi-red-fg">NameError</span>: name &#39;exp_KD&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>22027</th>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>2457</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Assoc</td>
-      <td>-</td>
-      <td>Blue-Collar</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>516</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>15831</th>
-      <td>-</td>
-      <td>Private</td>
-      <td>Bachelors</td>
-      <td>-</td>
-      <td>Professional</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-    <tr>
-      <th>22201</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Bachelors</td>
-      <td>Divorced</td>
-      <td>White-Collar</td>
-      <td>White</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 </section>
 </section>
@@ -3720,7 +1165,7 @@ <h4>Selecting the feature ranges<a class="headerlink" href="#Selecting-the-featu
           </div>
           <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
         <a href="DiCE_multiclass_classification_and_regression.html" class="btn btn-neutral float-left" title="Generating counterfactuals for multi-class classification and regression models" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
-        <a href="DiCE_with_private_data.html" class="btn btn-neutral float-right" title="Generating Counterfactual Explanations without access to training data" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
+        <a href="DiCE_with_private_data.html" class="btn btn-neutral float-right" title="Generating counterfactual explanations without access to training data" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
     </div>
 
   <hr/>
diff --git a/docs/notebooks/DiCE_multiclass_classification_and_regression.html b/docs/notebooks/DiCE_multiclass_classification_and_regression.html
index 0d85d215..f7cd4b88 100644
--- a/docs/notebooks/DiCE_multiclass_classification_and_regression.html
+++ b/docs/notebooks/DiCE_multiclass_classification_and_regression.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Generating counterfactuals for multi-class classification and regression models &mdash; DiCE 0.8 documentation</title>
+  <title>Generating counterfactuals for multi-class classification and regression models &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -54,7 +56,7 @@
 </li>
 <li class="toctree-l1"><a class="reference internal" href="#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -304,6 +306,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -312,10 +315,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -327,12 +334,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -360,7 +370,7 @@
 }
 </style>
 <section id="Generating-counterfactuals-for-multi-class-classification-and-regression-models">
-<h1>Generating counterfactuals for multi-class classification and regression models<a class="headerlink" href="#Generating-counterfactuals-for-multi-class-classification-and-regression-models" title="Permalink to this headline"></a></h1>
+<h1>Generating counterfactuals for multi-class classification and regression models<a class="headerlink" href="#Generating-counterfactuals-for-multi-class-classification-and-regression-models" title="Permalink to this heading"></a></h1>
 <p>This notebook will demonstrate how the DiCE library can be used for multiclass classification and regression for scikit-learn models. You can use any method (“random”, “kdtree”, “genetic”), just specific it in the method argument in the initialization step. The rest of the code is completely identical. For demonstration, we will be using the genetic algorithm for CFs.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
@@ -391,7 +401,7 @@ <h1>Generating counterfactuals for multi-class classification and regression mod
 </div>
 <p>We will use sklearn’s internal datasets to demonstrate DiCE’s features in this notebook</p>
 <section id="Multiclass-Classification">
-<h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classification" title="Permalink to this headline"></a></h2>
+<h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classification" title="Permalink to this heading"></a></h2>
 <p>For multiclass classification, we will use sklearn’s Iris dataset. This data set consists of 3 different types of irises’ (Setosa, Versicolour, and Virginica) petal and sepal length. More information at <a class="reference external" href="https://scikit-learn.org/stable/datasets/toy_dataset.html#iris-plants-dataset">https://scikit-learn.org/stable/datasets/toy_dataset.html#iris-plants-dataset</a></p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
@@ -586,7 +596,7 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 1/1 [00:01&lt;00:00,  1.15s/it]
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00&lt;00:00,  1.39it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -704,42 +714,42 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
     </tr>
     <tr>
       <th>0</th>
-      <td>5.0</td>
-      <td>3.7</td>
-      <td>5.7</td>
-      <td>2.1</td>
+      <td>4.7</td>
+      <td>3.8</td>
+      <td>6.6</td>
+      <td>2.3</td>
       <td>2</td>
     </tr>
     <tr>
       <th>0</th>
-      <td>5.0</td>
-      <td>4.1</td>
-      <td>6.1</td>
+      <td>4.9</td>
+      <td>3.3</td>
+      <td>6.0</td>
       <td>1.7</td>
       <td>2</td>
     </tr>
     <tr>
       <th>0</th>
-      <td>4.9</td>
-      <td>3.5</td>
-      <td>5.0</td>
-      <td>1.9</td>
+      <td>5.5</td>
+      <td>3.0</td>
+      <td>6.5</td>
+      <td>0.8</td>
       <td>2</td>
     </tr>
     <tr>
       <th>0</th>
-      <td>4.3</td>
-      <td>3.7</td>
-      <td>5.3</td>
-      <td>2.1</td>
+      <td>6.4</td>
+      <td>3.4</td>
+      <td>6.4</td>
+      <td>1.2</td>
       <td>2</td>
     </tr>
     <tr>
       <th>0</th>
-      <td>7.0</td>
+      <td>6.1</td>
       <td>3.8</td>
-      <td>6.2</td>
-      <td>1.4</td>
+      <td>6.6</td>
+      <td>2.3</td>
       <td>2</td>
     </tr>
   </tbody>
@@ -762,7 +772,7 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:02&lt;00:00,  1.42s/it]
+100%|█████████████████████████████████████████████████████████████████████████████████| 2/2 [00:01&lt;00:00,  1.83it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -904,10 +914,10 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
     </tr>
     <tr>
       <th>0</th>
-      <td>6.7</td>
-      <td>3.3</td>
-      <td>5.7</td>
-      <td>2.1</td>
+      <td>6.3</td>
+      <td>3.1</td>
+      <td>1.0</td>
+      <td>1.8</td>
       <td>2.0</td>
     </tr>
     <tr>
@@ -915,7 +925,7 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
       <td>6.7</td>
       <td>3.3</td>
       <td>5.7</td>
-      <td>2.5</td>
+      <td>2.1</td>
       <td>2.0</td>
     </tr>
   </tbody>
@@ -1019,14 +1029,6 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
       <td>1.8</td>
       <td>2.0</td>
     </tr>
-    <tr>
-      <th>0</th>
-      <td>6.5</td>
-      <td>3.2</td>
-      <td>5.0</td>
-      <td>2.0</td>
-      <td>2.0</td>
-    </tr>
     <tr>
       <th>0</th>
       <td>6.5</td>
@@ -1061,10 +1063,18 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
     </tr>
     <tr>
       <th>0</th>
-      <td>6.4</td>
-      <td>3.2</td>
-      <td>5.3</td>
-      <td>0.1</td>
+      <td>6.1</td>
+      <td>2.6</td>
+      <td>5.6</td>
+      <td>1.4</td>
+      <td>2.0</td>
+    </tr>
+    <tr>
+      <th>0</th>
+      <td>-</td>
+      <td>2.5</td>
+      <td>2.7</td>
+      <td>2.0</td>
       <td>2.0</td>
     </tr>
   </tbody>
@@ -1074,7 +1084,7 @@ <h2>Multiclass Classification<a class="headerlink" href="#Multiclass-Classificat
 </section>
 </section>
 <section id="Regression">
-<h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this headline"></a></h1>
+<h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this heading"></a></h1>
 <p>For regression, we will use sklearn’s California Housing dataset. This dataset contains California house prices. More information at <a class="reference external" href="https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_california_housing.html">https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_california_housing.html</a></p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[11]:
@@ -1296,7 +1306,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-100%|███████████████████████████████████████████████████████████████████| 2/2 [00:01&lt;00:00,  1.50it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00&lt;00:00,  2.49it/s]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -1359,7 +1369,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>2.910112</td>
       <td>38.650002</td>
       <td>-121.839996</td>
-      <td>1.44691</td>
+      <td>1.49846</td>
     </tr>
   </tbody>
 </table>
@@ -1418,7 +1428,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>2.7</td>
       <td>34.45</td>
       <td>-119.81</td>
-      <td>3.3564200999999985</td>
+      <td>3.4537603999999984</td>
     </tr>
     <tr>
       <th>0</th>
@@ -1430,7 +1440,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>2.7</td>
       <td>34.24</td>
       <td>-118.28</td>
-      <td>3.0918301</td>
+      <td>3.126689999999999</td>
     </tr>
   </tbody>
 </table>
@@ -1488,7 +1498,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>2.746479</td>
       <td>33.200001</td>
       <td>-115.599998</td>
-      <td>0.88245</td>
+      <td>0.91159</td>
     </tr>
   </tbody>
 </table>
@@ -1547,7 +1557,7 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>2.6</td>
       <td>33.61</td>
       <td>-117.92</td>
-      <td>4.96489929999999</td>
+      <td>4.98180959999999</td>
     </tr>
     <tr>
       <th>0</th>
@@ -1556,10 +1566,10 @@ <h1>Regression<a class="headerlink" href="#Regression" title="Permalink to this
       <td>4.6</td>
       <td>1.2</td>
       <td>393.0</td>
-      <td>1.6</td>
-      <td>34.01</td>
+      <td>1.2</td>
+      <td>33.97</td>
       <td>-118.47</td>
-      <td>4.039710699999995</td>
+      <td>3.890800399999997</td>
     </tr>
   </tbody>
 </table>
diff --git a/docs/notebooks/DiCE_with_advanced_options.html b/docs/notebooks/DiCE_with_advanced_options.html
index 6ec02779..fe7592b6 100644
--- a/docs/notebooks/DiCE_with_advanced_options.html
+++ b/docs/notebooks/DiCE_with_advanced_options.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Advanced options to customize Counterfactual Explanations &mdash; DiCE 0.8 documentation</title>
+  <title>Advanced options to customize Counterfactual Explanations &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -22,7 +24,7 @@
     <link rel="index" title="Index" href="../genindex.html" />
     <link rel="search" title="Search" href="../search.html" />
     <link rel="next" title="Generate feasible counterfactual explanations using a VAE" href="DiCE_getting_started_feasible.html" />
-    <link rel="prev" title="Generating Counterfactual Explanations without access to training data" href="DiCE_with_private_data.html" /> 
+    <link rel="prev" title="Generating counterfactual explanations without access to training data" href="DiCE_with_private_data.html" /> 
 </head>
 
 <body class="wy-body-for-nav"> 
@@ -51,7 +53,7 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1 current"><a class="current reference internal" href="#">Advanced options to customize Counterfactual Explanations</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="#Loading-dataset">Loading dataset</a></li>
 <li class="toctree-l2"><a class="reference internal" href="#1.-Loading-a-custom-ML-model">1. Loading a custom ML model</a></li>
@@ -308,6 +310,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -316,10 +319,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -331,12 +338,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -364,7 +374,7 @@
 }
 </style>
 <section id="Advanced-options-to-customize-Counterfactual-Explanations">
-<h1>Advanced options to customize Counterfactual Explanations<a class="headerlink" href="#Advanced-options-to-customize-Counterfactual-Explanations" title="Permalink to this headline"></a></h1>
+<h1>Advanced options to customize Counterfactual Explanations<a class="headerlink" href="#Advanced-options-to-customize-Counterfactual-Explanations" title="Permalink to this heading"></a></h1>
 <p>Here we discuss a few ways to change DiCE’s behavior.</p>
 <ul class="simple">
 <li><p>Train a custom ML model</p></li>
@@ -395,8 +405,9 @@ <h1>Advanced options to customize Counterfactual Explanations<a class="headerlin
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-2022-05-29 12:08:27.710724: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
-2022-05-29 12:08:27.710950: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
+2022-10-19 14:55:55.631881: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
+2022-10-19 14:55:55.635417: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
+2022-10-19 14:55:55.635428: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
 </pre></div></div>
 </div>
 <div class="nbinput nblast docutils container">
@@ -409,7 +420,7 @@ <h1>Advanced options to customize Counterfactual Explanations<a class="headerlin
 </div>
 </div>
 <section id="Loading-dataset">
-<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this headline"></a></h2>
+<h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalink to this heading"></a></h2>
 <p>We use “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>). For demonstration purposes, we transform the data as detailed in <strong>dice_ml.utils.helpers</strong> module.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
@@ -529,7 +540,7 @@ <h2>Loading dataset<a class="headerlink" href="#Loading-dataset" title="Permalin
 </div>
 </section>
 <section id="1.-Loading-a-custom-ML-model">
-<h2>1. Loading a custom ML model<a class="headerlink" href="#1.-Loading-a-custom-ML-model" title="Permalink to this headline"></a></h2>
+<h2>1. Loading a custom ML model<a class="headerlink" href="#1.-Loading-a-custom-ML-model" title="Permalink to this heading"></a></h2>
 <p>Below, we use an Artificial Neural Network based on Tensorflow framework.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]:
@@ -556,7 +567,7 @@ <h2>1. Loading a custom ML model<a class="headerlink" href="#1.-Loading-a-custom
 </div>
 </section>
 <section id="Generate-diverse-counterfactuals">
-<h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this headline"></a></h2>
+<h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this heading"></a></h2>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[7]:
 </pre></div>
@@ -571,10 +582,10 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-2022-05-29 12:08:36.437557: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
-2022-05-29 12:08:36.445164: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
-2022-05-29 12:08:36.445531: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-Z840): /proc/driver/nvidia/version does not exist
-2022-05-29 12:08:36.446615: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
+2022-10-19 14:56:14.394561: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
+2022-10-19 14:56:14.394614: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
+2022-10-19 14:56:14.394632: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-X1): /proc/driver/nvidia/version does not exist
+2022-10-19 14:56:14.394838: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
 </pre></div></div>
 </div>
@@ -604,12 +615,50 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+  0%|                                                                                         | 0/8 [00:00&lt;?, ?it/s]
+</pre></div></div>
+</div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 41 sec
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">AttributeError</span>                            Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [9]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">generate_counterfactuals</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">total_CFs</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">4</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">desired_class</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">opposite</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/explainer_interfaces/explainer_base.py:160</span>, in <span class="ansi-cyan-fg">ExplainerBase.generate_counterfactuals</span><span class="ansi-blue-fg">(self, query_instances, total_CFs, desired_class, desired_range, permitted_range, features_to_vary, stopping_threshold, posthoc_sparsity_param, proximity_weight, sparsity_weight, diversity_weight, categorical_penalty, posthoc_sparsity_algorithm, verbose, **kwargs)</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>     query_instances_list <span style="color: rgb(98,98,98)">=</span> query_instances
+<span class="ansi-green-intense-fg ansi-bold">    159</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> query_instance <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> tqdm(query_instances_list):
+<span class="ansi-green-fg">--&gt; 160</span>     <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">data_interface</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">set_continuous_feature_indexes</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    161</span>     res <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">    162</span>         query_instance, total_CFs,
+<span class="ansi-green-intense-fg ansi-bold">    163</span>         desired_class<span style="color: rgb(98,98,98)">=</span>desired_class,
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    170</span>         verbose<span style="color: rgb(98,98,98)">=</span>verbose,
+<span class="ansi-green-intense-fg ansi-bold">    171</span>         <span style="color: rgb(98,98,98)">*</span><span style="color: rgb(98,98,98)">*</span>kwargs)
+<span class="ansi-green-intense-fg ansi-bold">    172</span>     cf_examples_arr<span style="color: rgb(98,98,98)">.</span>append(res)
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">_BaseData.set_continuous_feature_indexes</span><span class="ansi-blue-fg">(self, query_instance)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [query_instance<span style="color: rgb(98,98,98)">.</span>columns<span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">&lt;listcomp&gt;</span><span class="ansi-blue-fg">(.0)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [<span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">columns</span><span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+<span class="ansi-red-fg">AttributeError</span>: &#39;str&#39; object has no attribute &#39;columns&#39;
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -621,162 +670,23 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.019</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [10]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># visualize the resutls</span>
+<span class="ansi-green-fg">----&gt; 2</span> <span class="ansi-yellow-bg">dice_exp</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>70.0</td>
-      <td>-</td>
-      <td>Masters</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>51.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>Self-Employed</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>47.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>36.0</td>
-      <td>-</td>
-      <td>Prof-school</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>62.0</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 <section id="2.-Changing-feature-weights">
-<h2>2. Changing feature weights<a class="headerlink" href="#2.-Changing-feature-weights" title="Permalink to this headline"></a></h2>
+<h2>2. Changing feature weights<a class="headerlink" href="#2.-Changing-feature-weights" title="Permalink to this heading"></a></h2>
 <p>It may be the case that some features are harder to change than others (e.g., education level is harder to change than working hours per week). DiCE allows input of relative difficulty in changing a feature through specifying <em>feature weights</em>. A higher feature weight means that the feature is harder to change than others. For instance, one way is to use the mean absolute deviation from the median as a measure of relative difficulty of changing a continuous feature.</p>
 <p>Median Absolute Deviation (MAD) of a continuous feature conveys the variability of the feature, and is more robust than standard deviation as is less affected by outliers and non-normality. The inverse of MAD would then imply the ease of varying the feature and is hence used as feature weights in our optimization to reflect the difficulty of changing a continuous feature. By default, DiCE computes this internally and divides the distance between continuous features by the MAD of the feature’s
 values in the training set. Let’s see what their values are by computing them below:</p>
@@ -824,12 +734,51 @@ <h2>2. Changing feature weights<a class="headerlink" href="#2.-Changing-feature-
 </pre></div>
 </div>
 </div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+  0%|                                                                                         | 0/8 [00:00&lt;?, ?it/s]
+</pre></div></div>
+</div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 44 sec
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">AttributeError</span>                            Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [13]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># generate counterfactuals</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">generate_counterfactuals</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">total_CFs</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">4</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">desired_class</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">opposite</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">      3</span> <span class="ansi-yellow-bg">                                        </span><span class="ansi-yellow-bg">feature_weights</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg">feature_weights</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/explainer_interfaces/explainer_base.py:160</span>, in <span class="ansi-cyan-fg">ExplainerBase.generate_counterfactuals</span><span class="ansi-blue-fg">(self, query_instances, total_CFs, desired_class, desired_range, permitted_range, features_to_vary, stopping_threshold, posthoc_sparsity_param, proximity_weight, sparsity_weight, diversity_weight, categorical_penalty, posthoc_sparsity_algorithm, verbose, **kwargs)</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>     query_instances_list <span style="color: rgb(98,98,98)">=</span> query_instances
+<span class="ansi-green-intense-fg ansi-bold">    159</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> query_instance <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> tqdm(query_instances_list):
+<span class="ansi-green-fg">--&gt; 160</span>     <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">data_interface</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">set_continuous_feature_indexes</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    161</span>     res <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">    162</span>         query_instance, total_CFs,
+<span class="ansi-green-intense-fg ansi-bold">    163</span>         desired_class<span style="color: rgb(98,98,98)">=</span>desired_class,
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    170</span>         verbose<span style="color: rgb(98,98,98)">=</span>verbose,
+<span class="ansi-green-intense-fg ansi-bold">    171</span>         <span style="color: rgb(98,98,98)">*</span><span style="color: rgb(98,98,98)">*</span>kwargs)
+<span class="ansi-green-intense-fg ansi-bold">    172</span>     cf_examples_arr<span style="color: rgb(98,98,98)">.</span>append(res)
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">_BaseData.set_continuous_feature_indexes</span><span class="ansi-blue-fg">(self, query_instance)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [query_instance<span style="color: rgb(98,98,98)">.</span>columns<span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">&lt;listcomp&gt;</span><span class="ansi-blue-fg">(.0)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [<span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">columns</span><span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+<span class="ansi-red-fg">AttributeError</span>: &#39;str&#39; object has no attribute &#39;columns&#39;
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -841,165 +790,26 @@ <h2>2. Changing feature weights<a class="headerlink" href="#2.-Changing-feature-
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.019</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [14]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># visualize the resutls</span>
+<span class="ansi-green-fg">----&gt; 2</span> <span class="ansi-yellow-bg">dice_exp</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>60.0</td>
-      <td>Self-Employed</td>
-      <td>Prof-school</td>
-      <td>Married</td>
-      <td>Professional</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>38.0</td>
-      <td>Other/Unknown</td>
-      <td>Assoc</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>55.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>90.0</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>99.0</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>70.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>White-Collar</td>
-      <td>Other</td>
-      <td>Male</td>
-      <td>73.0</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>Note that we transform continuous features and one-hot-encode categorical features to fall between 0 and 1 in order to handle relative scale of features. However, this also means that the relative ease of changing continuous features is higher than categorical features when the total number of continuous features are very less compared to the total number of categories of all categorical variables combined. This is reflected in the above table where continuous features (<em>age</em> and
 <em>hours_per_week</em>) have been varied to reach their extreme values (<em>range of age: [17, 90]</em>; <em>range of hours_per_week: [1, 99]</em>) for most of the counterfactuals. This is the reason why the distances are divided by a scaling factor. Deviation from the median provides a robust measure of the variability of a feature’s values, and thus dividing by the MAD allows us to capture the relative prevalence of observing the feature at a particular value (see our
 <a class="reference external" href="https://arxiv.org/pdf/1905.07697.pdf">paper</a> for more details).</p>
 </section>
 <section id="3.-Trading-off-between-proximity-and-diversity-goals">
-<h2>3. Trading off between proximity and diversity goals<a class="headerlink" href="#3.-Trading-off-between-proximity-and-diversity-goals" title="Permalink to this headline"></a></h2>
+<h2>3. Trading off between proximity and diversity goals<a class="headerlink" href="#3.-Trading-off-between-proximity-and-diversity-goals" title="Permalink to this heading"></a></h2>
 <p>We acknowledge that not all counterfactual explanations may be feasible for a user. In general, counterfactuals closer to an individual’s profile will be more feasible. Diversity is also important to help an individual choose between multiple possible options. DiCE allows tunable parameters <em>proximity_weight</em> (default: 0.5) and <em>diversity_weight</em> (default: 1.0) to handle proximity and diversity respectively. Below, we increase the proximity weight and see how the counterfactuals change.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[15]:
@@ -1011,12 +821,51 @@ <h2>3. Trading off between proximity and diversity goals<a class="headerlink" hr
 </pre></div>
 </div>
 </div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+  0%|                                                                                         | 0/8 [00:00&lt;?, ?it/s]
+</pre></div></div>
+</div>
 <div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 01 min 06 sec
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">AttributeError</span>                            Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [15]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># change proximity_weight from default value of 0.5 to 1.5</span>
+<span class="ansi-green-fg">----&gt; 2</span> dice_exp <span style="color: rgb(98,98,98)">=</span> <span class="ansi-yellow-bg">exp</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">generate_counterfactuals</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">total_CFs</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">4</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">desired_class</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">opposite</span><span class="ansi-yellow-bg" style="color: rgb(175,0,0)">&#34;</span><span class="ansi-yellow-bg">,</span>
+<span class="ansi-green-intense-fg ansi-bold">      3</span> <span class="ansi-yellow-bg">                                        </span><span class="ansi-yellow-bg">proximity_weight</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">1.5</span><span class="ansi-yellow-bg">,</span><span class="ansi-yellow-bg"> </span><span class="ansi-yellow-bg">diversity_weight</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">=</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">1.0</span><span class="ansi-yellow-bg">)</span>
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/explainer_interfaces/explainer_base.py:160</span>, in <span class="ansi-cyan-fg">ExplainerBase.generate_counterfactuals</span><span class="ansi-blue-fg">(self, query_instances, total_CFs, desired_class, desired_range, permitted_range, features_to_vary, stopping_threshold, posthoc_sparsity_param, proximity_weight, sparsity_weight, diversity_weight, categorical_penalty, posthoc_sparsity_algorithm, verbose, **kwargs)</span>
+<span class="ansi-green-intense-fg ansi-bold">    158</span>     query_instances_list <span style="color: rgb(98,98,98)">=</span> query_instances
+<span class="ansi-green-intense-fg ansi-bold">    159</span> <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> query_instance <span class="ansi-bold" style="color: rgb(175,0,255)">in</span> tqdm(query_instances_list):
+<span class="ansi-green-fg">--&gt; 160</span>     <span class="ansi-yellow-bg" style="color: rgb(0,135,0)">self</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">data_interface</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">set_continuous_feature_indexes</span><span class="ansi-yellow-bg">(</span><span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg">)</span>
+<span class="ansi-green-intense-fg ansi-bold">    161</span>     res <span style="color: rgb(98,98,98)">=</span> <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>_generate_counterfactuals(
+<span class="ansi-green-intense-fg ansi-bold">    162</span>         query_instance, total_CFs,
+<span class="ansi-green-intense-fg ansi-bold">    163</span>         desired_class<span style="color: rgb(98,98,98)">=</span>desired_class,
+<span class="ansi-green-fg">   (...)</span>
+<span class="ansi-green-intense-fg ansi-bold">    170</span>         verbose<span style="color: rgb(98,98,98)">=</span>verbose,
+<span class="ansi-green-intense-fg ansi-bold">    171</span>         <span style="color: rgb(98,98,98)">*</span><span style="color: rgb(98,98,98)">*</span>kwargs)
+<span class="ansi-green-intense-fg ansi-bold">    172</span>     cf_examples_arr<span style="color: rgb(98,98,98)">.</span>append(res)
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">_BaseData.set_continuous_feature_indexes</span><span class="ansi-blue-fg">(self, query_instance)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [query_instance<span style="color: rgb(98,98,98)">.</span>columns<span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+File <span class="ansi-green-fg">/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/base_data_interface.py:30</span>, in <span class="ansi-cyan-fg">&lt;listcomp&gt;</span><span class="ansi-blue-fg">(.0)</span>
+<span class="ansi-green-intense-fg ansi-bold">     28</span> <span class="ansi-bold" style="color: rgb(0,135,0)">def</span> <span style="color: rgb(0,0,255)">set_continuous_feature_indexes</span>(<span style="color: rgb(0,135,0)">self</span>, query_instance):
+<span class="ansi-green-intense-fg ansi-bold">     29</span>     <span style="color: rgb(175,0,0)">&#34;&#34;&#34;Remaps continuous feature indices based on the query instance&#34;&#34;&#34;</span>
+<span class="ansi-green-fg">---&gt; 30</span>     <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_indexes <span style="color: rgb(98,98,98)">=</span> [<span class="ansi-yellow-bg">query_instance</span><span class="ansi-yellow-bg" style="color: rgb(98,98,98)">.</span><span class="ansi-yellow-bg">columns</span><span style="color: rgb(98,98,98)">.</span>get_loc(name) <span class="ansi-bold" style="color: rgb(0,135,0)">for</span> name <span class="ansi-bold" style="color: rgb(175,0,255)">in</span>
+<span class="ansi-green-intense-fg ansi-bold">     31</span>                                        <span style="color: rgb(0,135,0)">self</span><span style="color: rgb(98,98,98)">.</span>continuous_feature_names]
+
+<span class="ansi-red-fg">AttributeError</span>: &#39;str&#39; object has no attribute &#39;columns&#39;
 </pre></div></div>
 </div>
 <div class="nbinput docutils container">
@@ -1028,159 +877,20 @@ <h2>3. Trading off between proximity and diversity goals<a class="headerlink" hr
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.019</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [16]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># visualize the resutls</span>
+<span class="ansi-green-fg">----&gt; 2</span> <span class="ansi-yellow-bg">dice_exp</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>30.0</td>
-      <td>Self-Employed</td>
-      <td>Prof-school</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>35.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>49.0</td>
-      <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 <p>As we see from above table, both continuous and categorical features are more closer to the original query instance and the counterfactuals are also less diverse than before.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[17]:
@@ -1191,159 +901,20 @@ <h2>3. Trading off between proximity and diversity goals<a class="headerlink" hr
 </pre></div>
 </div>
 </div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area docutils container">
-<div class="highlight"><pre>
-Query instance (original outcome : 0)
-</pre></div></div>
-</div>
-<div class="nboutput docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>22.0</td>
-      <td>Private</td>
-      <td>HS-grad</td>
-      <td>Single</td>
-      <td>Service</td>
-      <td>White</td>
-      <td>Female</td>
-      <td>45.0</td>
-      <td>0.019</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
-<div class="nboutput docutils container">
+<div class="nboutput nblast docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+<span class="ansi-red-fg">---------------------------------------------------------------------------</span>
+<span class="ansi-red-fg">NameError</span>                                 Traceback (most recent call last)
+Input <span class="ansi-green-fg">In [17]</span>, in <span class="ansi-cyan-fg">&lt;cell line: 2&gt;</span><span class="ansi-blue-fg">()</span>
+<span class="ansi-green-intense-fg ansi-bold">      1</span> <span style="color: rgb(95,135,135)"># visualize the resutls</span>
+<span class="ansi-green-fg">----&gt; 2</span> <span class="ansi-yellow-bg">dice_exp</span><span style="color: rgb(98,98,98)">.</span>visualize_as_dataframe(show_only_changes<span style="color: rgb(98,98,98)">=</span><span class="ansi-bold" style="color: rgb(0,135,0)">True</span>)
 
-Diverse Counterfactual set (new outcome: 1.0)
+<span class="ansi-red-fg">NameError</span>: name &#39;dice_exp&#39; is not defined
 </pre></div></div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area rendered_html docutils container">
-<div>
-<style scoped>
-    .dataframe tbody tr th:only-of-type {
-        vertical-align: middle;
-    }
-
-    .dataframe tbody tr th {
-        vertical-align: top;
-    }
-
-    .dataframe thead th {
-        text-align: right;
-    }
-</style>
-<table border="1" class="dataframe">
-  <thead>
-    <tr style="text-align: right;">
-      <th></th>
-      <th>age</th>
-      <th>workclass</th>
-      <th>education</th>
-      <th>marital_status</th>
-      <th>occupation</th>
-      <th>race</th>
-      <th>gender</th>
-      <th>hours_per_week</th>
-      <th>income</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr>
-      <th>0</th>
-      <td>30.0</td>
-      <td>Self-Employed</td>
-      <td>Prof-school</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>1</th>
-      <td>-</td>
-      <td>-</td>
-      <td>Doctorate</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>2</th>
-      <td>35.0</td>
-      <td>-</td>
-      <td>-</td>
-      <td>Married</td>
-      <td>White-Collar</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-    <tr>
-      <th>3</th>
-      <td>49.0</td>
-      <td>-</td>
-      <td>Masters</td>
-      <td>Married</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>-</td>
-      <td>0</td>
-    </tr>
-  </tbody>
-</table>
-</div></div>
-</div>
 </section>
 </section>
 
@@ -1351,7 +922,7 @@ <h2>3. Trading off between proximity and diversity goals<a class="headerlink" hr
            </div>
           </div>
           <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
-        <a href="DiCE_with_private_data.html" class="btn btn-neutral float-left" title="Generating Counterfactual Explanations without access to training data" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
+        <a href="DiCE_with_private_data.html" class="btn btn-neutral float-left" title="Generating counterfactual explanations without access to training data" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
         <a href="DiCE_getting_started_feasible.html" class="btn btn-neutral float-right" title="Generate feasible counterfactual explanations using a VAE" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
     </div>
 
diff --git a/docs/notebooks/DiCE_with_private_data.html b/docs/notebooks/DiCE_with_private_data.html
index 76732160..35bb489a 100644
--- a/docs/notebooks/DiCE_with_private_data.html
+++ b/docs/notebooks/DiCE_with_private_data.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Generating Counterfactual Explanations without access to training data &mdash; DiCE 0.8 documentation</title>
+  <title>Generating counterfactual explanations without access to training data &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
         <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
         <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
@@ -51,10 +53,16 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1 current"><a class="current reference internal" href="#">Generating Counterfactual Explanations without access to training data</a><ul>
-<li class="toctree-l2"><a class="reference internal" href="#Defining-meta-data">Defining meta data</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#Loading-trained-ML-model">Loading trained ML model</a></li>
-<li class="toctree-l2"><a class="reference internal" href="#Generate-diverse-counterfactuals">Generate diverse counterfactuals</a></li>
+<li class="toctree-l1 current"><a class="current reference internal" href="#">Generating counterfactual explanations without access to training data</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="#Defining-meta-data">Defining meta data</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#Explaining-pre-trained-sklearn-models">Explaining pre-trained sklearn models</a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#Generate-diverse-counterfactuals">Generate diverse counterfactuals</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="#Explaining-pre-trained-deep-learning-models">Explaining pre-trained deep learning models</a></li>
+</ul>
+</li>
+<li class="toctree-l2"><a class="reference internal" href="#id1">Generate diverse counterfactuals</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
@@ -81,7 +89,7 @@
   <ul class="wy-breadcrumbs">
       <li><a href="../index.html" class="icon icon-home"></a> &raquo;</li>
           <li><a href="nb_index.html">&lt;no title&gt;</a> &raquo;</li>
-      <li>Generating Counterfactual Explanations without access to training data</li>
+      <li>Generating counterfactual explanations without access to training data</li>
       <li class="wy-breadcrumbs-aside">
             <a href="../_sources/notebooks/DiCE_with_private_data.ipynb.txt" rel="nofollow"> View page source</a>
       </li>
@@ -306,6 +314,7 @@
 }
 
 /* Some additional styling taken form the Jupyter notebook CSS */
+.jp-RenderedHTMLCommon table,
 div.rendered_html table {
   border: none;
   border-collapse: collapse;
@@ -314,10 +323,14 @@
   font-size: 12px;
   table-layout: fixed;
 }
+.jp-RenderedHTMLCommon thead,
 div.rendered_html thead {
   border-bottom: 1px solid black;
   vertical-align: bottom;
 }
+.jp-RenderedHTMLCommon tr,
+.jp-RenderedHTMLCommon th,
+.jp-RenderedHTMLCommon td,
 div.rendered_html tr,
 div.rendered_html th,
 div.rendered_html td {
@@ -329,12 +342,15 @@
   max-width: none;
   border: none;
 }
+.jp-RenderedHTMLCommon th,
 div.rendered_html th {
   font-weight: bold;
 }
+.jp-RenderedHTMLCommon tbody tr:nth-child(odd),
 div.rendered_html tbody tr:nth-child(odd) {
   background: #f5f5f5;
 }
+.jp-RenderedHTMLCommon tbody tr:hover,
 div.rendered_html tbody tr:hover {
   background: rgba(66, 165, 245, 0.2);
 }
@@ -361,32 +377,20 @@
     text-align: unset;
 }
 </style>
-<section id="Generating-Counterfactual-Explanations-without-access-to-training-data">
-<h1>Generating Counterfactual Explanations without access to training data<a class="headerlink" href="#Generating-Counterfactual-Explanations-without-access-to-training-data" title="Permalink to this headline"></a></h1>
+<section id="Generating-counterfactual-explanations-without-access-to-training-data">
+<h1>Generating counterfactual explanations without access to training data<a class="headerlink" href="#Generating-counterfactual-explanations-without-access-to-training-data" title="Permalink to this heading"></a></h1>
 <p>If only the trained model is available but not the training data, DiCE can still be used to generate counterfactual explanations. Below we show an example where DiCE uses only basic metadata about each feature used in the ML model.</p>
-<div class="nbinput docutils container">
+<div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[1]:
 </pre></div>
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># import DiCE</span>
+<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
 <span class="kn">import</span> <span class="nn">dice_ml</span>
 <span class="kn">from</span> <span class="nn">dice_ml.utils</span> <span class="kn">import</span> <span class="n">helpers</span>  <span class="c1"># helper functions</span>
-
-<span class="c1"># supress deprecation warnings from TF</span>
-<span class="kn">import</span> <span class="nn">tensorflow</span> <span class="k">as</span> <span class="nn">tf</span>
-<span class="n">tf</span><span class="o">.</span><span class="n">compat</span><span class="o">.</span><span class="n">v1</span><span class="o">.</span><span class="n">logging</span><span class="o">.</span><span class="n">set_verbosity</span><span class="p">(</span><span class="n">tf</span><span class="o">.</span><span class="n">compat</span><span class="o">.</span><span class="n">v1</span><span class="o">.</span><span class="n">logging</span><span class="o">.</span><span class="n">ERROR</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput nblast docutils container">
-<div class="prompt empty docutils container">
-</div>
-<div class="output_area stderr docutils container">
-<div class="highlight"><pre>
-2022-05-29 12:11:38.503225: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
-2022-05-29 12:11:38.503642: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
-</pre></div></div>
-</div>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[2]:
 </pre></div>
@@ -397,49 +401,45 @@ <h1>Generating Counterfactual Explanations without access to training data<a cla
 </div>
 </div>
 <section id="Defining-meta-data">
-<h2>Defining meta data<a class="headerlink" href="#Defining-meta-data" title="Permalink to this headline"></a></h2>
+<h2>Defining meta data<a class="headerlink" href="#Defining-meta-data" title="Permalink to this heading"></a></h2>
 <p>We simulate “adult” income dataset from UCI Machine Learning Repository (<a class="reference external" href="https://archive.ics.uci.edu/ml/datasets/adult">https://archive.ics.uci.edu/ml/datasets/adult</a>) by providing only meta information about the data: range is provided for continuous features and categories are provided for categorical features. Please note for Python&lt;=3.6, “features” parameter should be provided as an OrderedDict in the same order that was used to train the ML model.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">d</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Data</span><span class="p">(</span><span class="n">features</span><span class="o">=</span><span class="p">{</span>
-    <span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">17</span><span class="p">,</span> <span class="mi">90</span><span class="p">],</span>
-    <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Government&#39;</span><span class="p">,</span> <span class="s1">&#39;Other/Unknown&#39;</span><span class="p">,</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span> <span class="s1">&#39;Self-Employed&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Assoc&#39;</span><span class="p">,</span> <span class="s1">&#39;Bachelors&#39;</span><span class="p">,</span> <span class="s1">&#39;Doctorate&#39;</span><span class="p">,</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span> <span class="s1">&#39;Masters&#39;</span><span class="p">,</span> <span class="s1">&#39;Prof-school&#39;</span><span class="p">,</span> <span class="s1">&#39;School&#39;</span><span class="p">,</span> <span class="s1">&#39;Some-college&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Divorced&#39;</span><span class="p">,</span> <span class="s1">&#39;Married&#39;</span><span class="p">,</span> <span class="s1">&#39;Separated&#39;</span><span class="p">,</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span> <span class="s1">&#39;Widowed&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Blue-Collar&#39;</span><span class="p">,</span> <span class="s1">&#39;Other/Unknown&#39;</span><span class="p">,</span> <span class="s1">&#39;Professional&#39;</span><span class="p">,</span> <span class="s1">&#39;Sales&#39;</span><span class="p">,</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span> <span class="s1">&#39;White-Collar&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Other&#39;</span><span class="p">,</span> <span class="s1">&#39;White&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Female&#39;</span><span class="p">,</span> <span class="s1">&#39;Male&#39;</span><span class="p">],</span>
-    <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">99</span><span class="p">]},</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">d</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Data</span><span class="p">(</span><span class="n">features</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">17</span><span class="p">,</span> <span class="mi">90</span><span class="p">],</span>
+                           <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Government&#39;</span><span class="p">,</span> <span class="s1">&#39;Other/Unknown&#39;</span><span class="p">,</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span> <span class="s1">&#39;Self-Employed&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Assoc&#39;</span><span class="p">,</span> <span class="s1">&#39;Bachelors&#39;</span><span class="p">,</span> <span class="s1">&#39;Doctorate&#39;</span><span class="p">,</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span> <span class="s1">&#39;Masters&#39;</span><span class="p">,</span>
+                                         <span class="s1">&#39;Prof-school&#39;</span><span class="p">,</span> <span class="s1">&#39;School&#39;</span><span class="p">,</span> <span class="s1">&#39;Some-college&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Divorced&#39;</span><span class="p">,</span> <span class="s1">&#39;Married&#39;</span><span class="p">,</span> <span class="s1">&#39;Separated&#39;</span><span class="p">,</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span> <span class="s1">&#39;Widowed&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Blue-Collar&#39;</span><span class="p">,</span> <span class="s1">&#39;Other/Unknown&#39;</span><span class="p">,</span> <span class="s1">&#39;Professional&#39;</span><span class="p">,</span> <span class="s1">&#39;Sales&#39;</span><span class="p">,</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span> <span class="s1">&#39;White-Collar&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Other&#39;</span><span class="p">,</span> <span class="s1">&#39;White&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="p">[</span><span class="s1">&#39;Female&#39;</span><span class="p">,</span> <span class="s1">&#39;Male&#39;</span><span class="p">],</span>
+                           <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">99</span><span class="p">]},</span>
                  <span class="n">outcome_name</span><span class="o">=</span><span class="s1">&#39;income&#39;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-</section>
-<section id="Loading-trained-ML-model">
-<h2>Loading trained ML model<a class="headerlink" href="#Loading-trained-ML-model" title="Permalink to this headline"></a></h2>
-<p>Below, we use a trained ML model which produces high accuracy on test datasets, comparable to other popular baselines. This sample trained model comes in-built with our package.</p>
-<p>The variable <em>backend</em> below indicates the implementation type of DiCE we want to use. We use TensorFlow 1.x in the notebooks with backend=’TF1’. You can set backend to ‘TF2’ or ‘PYT’ to use DiCE with TensorFlow 2.x or with PyTorch respectively. We want to note that the time required to find counterfactuals with Tensorflow 2.x’s eager style of execution is significantly greater than that with TensorFlow 1.x’s graph execution.</p>
+<section id="Explaining-pre-trained-sklearn-models">
+<h3>Explaining pre-trained sklearn models<a class="headerlink" href="#Explaining-pre-trained-sklearn-models" title="Permalink to this heading"></a></h3>
+<p>We first explain a RandomForest model that has been pre-trained on the Adult dataset.</p>
 <div class="nbinput nblast docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[4]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;TF&#39;</span><span class="o">+</span><span class="n">tf</span><span class="o">.</span><span class="n">__version__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>  <span class="c1"># TF1</span>
-<span class="n">ML_modelpath</span> <span class="o">=</span> <span class="n">helpers</span><span class="o">.</span><span class="n">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
-<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;sklearn&#39;</span>
+<span class="n">sk_modelpath</span> <span class="o">=</span> <span class="n">helpers</span><span class="o">.</span><span class="n">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>  <span class="c1"># pretrained model</span>
+<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">sk_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-</section>
-<section id="Generate-diverse-counterfactuals">
-<h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this headline"></a></h2>
+<p>The next two steps are the same as when using DiCE with training data. We specify the <code class="docutils literal notranslate"><span class="pre">random</span></code> algorithm and provide an input query instance.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]:
 </pre></div>
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># initiate DiCE</span>
-<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">)</span>
+<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;genetic&quot;</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
@@ -448,11 +448,21 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </div>
 <div class="output_area stderr docutils container">
 <div class="highlight"><pre>
-2022-05-29 12:11:59.202814: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
-2022-05-29 12:11:59.203128: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
-2022-05-29 12:11:59.203353: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-Z840): /proc/driver/nvidia/version does not exist
-2022-05-29 12:11:59.204072: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
-To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator OneHotEncoder from version 1.1.1 when using version 1.0.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/modules/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator Pipeline from version 1.1.1 when using version 1.0.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/modules/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator ColumnTransformer from version 1.1.1 when using version 1.0.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/modules/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 1.1.1 when using version 1.0.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/modules/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/home/amshar/python-envs/v3.8dowhy/lib/python3.8/site-packages/sklearn/base.py:329: UserWarning: Trying to unpickle estimator RandomForestClassifier from version 1.1.1 when using version 1.0.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/modules/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
 </pre></div></div>
 </div>
 <div class="nbinput nblast docutils container">
@@ -460,39 +470,277 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </pre></div>
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># query instance in the form of a dictionary; keys: feature name, values: feature value</span>
-<span class="n">query_instance</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">22</span><span class="p">,</span>
-                  <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="s1">&#39;White&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="s1">&#39;Female&#39;</span><span class="p">,</span>
-                  <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="mi">45</span><span class="p">}</span>
+<span class="n">query_instance</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">({</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">22</span><span class="p">,</span>
+                               <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="s1">&#39;White&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="s1">&#39;Female&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="mi">45</span><span class="p">},</span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
 </pre></div>
 </div>
 </div>
+</section>
+</section>
+<section id="Generate-diverse-counterfactuals">
+<h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-diverse-counterfactuals" title="Permalink to this heading"></a></h2>
+<p>The initialization needs to be provided as <code class="docutils literal notranslate"><span class="pre">random</span></code> since the default <code class="docutils literal notranslate"><span class="pre">kdtree</span></code> is not supported for private data.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[7]:
 </pre></div>
 </div>
 <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
-<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">,</span>
+                                        <span class="n">initialization</span><span class="o">=</span><span class="s2">&quot;random&quot;</span><span class="p">)</span>
+<span class="c1"># visualize the results</span>
+<span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
 </div>
-<div class="nboutput nblast docutils container">
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+100%|█████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02&lt;00:00,  2.16s/it]
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
 <div class="prompt empty docutils container">
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-Diverse Counterfactuals found! total time taken: 00 min 43 sec
+Query instance (original outcome : 0)
 </pre></div></div>
 </div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>22</td>
+      <td>Private</td>
+      <td>HS-grad</td>
+      <td>Single</td>
+      <td>Service</td>
+      <td>White</td>
+      <td>Female</td>
+      <td>45</td>
+      <td>0</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area docutils container">
+<div class="highlight"><pre>
+
+Diverse Counterfactual set without sparsity correction since only metadata about each  feature is available (new outcome: 1)
+</pre></div></div>
+</div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area rendered_html docutils container">
+<div>
+<style scoped>
+    .dataframe tbody tr th:only-of-type {
+        vertical-align: middle;
+    }
+
+    .dataframe tbody tr th {
+        vertical-align: top;
+    }
+
+    .dataframe thead th {
+        text-align: right;
+    }
+</style>
+<table border="1" class="dataframe">
+  <thead>
+    <tr style="text-align: right;">
+      <th></th>
+      <th>age</th>
+      <th>workclass</th>
+      <th>education</th>
+      <th>marital_status</th>
+      <th>occupation</th>
+      <th>race</th>
+      <th>gender</th>
+      <th>hours_per_week</th>
+      <th>income</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <th>0</th>
+      <td>24.0</td>
+      <td>Government</td>
+      <td>Assoc</td>
+      <td>-</td>
+      <td>Professional</td>
+      <td>-</td>
+      <td>Male</td>
+      <td>44.0</td>
+      <td>1</td>
+    </tr>
+    <tr>
+      <th>0</th>
+      <td>17.0</td>
+      <td>Self-Employed</td>
+      <td>Masters</td>
+      <td>Separated</td>
+      <td>White-Collar</td>
+      <td>-</td>
+      <td>Male</td>
+      <td>-</td>
+      <td>1</td>
+    </tr>
+    <tr>
+      <th>0</th>
+      <td>28.0</td>
+      <td>Self-Employed</td>
+      <td>Masters</td>
+      <td>Widowed</td>
+      <td>White-Collar</td>
+      <td>-</td>
+      <td>Male</td>
+      <td>-</td>
+      <td>1</td>
+    </tr>
+    <tr>
+      <th>0</th>
+      <td>17.0</td>
+      <td>Other/Unknown</td>
+      <td>Masters</td>
+      <td>-</td>
+      <td>Sales</td>
+      <td>-</td>
+      <td>-</td>
+      <td>89.0</td>
+      <td>1</td>
+    </tr>
+  </tbody>
+</table>
+</div></div>
+</div>
+<section id="Explaining-pre-trained-deep-learning-models">
+<h3>Explaining pre-trained deep learning models<a class="headerlink" href="#Explaining-pre-trained-deep-learning-models" title="Permalink to this heading"></a></h3>
+<p>We can also use a trained model based on tensorflow or pytorch. Below, we use a trained ML model which produces high accuracy on test datasets, comparable to other popular baselines. This sample trained model comes in-built with our package.</p>
+<p>The variable <em>backend</em> below indicates the implementation type of DiCE we want to use. We use TensorFlow 2 in the notebooks with backend=‘TF2’. You can set backend to ‘TF1’ or ‘PYT’ to use DiCE with TensorFlow 1.x or with PyTorch respectively. We want to note that the time required to find counterfactuals with Tensorflow 2.x’s eager style of execution is significantly greater than that with TensorFlow 1.x’s graph execution.</p>
 <div class="nbinput docutils container">
 <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[8]:
 </pre></div>
 </div>
-<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># visualize the results</span>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">tensorflow</span> <span class="k">as</span> <span class="nn">tf</span>  <span class="c1"># noqa</span>
+
+<span class="n">backend</span> <span class="o">=</span> <span class="s1">&#39;TF&#39;</span> <span class="o">+</span> <span class="n">tf</span><span class="o">.</span><span class="n">__version__</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>  <span class="c1"># TF2</span>
+<span class="n">ML_modelpath</span> <span class="o">=</span> <span class="n">helpers</span><span class="o">.</span><span class="n">get_adult_income_modelpath</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span>
+<span class="n">m</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Model</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">ML_modelpath</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">,</span> <span class="n">func</span><span class="o">=</span><span class="s2">&quot;ohe-min-max&quot;</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+2022-10-19 14:56:24.988801: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
+2022-10-19 14:56:24.992079: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcudart.so.11.0&#39;; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
+2022-10-19 14:56:24.992092: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
+</pre></div></div>
+</div>
+<div class="nbinput docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[9]:
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># initiate DiCE</span>
+<span class="n">exp</span> <span class="o">=</span> <span class="n">dice_ml</span><span class="o">.</span><span class="n">Dice</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;gradient&quot;</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+<div class="nboutput nblast docutils container">
+<div class="prompt empty docutils container">
+</div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+2022-10-19 14:56:26.820933: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library &#39;libcuda.so.1&#39;; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
+2022-10-19 14:56:26.820983: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
+2022-10-19 14:56:26.821002: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (AMSHAR-X1): /proc/driver/nvidia/version does not exist
+2022-10-19 14:56:26.821194: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F AVX512_VNNI FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+</pre></div></div>
+</div>
+<div class="nbinput nblast docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]:
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># query instance in the form of a dictionary; keys: feature name, values: feature value</span>
+<span class="n">query_instance</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">({</span><span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="mi">22</span><span class="p">,</span>
+                               <span class="s1">&#39;workclass&#39;</span><span class="p">:</span> <span class="s1">&#39;Private&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;education&#39;</span><span class="p">:</span> <span class="s1">&#39;HS-grad&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;marital_status&#39;</span><span class="p">:</span> <span class="s1">&#39;Single&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;occupation&#39;</span><span class="p">:</span> <span class="s1">&#39;Service&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;race&#39;</span><span class="p">:</span> <span class="s1">&#39;White&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;gender&#39;</span><span class="p">:</span> <span class="s1">&#39;Female&#39;</span><span class="p">,</span>
+                               <span class="s1">&#39;hours_per_week&#39;</span><span class="p">:</span> <span class="mi">45</span><span class="p">},</span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
+</pre></div>
+</div>
+</div>
+</section>
+</section>
+<section id="id1">
+<h2>Generate diverse counterfactuals<a class="headerlink" href="#id1" title="Permalink to this heading"></a></h2>
+<div class="nbinput docutils container">
+<div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[11]:
+</pre></div>
+</div>
+<div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># generate counterfactuals</span>
+<span class="n">dice_exp</span> <span class="o">=</span> <span class="n">exp</span><span class="o">.</span><span class="n">generate_counterfactuals</span><span class="p">(</span><span class="n">query_instance</span><span class="p">,</span> <span class="n">total_CFs</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">desired_class</span><span class="o">=</span><span class="s2">&quot;opposite&quot;</span><span class="p">)</span>
+<span class="c1"># visualize the results</span>
 <span class="n">dice_exp</span><span class="o">.</span><span class="n">visualize_as_dataframe</span><span class="p">(</span><span class="n">show_only_changes</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
@@ -500,8 +748,18 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 <div class="nboutput docutils container">
 <div class="prompt empty docutils container">
 </div>
+<div class="output_area stderr docutils container">
+<div class="highlight"><pre>
+/mnt/c/Users/amshar/code/dice/dice_ml/data_interfaces/private_data_interface.py:382: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
+  temp = ohe_base_df.append(query_instance, ignore_index=True, sort=False)
+</pre></div></div>
+</div>
+<div class="nboutput docutils container">
+<div class="prompt empty docutils container">
+</div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
+Diverse Counterfactuals found! total time taken: 00 min 24 sec
 Query instance (original outcome : 0)
 </pre></div></div>
 </div>
@@ -561,7 +819,7 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 <div class="output_area docutils container">
 <div class="highlight"><pre>
 
-Diverse Counterfactual set without sparsity correction since only metadata about each  feature is available (new outcome:  1.0
+Diverse Counterfactual set without sparsity correction since only metadata about each  feature is available (new outcome: 1)
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -650,9 +908,9 @@ <h2>Generate diverse counterfactuals<a class="headerlink" href="#Generate-divers
 </table>
 </div></div>
 </div>
-<p>When the training data is available, by default, the distance between two values of a continuous feature is scaled by the inverse median absolute deviation (MAD) of the feature using the training data. This is done to capture the relative prevalence of observing a continuous feature at a particular value, as discussed in <a class="reference external" href="https://arxiv.org/pdf/1905.07697.pdf">our paper</a>. However, when there is no access to the training data, as in the above case, no scaling is done and hence all features are
-weighted equally in the normalized form. As a result, the counterfactuals generated above are different from those in <a class="reference internal" href="DiCE_getting_started.html"><span class="doc">DiCE_getting_started</span></a> notebook where the training data was available. Nonetheless, you can manually provide the scaling constants through a parameter <em>feature_weights</em> to the <em>generate_counterfactuals()</em> method as shown in this <a class="reference internal" href="DiCE_with_advanced_options.html"><span class="doc">advanced notebook</span></a>, or you can provide the MADs directly to the data interface
-<em>dice_ml.Data</em> if you know them.</p>
+<p><strong>Note on weighing different features:</strong> When the training data is available, by default, the distance between two values of a continuous feature is scaled by the inverse median absolute deviation (MAD) of the feature using the training data. This is done to capture the relative prevalence of observing a continuous feature at a particular value, as discussed in <a class="reference external" href="https://arxiv.org/pdf/1905.07697.pdf">our paper</a>. However, when there is no access to the training data, as in the above case, no
+scaling is done and hence all features are weighted equally in the normalized form. As a result, the counterfactuals generated above are different from those in <a class="reference internal" href="DiCE_getting_started.html"><span class="doc">DiCE_getting_started</span></a> notebook where the training data was available. Nonetheless, you can manually provide the scaling constants through a parameter <em>feature_weights</em> to the <em>generate_counterfactuals()</em> method as shown in this <a class="reference internal" href="DiCE_with_advanced_options.html"><span class="doc">advanced notebook</span></a>, or you can provide
+the MADs directly to the data interface <em>dice_ml.Data</em> if you know them.</p>
 </section>
 </section>
 
diff --git a/docs/notebooks/nb_index.html b/docs/notebooks/nb_index.html
index 8d1d6522..9684f64b 100644
--- a/docs/notebooks/nb_index.html
+++ b/docs/notebooks/nb_index.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>&lt;no title&gt; &mdash; DiCE 0.8 documentation</title>
+  <title>&lt;no title&gt; &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
         <script src="../_static/jquery.js"></script>
         <script src="../_static/underscore.js"></script>
+        <script src="../_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="../_static/doctools.js"></script>
+        <script src="../_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="../_static/js/theme.js"></script>
     <link rel="index" title="Index" href="../genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -116,7 +118,7 @@
 <li class="toctree-l2"><a class="reference internal" href="DiCE_getting_started.html#Generating-counterfactual-examples-using-DiCE">Generating counterfactual examples using DiCE</a></li>
 <li class="toctree-l2"><a class="reference internal" href="DiCE_getting_started.html#Generating-feature-attributions-(local-and-global)-using-DiCE">Generating feature attributions (local and global) using DiCE</a></li>
 <li class="toctree-l2"><a class="reference internal" href="DiCE_getting_started.html#Working-with-deep-learning-models-(TensorFlow-and-PyTorch)">Working with deep learning models (TensorFlow and PyTorch)</a></li>
-<li class="toctree-l2"><a class="reference internal" href="DiCE_getting_started.html#More-resources:-What's-next?">More resources: What’s next?</a></li>
+<li class="toctree-l2"><a class="reference internal" href="DiCE_getting_started.html#More-resources:-What’s-next?">More resources: What’s next?</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_feature_importances.html">Estimating local and global feature importance scores using DiCE</a><ul>
@@ -138,10 +140,10 @@
 <li class="toctree-l2"><a class="reference internal" href="DiCE_model_agnostic_CFs.html#3.-Querying-a-KD-Tree">3. Querying a KD Tree</a></li>
 </ul>
 </li>
-<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a><ul>
+<li class="toctree-l1"><a class="reference internal" href="DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="DiCE_with_private_data.html#Defining-meta-data">Defining meta data</a></li>
-<li class="toctree-l2"><a class="reference internal" href="DiCE_with_private_data.html#Loading-trained-ML-model">Loading trained ML model</a></li>
 <li class="toctree-l2"><a class="reference internal" href="DiCE_with_private_data.html#Generate-diverse-counterfactuals">Generate diverse counterfactuals</a></li>
+<li class="toctree-l2"><a class="reference internal" href="DiCE_with_private_data.html#id1">Generate diverse counterfactuals</a></li>
 </ul>
 </li>
 <li class="toctree-l1"><a class="reference internal" href="DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a><ul>
diff --git a/docs/objects.inv b/docs/objects.inv
index b357406f00b3cf8cc89ec13eaee843d4e6c81f73..3e07d7a61e58b5d08a27b5ba9376f77be0098150 100644
GIT binary patch
delta 9799
zcmV-NCb-%8O7~2Vbbrf|oJf}4_g7%1S#&Lkp33Ukw2jS}Dj%{kNo{ILUA@Fe@W`Z-
z01AkdqF3`9^Lz6p;}0GV_#3|-wUIKw{hWIbj&t$rxaUQNl2aKqm%p6q{9K~w-=mxz
zJ3RNN@(nv0|63IQVLX19_9>~5m1);SKQ7C!3m$Tm6*)?ZQ-4#U6RP^OFX}4kFAbuk
zsDG|=B?$iCj1B+4o9$zrqtb|umfX#k)m7K0Ro_`%fvMKv=QMk{ukx>$uro4ST=nqw
z!v|75?fbTPJom@};?t$C+w6HS%$JuErERqr<}0eYx;>Wlw;%mM-8ewecH(k<=8BG2
zhXc4Jw8gPN?SDR;&*-T|9ah5u=1YoilA?P0(zj`ko-UShtg9d1p$hdy=E0J~yEe@W
zeE0gmdY^x75%PibIj!>gWPx<9dek1%tUsq^g1$FpTG9T<wsVo<9Bvoq?pG8BSJMUh
zkR5SRq7Lekvgqh#YTCL%ZGQovJGS*H`Da&Grd_xbOMh8sxHNun)GfaL>=_5>6!s&{
zhX*$xO?N(>()JS0ufB%ARIf#c4;BAHN!leu#ABPDP&mr5&Fk65D{OqTlM3bm-Bfya
z+>_5Bq{8uBWduQ2B`F5Mkho7<l~KCQmwQY*lq?T=#c$f;6?f|4DGs05Vc8`XvhAZe
zWGx~k>VIdHG%3DQI$@K5V8$)7s@oI0ai)7A1oN@zlQMlo_ztf!951!uoTiVf9QV5g
z3QS5J4o3Ne`Xnt&>gpxQ>axO}a2J%Go@Q-2Io56RG{lWbKD?xcvjlgYxSc0Wi~s1R
z7%w0_Zsd8`dyEjXyDLvJ5+c`aL1L&Q?rzR4et#HMIr<*BMGV|s(x%l@*d{Qzo7BhI
z3LFi+;_xf59j~~%WBvW9sFG9qeeQ*?&_qsY9<~i&r@s@gzXxUgy~zEFiSy|m41XIi
z{-78AN-;)Vq2#$9`@pc=_&I~0d$`DvKKMxEqh=J<Q*ax8J0tRjNykmRJ$BEJWs!l#
z=YJxG!zX&wUv#b^0gKIbyik$3ju$L0*An}W%8e*}#^gFe(1_fGJVZQhY=?C41Besq
z4Zx7xcl>Wc8!q}cu?8geHz9_P{LQQg75AH1<1qj<qVpW{n{fU<g#PWER((NIG4y%U
zw`oz~C@{1caIYQa>;c={Re~qD7Y-dW{D13)sRdqMHVVnRg!J8kOl2{i_%fB=pOu+G
zjI%NYdkQS`T%D!6LX1s*jHQ4LHL-!j#k;0VFSxy#3S|XvnNhYx$FI&f<h4i=+QD08
zSS_*lWLEc3?H7wkf)A1ysAsckOzsw%{w*rh>Jpivg3|j(SeTxCe+P?ByB$WdzJDd<
z9G2jRyiPjY7k5REUoxLj_9DD;9{J7<ehT1Mj1HLShy!_H#|cM?A8Ysses`&WiO9<c
z3zI;Ip61D4P_28Qpbl|!&3w0W0nH(+PtCbUNm+Ltq<lisrmephCvvl0g?_r#ufl!_
z%8Glo_jkBt(TAkWj+C+>PeX2gV1FQXBJef&>2TpS4QT1K&ahWK*po&?Zu7bh!OzD3
z*^uQ`Nbw!l1tw;%?7>J+I9duu1{}kvDU&X%TNLhco|~K`?4I#Ed`r77)XS1sd+D3`
z0}iN|YM`JVe!6@e>3qjj0-EUwpUYnTU`feaBxqElqQ44hfH+b`-=e2;nUhNe6Mx<G
zxWWC4R=AQ8O_Ox}r9{CPgGF{Ca+(PvUxy|2xyLO&81Zy{QF8kb&R^ijLrqCDA>-R|
zF#Z-dtvsoZN3bAP#M<?BgS(Tu3C0*O&T6Oc`k=xr#z6g>KO*!UWNk=jcaYUpUsUJ%
z+$G(duL06<O%BP}FFz=Tx^x^3^?#0ieEcxd`o4$?I{1j$j2t|2HZdbWFl%B)sG!!w
zmdjPx!v(n-D}n{P8au)Uy-H(1gI^VMupn4v1R1>{U+!PskO0B4iXJ#fHlv0QmQ{AZ
z2hA$>E-RYL+%H_g0MO`N#XO(8rvCxoCHm#sH1JXB&C1&w*r;?v7cweUk$(q_O66u;
zl{{!jEH@*3NG!MIauxP#gv3HCt`HIn?YLG*EHEZeNW5jfLP)$d;z}X$){vkf@s>VV
zNUWj`84_>p2pJM@*+WI7Tjnsa;Czs*WCRomE=dme<IkT5N{>;Xit6xqF3Oxtoa={$
z_TZFUG1J+{3BHmz?CDVsGk=fCz=GvRDQt2Tz)h{RWcbzuM;=$A?@&8*=~Kb57SzdO
zQIToR9ZJV}GXcp<{3C6zMBdaLCd=m8x~O_4ZSgd$q8ZGV>GR*kf`h^6Lq#|mBbI4+
z_GKo_L^ZV`W&Oy1l6{?PQdCELqEB0zk34n>doW$qgz!&_qMQ2Wpntq<UDGQ!fm6|C
zATz9$tZ-qzAuVW#ue5=M_kBGtM-i0%+Oa@~`g0SOv3NSw{%>u3-*&}gi6|xRJ)qtt
zHav%i;Rx~W*SGhcUnsPEpku0f_E2$z-V(Z?0~jp}Q__YE9z!=Ro@;WGE@uCB;)iHr
zI^Nw9pT<opjK8p_HGeENx8Ta}UR2=3p_qOr%_P)(BfT!9_I|V6vs^_Vzz1?aNd*@(
zSVPmu|B2hYU~@Hm5>@BZ_<~X4gI#dK8*oO&G-h8kWu4|++w(y4f}b26HwX#Rvc)8a
z_vG+A-s!W!TQGv$2e$lBw}-7Ae%r7OyZ@#=%+v;H(F^RuFn<r+X9JcKfV5W)9aQtw
z(E4qS3Nqlvw<PPxVuY`0NzXa*b=fmIiFfN@r=(5!+!vA+mgpIEJse|ZsOiTy^j!#t
zFPE-Ir+Xf8hW}9nszUoaevQAat7Gx>D;c(;f#yE!XH+(0y3NJYp+4R7<ZGK&-LXEg
zp@nt-U}DA!27kXX49oYa*5Y*m=F;6gJKCNS5_fxKV9O#+@ZOL;AkuYd@fGdI_1%uO
z<i*1huBb9>BkK^Fw13`<N&`gv>c5@8vllr#cRg8v82jIi*#Tm4(i9CMnImw5Avp%m
zbHZ1qn1=XaxmvdWoxcn8nzkL#RT8bwI^A5m8yS7vE`RQd!HeCXgEBqp`f*)RI9Ly@
zRE6%RZK@djv`7{_4UGi-Ms_Omr8^D)Y4fORvJ!hoz7Q<Wr^*LDOv~=lS0w1~T_7uT
zZqu?t{kOV(agRclFo%bSzp_8A;}99p0SosnZFBoaF8ks#AyW{F9%Urwr*KnHTI0H?
z#%rn?ynh2>I=nsi^*!4`K(4x!bO+mkEg{q@E)57Rs;)w-Z-^kYY<cCREMD+q_qncv
z8!(hC)1GW!AYHo&(1LLxZ`ppco~dsi5=oX1glJ0dq4Kc~A?-jL@a`QL1Kzj;W59cM
zV7$uhI&fd-P94bo-=yQj3FqKsLO9%!ZD7dT{C_X}21-@|iV94*5cLZ6PqMYy+pdqg
zKK~2bCMQ-e;vPx2o=vlt^a&|x-jH+gsf@|Fcs>^omCeo2BJDQQVneRsFx?Bl&I89y
zYu&3t`7PK)D})jPTAyHGYHhdv3ZmAQ)+ZR4T7nJBg2*M{^@;{37{Ae47^!$hPdKph
zFn>wHiNjdDpnwS@*}N`@ND^-Eh@j%BH{T1UquLBea9DM>+xvx+bj$4>5n8-?d%}>i
z&8!}=K&3L-QZbl<CdR;1fa<;4G%}d9D_*Z?pn|D3y9}nD$_O}UU|sdwcLvl~Zwx#I
zsNQt5$Y6p}HV+uEl1!VZhSO!D^aTW}(0}jZ<^;ScuXQtuwxbEAr-<A?WB~obc4-`^
zHzY8Tt}){2Z@4qiSf^-z;UG$hi2cHWX{Op4If!;D17KjmwOsA-98|^?w|7KG@r2uB
zv!lLlQ_T+Ck!wX5k71I2x?RXEQhwG@Kste>`*hA(B>SwPfOLXM^y$2_N%PrbL4Qf*
zImM@S%qYQUg90gxx8$CYLz>i{IR=m<aA`fAYqm)}H#|Vuz!Q2V9y_M<c0)t!O4rK>
zsUaow0|TiINSf2gJBuWz8y>7|UK5;#4jQC4ZIJ*)3Y6M3@pxBa(-Q%p(*Bd0CO(^{
zH0`kfr2<Z8n)vFJ%-jhKs%Vfzrhl0LJJOh*2mqD#HQsOHsd}8>6ai8UpUF!jfApzK
zD;Pj+eh0TA*e!USTkp4XTJ=SVJ5>4xJ$?riR8pl4V90=?0%d_sJhsXKI|70$7xH;v
zlKr*A0g@;D;J2@l?;yk8KsjHXZ&n#!2QVPDfU~_iN1bxLJ3xU|^q=Q7^?%hg%j<@x
zmTmZQSN4&pxe6MfkL>GVvH?7*`fiU=Y~|GDL2rf%!EMSi_+9>q)A{~fl;B$y_u;6h
zMSJv92ya)~#LMpd$cowAFI=TB)1NbsaIJ6Y_vzA=!IdSppMc9)r;p610><C0%NH#-
z!t`jrdYd+~#(rO9^vCeGi+@9ABxE1BcLRx2Ehv|l8y$r3f62HX0$iEZ&bC1{T5<aX
z1J`ZZ3@p5COKOi;;G$i^i*@lJ(gjo;@s`FxL=sbb#DWy<C1<-{g;MJM9pl>z0I7*^
zSL#p#3CX>pK}ts_%Un%6F}q(lNcGyZ%Ij0u8<OYr0RpCvaDVb3Dt`%?{Xu~#W|gt<
zEt)Q8;ROv$IyOt0O*;ys*Mf0BL=a`@&g{X}p{#yjfK_6{{UH?^823YfDRWBuK#EW%
z_o`qDaGSmc(ShUJ3lKn)aTn^q(u}m8aKMB*H#r%1f4(%RrSU21r5^(MR!hR|6U>Wl
zFFF1HCHF7O`#b8y`+vL0qO4!1NW47_IAzZ$djWJ)K(?#4Zz;}AS&$jb9jFE~i(56%
zUWa)TnjLX`|4{>Y)&%mQIy++ZC>2%n>@}Gv&EAV3z2;cls(JBx*j$hP82<L}^hiQn
z820aroN7V2JPoJkMb`)Mf62HXB7ibv$~#<EN$uc*+b0;fZhzs`@}N-=WuVi$DhI98
zyXIivy0z%(T&C?XbbbZ#L<V?A1efs=Ubu?~sV<=61WNdd9CS_i8e>6<7ACnVan&)o
zX@LeQUETD!^ZXaBa2@^R7WjvRQ?hB2uD_HhkZcp(&iY`2gn6GA`R4d$Zwdvb*weW8
z?YLWf5Vba}et%%VRN^-E21(S3oZ~oeA6(ng5(G>i$T1_4TUMh-YJdQm&~I(V(c91h
zEy=y2fl1fm&M!~u<1yUbwxslc0VYn@*9{KX>L!dZGu_VmV1k57<cYj<PUM+`dC`qc
zE2Dq2KmE%yP!NYcGYW?~FwW9IfqWcSROkBKC2W(<E`NXqGG>2JfQki{X|Fau1?f@M
z)$OsYzx_xLaKHV_!IKf6zS7?hlx$aRXeoeGC<@PPQz@oU0TqKyt(ZA%nPRaA4W=h_
zV!_09>jZ;6XfQp4BpgiqcS}4tA_tTAay>yW9wod45iL-HLglb)qQV+8gqUFx7aG?c
z6BrJtA%7$dn9$HDuqUzM3JtF?T%tqivqi$g2nSrKFbNQqua1cjTS#yv$xQ2(498qm
zO{o<yu;8jfCsI^STPIY^!N7HcOt7fjv`Vy?0R_|wIPqfUuWbUx0To<Q;Dn6IW!uDz
zF&4OJT~;)gIcN&3+lJjQ9K3pPX)dLo7U?b{9Di`3=D)Aj*2E?NV1kPoDwnA8+&QOc
z59(RZo0Xn7kiy-pe7uQv)rOWLSgvH_nR~884HZzaP`MJ7!_K)9Q_x^~UQb1j+67fC
zTy{zB@Q&<~DQGY~180}y{_o8$Ss@3L_i{Z!FCHbl1Q9KGc4_PI{_K(=W(YAuXP1Po
z?|;rN8KZ`f^eWjUp#pxgOLoxk3Wvxp34C_SE-7%pg$kWr+WNXXyJQ9luH-ecOIz2y
zWS7ig!Bq{HUD`UmBfF#n1J^A~c4_OTV|Gae6i};R*(H^~?%5?{RB%ayWtX-tyJwd)
zSm2@s$&YNEbjyz@aKMEMKcv6)*29p#DSzl*J?DdD|E2jS`Q=r#7190p^JhZjTocm$
z!{fOqbF$EX-=c7047Bg>7_BE9P@(7wg$Zt#r=sss4zOCb(or$JXS@IcF1MOvE5P}V
zH4Ge=nE`|gDr}Cjg05J71vLfSKEZ%>>rgwql1yhpN++WCj0Y=Vojev5S;(<NsekVk
z7uCM5nf*aQD^}tkX?qRDmdyU3pcQNCu79qxd9h$rJ(J$`gsMKMfJ#HakU`}gH_Rwb
zP2DQ?v4v1n!0i(ZRJS05ol1w@20EP}ft6e?c$6I5`UJ7gzs7Zi6)>={s+RR*S|-=L
zz2znVV1kNSR7ZTGPg}ZN#j#7WGJov?Hckn@Z@{n`27Z5*@cRaY)v%l1jRFeCk$OP^
zm8h(<D|dTR3;aWZDtRip%>QPCN<U{x4;Y~00A&}Io|$GA4M76w1D8=W^wT1n=z<6;
zBTK*a`2Da&S<w}Bz~(04_6Y{6+f~Q){Eq5{9@Fbke{MpGMd)_chZUrFI)Bw61Fn&9
zH^N?7aKO<Ok0qiMICewR5pn?k_NvL2?O`}VeERk6eYCGSxEgTZqG)}y_!z|w3tqG!
z18I7v-A2>gap8sSTU;ryij30-h&O%M=v&&5uY#td^dLJ1qtJqNbnqiN_?EHyfeEG(
zWNXqnY1OLCzzlT5K<5(0s(*5}a+pAVq-7$qCN8S_&X1vseO3XiUgDdVWY9i+wBOa$
z7}{`GR{*CR_cOG{H!tbmN4FKcZQ+dz`gd^0YRgU>cBLWxy$Rs2<w6O5{awC`L3q1j
zuqo@+(@pRO;p~>gvN(*(d}IOY_JYWvin06M`H_{ij%2u+U#352Mt^3`l1)spDM{d^
zXQL*~UQ#~ECSsytXM8GSdNQ6*#zS=rQ}kFKY!#lQt(hLBf6~8f4c7saH!d0*M^>eM
zx<qG4Jhf?FNGEf7@NdcDUe&wj)%i5e45{$J4pxB;+kOaeMQ*}Ma^pdh8}Fj1_ObJ&
z#A??%+lpR&F6%T;V1K(jp2M}GtIsc}O*<|g9VqDG`KUktC4BG6;rZ(;&6B_aB!Djd
zpBonb89q*25ktub^6;^B+WeWc7de!y9y@DWmvw!(8(s+EJoorEj+#6O-0)n58;02i
zlHr#>ahCAIPJNo*UtY(*lm7d5x%Gx!xgh|M79bt9#wGK9*?$rUNF$HEuErr<Cu>w4
zKn2fTsKO1C9@D5gfC?R!7`>(?JqInsl597EMvm1e;%3Cj!dV@ZG!5xu821|G(MBHC
zq|AC))X5WZ9N^O{34?8UFWxTNtxqSHz=p+)T+)qci|y5nXG@2#`O)g_fG<B5tsHt@
zj5MzXmgTVIZ-0D)l9dK}($cdRROS7pk-5I;<>rb%<BIoH{*_i#pSH2#kd~#h9f!9c
zK1BK=R`w{f=q5IOTBXU=#jI@WUP_d<mAh?U1^}~SR<>yq*CzIT6=bIMMIG(D@nPqU
zxt%vUJ87q5e`nGNL3UrxC(YTd@5z}&az`!;SXe?oIDagTg=}KJ-k{qV!LXc#c`bTs
zQHQUut973z0JCB`+vrB%MfKG6WH#y3#mcTPL**}HWqlD_dk)IkWrlVg-mRvP>5JOi
zsT@}@Hgr8=U{KcD)R$boCYPz9@AI$x0$bXW)<&u(ZkZbSc{w{vTT*5uKf{`RE>p4P
zmRINaQ-4O5%Yknf=k9snebs&Xc*u^pDA5viNm+C~nA2M(&v;&Cp^Gv6v#TpOJ!T4D
zKwcGKUl!{=llCFRhRHLYS6NP|PxG`-;pCVYJmGkCzdN5!WI?PD?Lxri9nq^eeGS}Y
zj0ApQy!!rHbZ7Q4YT6~F*&WFet#DFE_&`wMgnxp4;%=#Y1B#U~>>uy=PVP?HQxP;%
zNLqG*I~~!0k1I?TB%mN`tFeuY$UC16uL{Pdu*zCm$<(N!wBVSQ!chxT8Qc^ojGj1T
z@#u*EAxE>&lPfJarloMzQ-fewPGz2%sI=@t+3AP|eCN$IvKZZ528CtTlI;mMpW|-&
za)0*9VPv-$aNWTUfNs@%_=1afxR<{q`O&*uJoat`FV5P$+F4q<eWh~+@ZxFH7FBN=
zV^~_sVedxp;;eb_ZE5E^=yt2_#Yg8L+tOxDaP0-nzaTITT^>a51+r6sG$MSk!e@J<
z)QBOFU2(C^idg^)la@0HS91h6faa0eqJOyPpq|AsHu<Q7FfFLE&{SSlS}<KxFSQ3L
zI3^Q8%!)5<UQQlS*t9ArowFpE>N2GmjN!Q|+av3#DMCi+%eajVauAa;26k%R!9}GP
zKTIgpZz7`7iyuZ5!hX(%RScjzZ(y75Mi&-e{t~h1W<D8CbRtEDDMuQhsnnPG?|&Jp
z%bw9Gl~0`-&M&_AWyiKNo@T6RmJ~aro>s+C$m&@zuP)0_LrW~KChe=veNigDmu9CI
zqR~TJ%O{}8b$Udt*bFbJWkot4LEkgfkS^%ZUAi9k{^M^WGekIFD9-(aV_43{)N_Yg
ze1VR|6J55LcA@(X|2sy#rKrD7sDFAll(qCuJ)^S0-4*Sj`!=n*V||i^mr@@_5Hh6q
zbp|mh<Z9vJh)_=7CK9?ET<68)Evi#3XQ#NGP=}-KDLJ02%#U|+_<hxP_{*M^6PzzU
z*RXEYoc;3bkEI_D_LI*~QvBfQSu-xGW9?|V2+6pli@`;eVXxUt@Fwk_cYoWx0ko}P
z=LP)`;R#h_75wF1@H;$FfVxz&^C&xaeSM-=wHtRiA-W_@(IB!v)DFk=*gNWac5~Q0
z4AR??Vn2j$-%t3?C=|P)c=Dg4@dM*qhhe_(zT4S~#t)2>4zFq3f!_Bzg1rFdUXQ^-
z{fti*RdPzd&w<09?%M#^wSS_ycl1Nd#nWxj%+V=1o@IGU7ly0eqpmNiCm&8o5Up!?
zab({U#sJv0q95;eKSK<`_f+=d>F%e5A^4ukmY$AX5c-V_HhZ}9#DKOHEWN1DJ?(y~
zx=--s#?O(uJfA8b{^+3HtD5`h{pn@>)bjDP>e5#vco%bYL55~kT7PeRh0bkSR;d40
zw=dn{cpUz;w0Z^e@bK3G#;lmTod<lOzNKyM$=(UhuDIU*X`7rwem<Qp<QADe^0u^n
zhPoqAWZ31G3Cg_aKAY7uU7T#+%yBWVBJyRG*kBm}owdSB`ecZ(-obn@UQ=Cme4S>~
z*fVq%Zq|&I#YZhIS%2P7ZU(I|lqW6Co0^=PWpj1eak)LZEGfsW$(1fJ)fv+zs5);t
zxI(8BC1iK?qDL9o_feM=6jj+K3Pr_ac|3^`tJEMX74xM`l8iEQEzm(6Q<r*8$Mrzd
zb6+DI3gqfMn$k^EuD6)$e&BMf2P^@Z+!I=giF0RtXlbs{N`EHKo%NxmF$gZbOCydz
zt?NTeQ;`>>GAWA}R2I*59af|*yEi0g;f9iBN`lEGldb{>q?~}>9~889baSktdJ3x8
zM7kFMLLItkIeZJceMtBnF3qdJ`8@3diOR=1kN`{0o%I2w2^H-OUbzH1%c_7{gbHs4
zhg>3?WmP~eLVv|GgF`N%%(5z=7U2V!!L@y{iwp!%sVhV*gO@vl6)6g!SiwS+!8xbs
zWL4Kx4)JK0U|hq+cVlqPaO_^=XPH3V;Am{hiboD*KAVjuN_~-xFcwvgzHf*7*kL-P
zcgMayiIyKBMvLXg{&-j1-v1Ecjz0SMfdhS$75(P^nSZgz)3@}$MLpag+T!u7uFV&^
z<$mx;!^bo6^5dD9|5S-y;20YpuRj6f$ZT<T$;LL@E6Sq3#Pw0dDYe%E;$bct)yHUA
zG(wAo;$|D4P*1duyFP7ul*iwS{yE-$ZpE1-ukntZiH0)~ITI0actZSFL3YDSt32-0
z$IXqvF@Fh){=yDL_)x?SEwM3mNtXXpyRa_z%k(?C`(<fvTc`OcZKP1+`OoZszG`=F
z$Z}Fxq7&+$>%60lYS`YLa4SDG<2bB=zKj*3p#p83bA@QLwY<pcGr3RF4w)D>mz}w%
zV?2ESjN+!PPX#{dcu!bBe0@gIP*i(Q44vt=7k?d3@TrkS@i74*uQrvKs#kT79_#w0
z`_m(S$#_1c?F*e<Qyh<|r9sh={}3}7F65zTF4g0bXomV(425G05ft@@uM$mFqT2^v
zov|71H2V!-C!XrW*^$3$V<Y$H<eQ(xytfZR-k_2UHziVc2D`j}H&WcLD8>`3r`v9y
z=6~;j);H(a1%X`UUu<aS!s}jPF6`?Xlc`y><%#Bo?Q;3U3VHY)P4m6>89u&^#H7m|
zx3u+W{#PFV<A(u%JR0GnIHHP%c~dhJ?L={8M8aZj%|=b<NCFXIE!q#>cYSeU4@bIA
zD2*_l%K8!iIaG@H#VxbC#Sgo4M`H#W;(wUh_hwi$gF3xxsBEX7xUb{wOddl|-rO3)
z4<)J2tD9ihv8b;jHkrrCIZ~D5OgH8{{u963?Dx`;hj*9yKRcOj{HIkc{6<sziD~<x
zK`U!N@lY$CYsIYn#I*egVpUTW?su>f<dDsNFiW;Vtf|ZIHZbf+#4p}zY!p*%D}R-n
zZ69Q4^n^fA3rm|8mBoonqAyVQmw0@pkoHe{dwS({U9{TzPfLamB8I7xUKXAnJmlV@
zi+YfDB<;J0SIA^|Q8ehc*EMLL{kL<Gz2G;4zQv(-MxWUDUY5S*EaH7t8y1@PX4u=F
zNRr0G)-VQgi!6V0&trXBV9lp+uYWXdAY&op($0B{6ECKIUBfM`ozGesEPauU$Mw8S
z`$?e#?@Zxohxks>dWHoVty>P~;Mg~${V>c$2Aux5?z?~R<**&yT7a>?;%i5LTt6p%
za1ccEgmUm%hxktOOf$5c?{?|reqB&6H<|BW-!7o|&Xk@J#q)+n8a)!U_J2*?K5v>`
z_bz?ZI$!e-8bH}Y*Y1j+aM>6aug`5p9*f_e)BgYd=YPAnLf`xUwzvA@3hy6FJaRgk
zPe<eFh@LjISrRLxV+*7Aemb>{n7-$sJg#wk92X94SrR&|3CCu%A(TWD>DcgTcau&n
zE*k1bq<&PG-WR`-cp>KF1%L9opnCjpS%E!0^56Co)4n-uz(XeL6KXcVk5CiSt>DNZ
zdKK`KgbOdo6&|9ZAM6$Shn{QRG@Eh_d!qgj4OLmTfmDsgs;sf#N7h`GHl(qtPKShL
zUrJ;jpw3lkq&khXjfV}cR2tFAT2>~$N%MSo?oVkWy5=CcU;577gMT+~)xhj@#GQ_~
z)3#p721SQ^A&p;CWdB%OdGt<4g5@7brpvb;q~)%Z*|SjU>3H0rE1>TCaNLTMxEQP%
z(-CAkl1pP4`ph6V{qSys9~vYBHddnN)23<b?>l7qWx@Gz;=EsQJ`8o}`L~R7s>#A4
z+GI#SGu5Q&H$hEXS$_-%k`0`-7&x{u%r)YaShqX$T-)iVrSR8Ybv4<}!Rb>~cYTp1
z+0kT#dR6K6p<6scbWeHu6ilm&Tq2oOZ+<+)B+J?${7==#Y@5D#+`f;bT8CJ=b8&#c
z|6&OL<00aTM&pKoLs62+9gCWKcXNn`4JYHYe5zZl)5*yX41YB2BpJV*fNl=axD(}c
z(A>744)Jei)LvLm`;y1oT^tRK!$^Odk>20MbT7xB4$*iN_s8$=BDQa%sd?FRU3dI&
z0=^(mj;-KUf;AqW-q+Z1b0eoGsd$Qyo3-zBpwkm^D6pMbVQIhaZGZ;I`2IHQW;K2p
zlTDp4d@oewKYu#8MCwhM!!%;6mN@a>IP%|kYz;;JlcN<sc~arej{JZ2s=|LbTJayz
z7gVCG9|MNz(SqNXU+FqTrZ(8bTrzuXqb;d1-RKkzjXZS6UsQlX39UP3q0Jo`0D0Xk
zQMJeF8PeCKpQb;gF}soWb-G_SaN8*l2Dj|A!c;Quh<~23sTDX%;#Orc2{lcj)Bz})
zT}Z)Vwr<uEjlK(UYfZ6HnVpWwpO<WQBxg>%grhHYGu$w~<WDI1!`0EU-<j}p@s;@=
zCHy#Z+%7rhGtu(QUbkc`t?lyT^9=f#TQ6;8DT$VnG=C+@i9D$rwyCE6{uS4wH|yKs
zXfzxpoqr$eS;#PjVm7;tapaY5&Mnw<k#frk=7%-r)KB6U!#Ovg>nT;1<CnPX89&JQ
zH<53sczV_hk}3?xkhd~O{CYT^o1UY?IV-dA>m7b5<?Ma=7(b%^8$uPC4gI}1kuh1)
zgRroR{CcW&FFp!?FxOXWF8roBRKjoR$7rY&O@EbWmo!z1XeBEJ#>4S&m^}2ShHXBb
z++2pYO2Xxx6feFD33Ctbdhb>E?f=zR<%La@tuWd)(56sLTfAaF=pu=xz3!rp?f6`M
z?xQrz@Y8@aiTQIux*M^Xg>Q0nWWgla&OP34!DM9go4YN_c!*4XPVH>sW*#-T^Ba@A
zqJMOri?R0>@Z7v4uB<RUxYxbzg#!9_Yy~WFX((mu%>Hg;>jzMmA-CRS{0iS}F}vAF
z&po};x!y7F{4fXZEp&rw5@$&@{WWV*nx6!V%?-z0KR=yeh2NiY=<5$q`I^!%P#5*(
zpP+JByS_o?=>mL&%9-u@6)JBr&}XQem4Alcq4GvKeTd3YD!&%xiL{@Ka-hQRMR~Bz
z2cul&eP4|7ECD_l71}NNW>jpN=A%)L!1b$9o)_k`QGU<Syw29U9*#ezbtU<oFOzBQ
z-cD41Rb;s|=eqtHf0`+wArX~ZG6|8^bZpF1O|>qwq}d>>DY)$uSHK1vLvGg`UVmX|
zw@EZxVnc}PVVzZcBhoLRm(6=T%Fsy4{QDo~VuLNa7J<N5MZnu!;_(Cn9u@#$7Vzs^
z3^oWqp?3UqkjD-9>9hVT8nI!(pB<_vt|&|b{i4QjI*qw`-sV$kb2SQ^yid(>99veI
zc-54S$v}<5c#!dI-J6ci9<Y&~nLMm|Og6pt_ADd+&kExdeTn|-4_q&->7GAbuqoBD
hmu8_6Pr2`XtwZF&wKRksV~Aha`A_6&_Wz+}J3mh#Wd#5L

delta 9488
zcmV+rCGXnzO!-QXbbniK+&GqgpI;#$3+(iRYPQ`wFN4J{(zX)>Nq|h8>3I}niDhf7
zOSPnOQuFJV7hNccck!_LC2>jQ_nq^Jq7Hc^GA}ZeRAqF!{H<#8bBUt=igI@B@Z4AB
z8+J7Qk0}1rc>FHyQ&J%-)2@qtUY1`MJme@Va+DO+sYDg3`(v~(nmXw(Cqzk6|J>wC
z5d6Ox8~%Sc+vg@nr4b!1xtlL*>aI`gzO%XlQ?0|VY4&no=ie}4XJodx>f!CDPo#R<
z_igcb?vVq;mrLKY+4EkQhnEtiZM_%f8>+jeJ(kV)pOaew8Go<nsYM-D!vW?Y#WzV&
zKRxtq+M}n7r5x+(hxe#PeUW*v<nS^7)*|Es>1$f&O=W>}u6xuT)2u(IWrBX3%Cx3^
zh;4@;#W~zA&fTvl46c9+^dURqqC_3kC1ug|gzMBcC)D;A0J>w_RLQ@(rZ(+%omk2y
z!=-U&-?aGpvw!Cjpi|h7G#?(efHd8?s?zon&ab|Kzf`Y9hYuD1MoHQwM8sp8Rwx|h
z*yi<Y;}tf(*+~WSAZ#kVJ66eO5K`fIt}}w5tCAFhU`X7jt;#6f=F2^%9ZHr5z2cwR
z;uUx5;VBMZ*kRcv7P9T5Ib<y&C7NfHoKk$JbiyV9!GDZfWZkqCyK$y_Ap|phX5_f@
zD^M4fv`in_C?g2v6YAM%c4d=e(<V=CniseaNb+HL70wdef#9p1oLc-xH$^%D>2Wxl
zhiz$u7}bn8BY|Sm79^55;+yW=;x4()(GL_>h=DU{j-we}f*;JUI1&hK$17?(*7a0H
zomA<Mxqm~r!gZ?BJnV(QPX8cY{|L(ZN0Iv#6X#(?ztZETsZsLWj2%H(Zrs`8&L0;!
z(%zq3d};<Bx(2u5_cJ1c4LXGO_Ut)7mPG~{s)-m5U+7VPftrTokUgX91**R`BgeNY
zyJ?F)EHNI9Rz=_APO44oClrbsC@|LXLWRXTUVng~*oe|+NUS3a6%ZTSAsvGQaYBXQ
zhUC5ja1+{a;kSu3Qx6`pD+?3#n^_Sm<~Om%WAJH2=Q-Xt;rwF={rfqs`+{TyXqVr&
zX;I?{G_)CP$T8mhq3=NN10EgeRl*3k!H$j@eyC$=ftP_!AsNR=$1UV72;+AqrqcV9
z1AjA!adMzwPl08+rL%Nbh_Ol2uuP<(CN_|`cy}t(3vO?wLRrCECN?e6@vt3-ycW4C
zJ9w)^pC$I51m7O2{bCVG@Iev-_3VWVle>jxA&VNdx_p|bp!EI`7N#dZ-oc{NZikVq
zZ%H|aCHNt4k`DL9UD00>I*TB@avu54Cx84Dz(b4<nCOTDd11#1M~NS6_y``m)WAe!
zFv7wl5Td8~y&<U9Jy1}GxYv|?w{ro_A#1ABxkpLabRDF8Lef*){3t4Nvt5OLy4A13
zehJEod$x~vxMb0Xq|A<#vLH`G?lrYQ>_p&e^3&<UYZ}nfw+q8w^<YmL5xLE99a4gy
z&PoqcmRBLgcU%{km<`#3kybcb3PuJT!>B2fE^As8?sA?_IZ0hT<1u_oyDo(5z|f!O
zcmJVcs)2%f_~r6#r1Kq9323G#d@dXM!IF|ulUW5Me{<?_gZnqFa3v#7r=;sIB?`tE
zEV2`klLr?0X6A|p^hrg&Y)YDQk8inP#8U%9$?dyv{sM<SYD$`l8HeY=_*>kx@}xN)
z!J=ppYu7g?+@Ce4V2l9+y>|M(4JyuK4Aj5*V>;ha-iCyB2U%11MSX70UDC}7BOnde
z<dBU0fAV8ks7uGuQ194>v+qV)-xpCq2OqMVk%NcsCT0YPrcKNU6;+$qa=8k7xF}m=
zMX+dFV@KGiTWJhv^sQnJ7KN*f2pWy63<(e%tLTA)WHV~`U|D4ce9)|7@3P`_nfrw+
z7yuf*tC;6=*YrQ&SfXF9s{$XD-mJX6fsINxe{><EQWbf?s8nvoRmp>f#Bwvjhs1JQ
zE>~f{Mo28Q;tC<L(2i?`!~$aig~VItD}=;bBd!z@Zw(0=5^w2)g~TfAkRkEbj*ubo
zmOWHNx@8U%3(g10iatP*;F9EUKmPo6p!668s;CZ+=c3HXn|uAR;2fNiD`xYLs9`Nw
ze|{CC{*)ZblHp?)9C=)czC-QMrB4OJTF@kqMNQtb?oc|uxD$}P#6QyZO5~@e!(`d~
zx-hDrNn0eJJq5L8`u=#a@Ln+bP!W#Ch-Dg{eHse$rkvW4vU%jc3BS%YDe5CW(WfoV
zM;^O`J(#X)Lii^|(M^4GP+qpa=arj4e^qoD$SdATR=6<VkQOw=SK7eB`@Wgi!w5=$
z?O32g{rMD@v3RN)|F<^2Z@c2LM3fTu9#CV64bS1-aD;gG+uM830}3r4=$xvaJyaZ_
zw}h@J0Y=Nhl=MU<kD;3u&o#M87h-=q@k2B*9q(?5t8s$`<4^o)4U3H#xbnMKe>JE$
z6w?p2nS`2;wAY2y-fxyYmaFIk_(1L_so-J;YiJtzkE?D8uZB;e`dp0zj2a*8f)n0=
zGb&zV_C-@RY0kAh4>T|M$<c9>kRUBvOmg^04$t$QJ{!CRBglPV%MW#X*xKQ@4coB$
zZ`#9~+8`}@fqfX>1NYg0<pdz@e^o;V)jTz{ep{o047l+v$vUzc;%i#cbB=sn_KYg=
zt`+Q*v?-taLbAjYJ)^FNW6TVl`f-H53*qo^>3US%^N2J2&mvG2+CT6x{<f))#nW$O
z+KL96`>>x;c^cDgE}jnc>E0jT+O+PDO~s}b*8PKt87mk(Vi?vBR4t3^e*(;<yL)!D
ztr8M<dt_kiGEMN_kUb!heka9Ov>z9kJ2sMmhb3H5XV^y8A)M0wc`qsr5b@A|`~J>e
z<m}w_WD#QQe>Y|ah{egNI3bcb0w)-fWAHo`zB0u$#ShEXvc22<U7**r?SQTleIPE{
z?ZC4ebg;cgT|X{83J2?<e;ujN{j?qxgP%6T!kc0FS@b*EQ_Gj`I7Fk(qi*^H3qii&
zE6-K!1D{_rck0-kJ2>`vUqbTTMUOI)U{XBU1*J7ldr^(oR5eos!gP3h?wfnMf{Y^6
zkdp3TJFo?FTE(Lmgcj9Tp~a2yd)nrqY1v}JNm;z$KK{9Bf*UZDe=O6UEY>ewsmQYh
zx9<{3UI&C|O6Z{Su?gp2$XjS&40!hpi~(<)f$=K$%)kwHyNpR|=i%vuaJV~H)rE|t
zKJYvDSPfEDV9Hg9SEzrHEzI3^ebn{&-`F-Kv3dpXNV@%Hn!Th?NJ;aCoQtb6Cg<Y$
zTs%}ZH$#iG+f0j{f1rlLbRl><4;(knbgv5Kw_q=!5K0JWeS(3hwcP<Jh+11(pI~5W
zE%t2+BGiJ>6Ar9AOp<WoFcvQ;V8ZD4!V037-V8`^Sar9%ZH1F`%k3QzTD*C;u#mFN
ztRAsIr83#!ESQ2O#=uj6>aE&JEtt+KBjBKcb=7YU7f@fle=+bBpnB7-$btz<**svt
zN-}NH7fzRn(iae@LVt*x6Y!?I*3HQ64j4>Ej?)_wm`K-{67V-45NI+$wEJQZr9{Mj
z;lMOg?Hd_HJCy-2u;5y*cEAiO<BHomqN8}i%|qEyU$?1df6~acB8<nwvJenMDBVV_
z5@yeMpt9j-f9<@6MKH-0tRAsIrCKk25=^Z%v0peS%^-4BS_jQDRn|~II)P-Vbk14i
zsH~xYbn=~_()neUow7lJ6vkU-%E%#2UdkK;NRl8qDV>))GE%#tp>?GnK!?<j68eFG
z)CMF|XXKqlp3V&qRyMCWIztByGIX{`fFcFT&Y5_;e=9fVi2zXPY5Wx|%onhF!~&EG
zIE88At5X7VCorg@L6Vnd0_;d#dLjT++E<Rm#8Y){#1sKi44(;0BY*ViN-G#ZZT<ka
zBG@f>om=nsb6WRBi91v}6r@W+jb9Chl2mB}7&4%!qHXR2X(^)i4G6AW$mfAc#@r4E
zNS^Rhf0MrEC4)>#0_DkdzFB3-9l(Ip0?v@@9CgZ%?*Ii>(SL5-)K}BYxEr2Yw&8O?
z*_UVLDrkT{vriJqj=rewyFEs+rSO&qy%{P5w<*iucljrN1;U?;5`4?zJ{%RbXpeph
z;q6MBc-fsFSuvaYg{$;1{W<dp7jKn*^eSEIe^psx`(3Gwb^3C3Dq#E}tb7$(BTSF>
ztM}a@izfF)Mt=-{yEtS<LN@k!Kae=pf^vDea&-v*myG)%z?E5TRTxyG6}L|?aNVZe
zUBb(@r1ppfF4`r$SQif>T|mVV?@<{<Br&x|EJ)E_a<+|0D5XB$F}}S3keUd$84V?n
ze~{cO8l-geWtppKCua8x2dQ40)_GHfy&-u{A0S}*2sfM!qLPr=9~78kRv8Q5qUmxL
zUeLg#qw)-|9fi?r!MGnHh%$7m-Qem_RzEPnDzWMQkO~cq`ys%TsnR}>B9zI!DwqP?
zE`C9D;Q00e1khyMRy43QBdsSKFrg&de|-m0OTz6F%!_U>IsN}7_b<!GJL<&8yU3!f
zU#CdCJxw^#ugw766p-zz?OTfTsVvAF%pIr(GmBd_&t8Wa3C)f;j(^kuo;87dsLqa9
zJxWE@JbO)ElpeNV2K1U^ajWLV>tVMf`eXRpztbZLabehyDRQa><?=M0o)=vof5iVK
z<9>($%8*yy;j&6<2N&Ev!N7G3ua*amf+z!>-c>nho!&JE1J|uZPv<gihpF=`h$k|@
zJ0iG@m+-<}JV<o`6(>-_SLC2;!q*rJQnWD1O^K_H$xRD1Na>nWk2}wQ(+bzoPi}#K
zNH`@=r=;sIB?=_lM7Og(m>^-sfAb>W97p!1P+*FY3B{I7A6`W@DZ5`dK=p>LAji#<
z1F5!R^#cQ@61T@KNSagR9LIV4&b2))LBRBZoN*JmWi|Jv1_+=D{ZeV1`wlJ8lH4mA
zm~<`f{PLtZ9>d*jOG*zIVB&OrbHd?na|$EOOt-T>m>{9jpd#;_)1c;He_nKBFXhp{
z*`NO987PQDUm1l%9T;cXCfH5g7xlS0cM01!u?wJqjM*O)pkje#+N+IEL3&hoO?xbx
z??2N6+;9JK@MOfNZ}j&&O17&uv=qPzD1~RXi6~R3fQrE;rpz3+Oi<Z_2GbKdEo0)k
zb$Z4gG?<=2(lsXjyQOU$f02X9d%2#V7mpHNf`}F<y`ys2HO*s<8A8l3X&;U2j_Dr<
z)DV&eOb2Nc*pn7=g@#ucE={EL*&<zJgaa;AnDmj#SI0DxEhM;-;nGSf*LS3sTwuXf
zg-)cXoVHG=n1g}q2AN<{xoMSXF#`&y6>#Fk%wO9Ci~}mTq`(Oof0fI&i5X)oaM8M~
zI9=wTDX?xEcE51&>cOSClzv*IyNqzag_{4qT3ZvF0DuWDW~f}E%5&$OqCKc*J#SWe
z-ara>v-0sK+Ep7`ieR~tjc4w;5;asn#X{vuR1Q1mN=!k6>3KaBJ!%(Jv2fWXxx+iM
zOQxW~^bDL`lKa0mf4gLb98BKJ^#r|ml<*QnwBXsLt;74XONN*s#0;HX61u)SyJU<S
zLei^bmxK!V$u8MJ!z&yjyCm@0DZ8Y=0T(KCc4_PD?(C8oB)F2-$S!SN_mW*QhXq$P
zTy|;e^p5P34h&qkFxjQ8n~vEf6;ME}f@POf{<>$Ej8VZQe+`yh+PdtXUD9BIixwn5
zvUSoeKcc_^7b^Ue{?=O$Q~IW$d-a?TlHIH3pX8TU(N;wF<Ii6Sk#kK*_YaTfqRh!Q
z34M#gi80WAykoSUa6pBk>pLd6T~<Zkqa0wZaiybTde3+P1YB;^$JWpD9cvgkE;9oN
z7gX3BWd&XDfBOn*3b=iO0qfSGb{LXOXF^IRqW6pkD`1m67ByK0vqP!x^(xiAu9^Ko
zK`U0`A8C6H#g@$epr92yHC_MQWb;zXsD38BYlZ4QsDMgCz>q=Z9k&}Ps#DV{b^(S^
zRKV>M3{<xulbuS3-6lGnAc2)!E_jq2+opopB|+o5f5HkFSXfod<}odkYu?^+696zl
z#VqP0KGCNwU9RHTC0Utv0UM`;-#1`b4Fiv#CH%etVKwZgu~9(bI8rYtpc0i$cI9qQ
zYJq=9P$jFP%lvQEsPuED^nd{>4p4Sc>6vL}(GVn%K5!XDLq9FDi7tqsGP3krkH?2C
z%8IUNe*!i)0k=;uP~EONujhAGFZ7&Vhx+p=q*#P*XMI>fil?dx8E}n+yAk%vf&-4O
zcq|d6z_A;ej*tWRw^vQJZ1096#HZih-beeYgR24eEsEARi;q$4u;4`tGLfct+HE$?
z9T#5MzQvUStH?NgfOyk~&Az24@>S4ulpbWqe_#|^u#OIXCI{a#RzEPoRDx_xIw!4K
zl^K|UZW!oXqF7bVRt^)$&$LWL*2G11-}y0gu}dw0)k}Qyk__6XkM?`w8bcfIi3{MA
z<8F}F_~s@3`{=fUw=KMJLH`c!SZ&#f!>%->zc&H=wOlB{ufNN&7=*Vg2Ai^8J>3Lv
ze-O@YNi2)QxXecupl&aS9I6<*-<=;>S?frKtNAefIWsbImTY2*O-TYTJsX|U>?P%s
zY$7HacE(j1)06RhG9Id1n4-t>V5{&XZO!y3{geJ>Yq$=WjJRlQ99fn2=@NZI;;BvZ
zLi#e72mh8V?p3{eUZ1P+&5#-&>|hnxf3WR`09WKDtRy!cG`aCEifSJ_UrMZYt+TD@
z)#tKF^8~ib<2hU_y88Tr+O*^1(Sd><o{#$TU&8m19G<_v(mV+)KmzFE|G8n|pW)-g
z6)}{2AP*l~r_G;9dyzxQ>anx7by?SkyWxcp&U24%<EY7lzzxq;xM7-YAQ^u7e-md3
zKkU?}>HXz({5$EtZ<kwd*p(Xs0BHfzQEOZ>@0TrsfHd;h>uMa*b+Sg)0aWnZg(}=I
z=`oF}1E|npiP39X(sR&4EXj5wXyjPUB5r1!ES%LrNz;%nhH=9vk2dnCCS}&sqE4QO
z;{cytNf>O)d+~PBZhbnr1U4*Yf8>&GPFrlRW<Fawea+8SZzp{DxoG9o^J1oXHL)y*
zC4b`^l&mz+la`*npgQj_Cz<PuUT&`VE3SB7=ig{W^=TU$4ry6B+i`gN=~JXHVr7pq
zi*91mmsOfvUChe1?xjR&Tf5u#FaVepv$9Q_xHhrxn;<i-FY0LLjSo9-f6VQ?(b-8m
z9s4_zMhLR|az1I!ZhcSAB$7LFS-`>)`oUpwEMza{>kYb{5e&;&nAf7G7Ipagx?1;j
z0x&D4vyE;9Uer%rPu?bdx>(uuFjRgRE9;Bc+H+98U1n(4;r;3rGJR2NJ7047LRY3{
ze$2n|t5#`CS{tc)8_Lwkf3M3|p0p)pM)I#Mvu{vpwubTQ9DmBlayjtr;@mwCysx@X
z9}n3P7bRMvE-4FDh`7_~Et6+Fud>h;4*u0OHJlzZg)bnl3b4<0b>ANQ5MsmR8PBUM
z73$MG?Nc~8CI(M9Ufu7`RYg{r3eheET;37Aiqkj1UB*b@2ga-Kf3HP%W?y)wT|%1O
zk*s?PCxwI$1Qkvw*eC9m$~T}`8N>eZj_>5|q&*cuGlisO7r4_A4fwchV?hE6vS1n8
z9f%C1Y<N{LHicEz(n_XA4W$Lgv=ok7n9AU$Kw<R6AuBRR{0}*rg`Qk#!7(j`tDYJJ
z!*VL~%tWPS7s^gYe>C7bZ?2KW=;ksgEVGvE`M3GTb<>x#A%~IOV!(9=I{>;>^Wh6F
z-r-*UlH^D4Zt>W=5xh8SGqkg`bUUPT1@PkOsV(Z>G{&&Bl*8VQ;Kf<<;M>y9b<pir
z-HVUTLAIsMn&8?CntwrH8oE4)-V0=>0BJ<{V2#iAM)?Lqe;~W!Vw)AI^@T~x*Yj2{
z-faNQBeO+u(Lp_nV{GzS2Vq)JWud9OthC@ANWIh^q~MrL1TibVw0ZePhQg**LFtP?
zg7-(J6oWB5S7m!-{l15gQ92m6u|W=EQpUhe%@|x%dhx@ALOl`@m0tWXq7e3THmqU*
z-FXAsbT_)NfB5p3h(-50k>T4zq{#3dj|ONe^)UZELv`6Rs#5v;NW=NXN3`tN_BEmz
zYkKvF9a6um#8JrVSun3I%TPm0EUqT)tImB<Dn3GHrx&8pLtD!ypviT5M6K8iFR5ik
zIv+tlGISzc(4o6@J?{O--$rJLa2_bm{e)v!&c@Vpe}`IpfsVx!T??3Yq5BR02S&Z6
zsJ~69dN-7{^iDma@`Sr9+C%qkT6f2$l7*L2A4U)|rT1+HF)8F~;o*o-PDc|7-D0it
zV)7Q%sg|=--1efw(Y8vC=Q{J_og98&^&S4QXXOOv%g;5eTQz6DJo{tmhlBm(n~oGe
zczV{1e~bFqIGQd(GA`+2a8YO2Yxa8eDea$k+r0s_tzhQ`eY^h&)nsY;<p%3JJW+tU
zRI>9ZJ9m9k(W}~xTZa%`l2dU)WYeV`j_I*?)b;G<uq79yw<E=V2;aU}_|7O4Ta0+}
zpQG^u<6DQ}CER_tvlWdW7$+TG)3yV>?{x%we*w(Brr-Z9`u_pd(MdU;WqC^%23>m8
z^+o;U!wCtZbqz0$?CXOKfL$y4@osl7YY4ulvL8=(_oIg3dn#LcS`~Ftr9Tq%JDHC4
zaOa5uZ7W!M(VTnQ{nSmL;LDAB+NL~LwGV%E(C$^ueQci5B-1po+7q5D0BtMiy_h!M
ze>mjls=5&Gr_V+$?Vq9U2oxD}ewd)li|(^oo#uD4eUsofuOjkgHLJ^}Lv_{)E9qx~
zh4l{RGm)C=vg7L<gT|hr9lKdGRu&(%v}C%bZnn(TWyj_A=yEU|w<Z&_z*OgBmZ0ja
z%-{-rSs@`CA{RZ%$X0E-l!K_sHVq*ve<sTkNQ_t|9$2ZEFJ+R#keO?N4&s=))N48}
z;g_EK2H}7|SI^Qb-8AKTi@ELxF2{Pn5|CF1LQ64m?yL_j%@tb7#JRIRv@|$^`kuCV
zP-#Zao%NxmsY!5ICS~!0%Hp|c!iuzI_l5*5+)%PiNwk(^(uJFVloQbVgM!eGf9|9U
zuhH$hgx_|}yb7Gp)8=HTd~5;<u;koXA5fZ5&-1}6mq+=sDxemj9^ivRF3;{|RX{C5
zJ+TLeTprfTs(@OAe?$+i?Rz@QKme7x!ZUgBa_8e%ief63cmhK(RCUqA7+f=jwb%Gr
zFi<x*8k@4>$sn1}W)nnGUnG-8EJdB8AKMumc9_o6+_Be{qvcmC(PF)tKi?I%_di9r
zXNx|6;y~YI1<8cSu#?Xm7Ju8;@$zl!n18pOUf>uTAFsa|;K*!ocFD%JJSxhfzr@W^
z#VNJd0^;3VG-{5~vS@@BD+|pwKB1my9d~`&_9&0P7yWa*eLtTwNnYbUI};6OB621o
z;_!s{uY&AJl-7CNr;nQ(fnyRB{lE@I_)x?SEwM3mN!E)}yRa_zVSoA^-F;Y^+cs%l
zr6(!Wc>XK<pRd}TPh|ZOEK!B}=O*uHqZ&5ZCEUty6F3fQpog(SG*qCCbFL6=Hux1;
zeJ1xw+94Ce=CU*Qbc~1ZpHX~jo2tMk9q$PXh;Pp*8j5P~iJ>#y_M+nneztp2e4JC3
zSDQ*q)$685k4^K^{eR^VN7c_&+P=_ab8$SPmPP?b{>z<YxR8h9bg3VgL^IT{VkjJC
zh@hxHe3fXb65YPz)ft=7PP5<eb>gW`oE`bAHa2p9PQLk7%zOJz$Qx9WanEgaXRyor
z_anvaiefymdb;iQX?}rxeRGao5Xe>jU_(0>UiS)fVPDsnynm@cTb}4uiCr##S|Ja=
zqv`dBeTLKhrwKmka>tDYJ(~ZG$N&6kz#orB_$ZF3qG9#@nTd9yI5Hw(F}KK<rgJ2L
zh_Dvz2k*PSsMy1iE-XhQjHj}B#D5NzB7QZrtZDJX?%dIsfrdDy_PrUtvZhY28Y<gw
zA?}-a`}TvOCx35ljp2uqROi)AFzg%AHxYXQ!pS*OmE%k|<~;rjk8SpQX~@I7OZ}gn
zOgH}1Di(gDsr|&X{m`J5wV!yX70<O|)_!8zegv_qsS5WySP62-W<QuETT;-}<@XyH
zb|m6g`!hC*skW8M&9+Z6G<rfHsD-7c7L`Rs-YG3m_kXu|e5R20PkMWL<#k=O+WId`
zhEF1fsgqt7o*q2p-lAWDlXfKSyN4lUG7J<A`t5ZM+Gqd$Tx2hJWYD)b)XwM=8{f;)
zVa_7nSG8fGd2fathKVF;JS@;}Ah*c!H}^c&mj%{*3inE1<~{69Wn9`hFEsDP)NgCJ
zg|+ipD}RHf1KD_70LHYR6gu$U6rOg7?-i|QSi#G><!}y;eM8z0(_Cc2>CfxF`zK!x
z+tIBB82c-}cJ$}<bK)llK{QV&2cLC_?={afL(BPYmwuI@3+m-2^Zo1F1r*<z(lerX
z-q1*+M}pSAsoUpGv+Lfak6Pzz{z(HUd+6F-@qY@JjdAhj+-Bsl`29KU|Fes0^rQbj
zdz(M6(EiDzk(1GUGGZqqdeYEZNtBR|ZHwOZ>AXoi9pRxoZg6BA7Y?mh5;Uv{#|E?^
zl*AF~*yL$PlTK|d8tO-+epHy=5x<j2A?70mGEh)Gc({DPp1%0+`-y3<95&SX-ms}M
zHh;B`&?%-{@sLCGD&S`b7g&%hJj6pk*(>x<J=eTxDdigWr28ovs<J!-sTz${S!2Nu
ztGOy|NMlu<4hhS<l*m3bovYFqb(&)v4;x&mG@|b%S(*4I&GX@jKP8Ol@>Jx0={t81
z-n>-<v(piGI^s^-dLf$*9qxrReoc}61AlGh(R&>UmVY3bF5h~3mb+4BPeG}t<8gzo
zfV%I)aVt*ZVz6dR=Z@(dE{$I3GlSgp!>9&7G)V4itVGYJr&HVf*dfb@1?T69^M1kk
zZm2`gzh#_LO%@Q*CPVs}sU}Ul32NHPVmO6t;H<@zv5jG_v8Kej-9hKtPCqS$zkl|s
ztI2k5OrPqe>x(SOjwW-{t4g=;y2T?z_mrnk!L+`}C6Zb7=I299@~bC=|Ec?!?dTMb
zJ3Wyk>kvhEE)Ed*4~FnRA0n=3H0~`m6eT&_v8cIsH-~uG@GDNsr>4a^RZf0jpkXJk
z`0WIAbBM;Bz@~%dw*7L5e?O!4!hd?&mptBX_+@AuM*91V^zkmH+kX9Wh{mJ1KmK?Z
zu`Rw#&C8yfrsF3P@CA8tYz4Oxtnv6XQe(%>jhvpO;+K2etbMNoot}t8f$cjLmiFsL
z12jO!_qSO$tMSX2Z0dyJd!Zu#*~ukRZ^{{_5&L}KiT}ot|Hfl$DDqz%t$+B%lM4Us
z$p7D7Rrsr;6@QH$P>HgB3>c<I3mz}O(git8ZLo>CWcJubTT)}X(J2}ldFYNGRDePW
ztvhC+%^jHldEKnlvd8Kf($}S*UVKPnb|dZUbiZxjwl6yv+_KYBE6KPcZN^@zz)=#n
zJc&uDX$qwdK-qhR6f9;7$bT%+=vatbbcM~z>~u{2ykzf1a^}QKI6A1C;fDDoe?rM0
zu8x-d!GxcSugv!-;pds-cF8fHiI!*fx+Pn3XqO*fXV9<Q!a*xbNwk!t`723F<Vka4
z`>*NmUvWKpv%VdUM#E9k`LUjbOj9V{W4AGm4C&_Ff=w4Gx13;pT7P3s{Ujb3&ba|y
zPpPsT58|?C{2=2;BHvN*^sJdARTz#TZ)K2pcsQP$o}<G#E3@(N4nLG~HeNo)kEs8S
zP)**0{!vt9PL}i_EbJn`o*Lc2N8u0V`ex0AN18(=JW4-CL#1e{M7yM^Qba3RDKH+6
zhr{HdKQ(Og7s<_Kcz>%TT;56X;){?l_u#H^uflKtLtm8_Hc__1Xxl)WLY>;;75hO~
z3p4F?7j@R*k?J!cQoA|#QJQ7=X+WC97-dFm|6Vf--{k1Xf=ROTZ@k^D!^r42cUzS4
z5P9u6wX<n|Q`}kz)C}d;o6L#e3mCHtNP2^5nBaO9xPVd7pMPkX1Gm6w&VR_|n?Lxs
z3Vd2&Z72PQg#Y}oZ&8|8g7vC~<F21O&alGo9Xa&%2akMB=@*ZS`tna6IjmjZJo0n_
zK6>QLcKzy+w;1TNN6t#a?;d%hoIZTyD3xC)@<iIt6FE@f_lZ2%<^x5p^1d$=d6od5
zC<^VCe4{8fO@H%|B1ho*l_Jjz^O+*QDO%oS>us6FAJfuw{MKB_w7zC1s=q3-T-|S7
ze~mxo=QSjva!V#5(wdIVw5h4qWtKD>gf#`XztalXVCSmsx}Ylz?LJOsOF9TqJuKCT
zZ$$dV?Xr1~M;RJP)c*L>Tx_sq*P;XXst9;bmv}tEfPaStCzu8NdJ2OL!cTS`KUL##
z1Ac0&|7t^Q81QFq>enR{CV_szVfYe<xq05+;?rgb6gGK(A;fV;Q)S{+6A32M0}A6o
zW>Iy+9-Td4^9wWCKkB~dOWEBzo@M0!Q)3+R`+qrr`Z3vb``fb{0InO?^zUCT*q3_Q
i&9m5wry1Ng;Oh{1@+}Qv#~9)RJO70|4*wr9-QvyfSGXVm

diff --git a/docs/py-modindex.html b/docs/py-modindex.html
index 5be6aa68..bfd7abbd 100644
--- a/docs/py-modindex.html
+++ b/docs/py-modindex.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Python Module Index &mdash; DiCE 0.8 documentation</title>
+  <title>Python Module Index &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -13,7 +13,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -239,6 +241,11 @@ <h1>Python Module Index</h1>
        <td>&#160;&#160;&#160;
        <a href="dice_ml.utils.html#module-dice_ml.utils.helpers"><code class="xref">dice_ml.utils.helpers</code></a></td><td>
        <em></em></td></tr>
+     <tr class="cg-1">
+       <td></td>
+       <td>&#160;&#160;&#160;
+       <a href="dice_ml.utils.html#module-dice_ml.utils.neuralnetworks"><code class="xref">dice_ml.utils.neuralnetworks</code></a></td><td>
+       <em></em></td></tr>
      <tr class="cg-1">
        <td></td>
        <td>&#160;&#160;&#160;
diff --git a/docs/readme.html b/docs/readme.html
index 2d786adb..e82b06e3 100644
--- a/docs/readme.html
+++ b/docs/readme.html
@@ -4,7 +4,7 @@
   <meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Diverse Counterfactual Explanations (DiCE) for ML &mdash; DiCE 0.8 documentation</title>
+  <title>Diverse Counterfactual Explanations (DiCE) for ML &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
@@ -60,7 +62,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
@@ -118,9 +120,9 @@
     text-align: unset;
 }
 </style>
-<p><a class="reference external" href="https://github.com/interpretml/dice/actions?query=workflow%3A%22Python+package%22"><img alt="BuildStatus" src="https://github.com/interpretml/dice/workflows/Python%20package/badge.svg" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PyPiVersion" src="https://img.shields.io/pypi/v/dice-ml" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PythonSupport" src="https://img.shields.io/pypi/pyversions/dice-ml" /></a></p>
+<p><a class="reference external" href="https://github.com/interpretml/dice/actions?query=workflow%3A%22Python+package%22"><img alt="BuildStatus" src="https://github.com/interpretml/dice/workflows/Python%20package/badge.svg" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PyPiVersion" src="https://img.shields.io/pypi/v/dice-ml" /></a> <a class="reference external" href="https://pypi.org/project/dice-ml/"><img alt="PythonSupport" src="https://img.shields.io/pypi/pyversions/dice-ml" /></a> <a class="reference external" href="https://anaconda.org/conda-forge/dice-ml"><img alt="CondaVersion" src="https://anaconda.org/conda-forge/dice-ml/badges/version.svg" /></a></p>
 <section id="diverse-counterfactual-explanations-dice-for-ml">
-<h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href="#diverse-counterfactual-explanations-dice-for-ml" title="Permalink to this headline"></a></h1>
+<h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href="#diverse-counterfactual-explanations-dice-for-ml" title="Permalink to this heading"></a></h1>
 <p><em>How to explain a machine learning model such that the explanation is truthful to the model and yet interpretable to people?</em></p>
 <p><a class="reference external" href="https://raam93.github.io/">Ramaravind K. Mothilal</a>, <a class="reference external" href="http://www.amitsharma.in/">Amit Sharma</a>, <a class="reference external" href="https://chenhaot.com/">Chenhao Tan</a></p>
 <p><a class="reference external" href="https://arxiv.org/abs/1905.07697">FAT* ‘20 paper</a> | <a class="reference external" href="https://interpretml.github.io/DiCE/">Docs</a> | <a class="reference external" href="https://github.com/interpretml/DiCE/tree/master/docs/source/notebooks">Example Notebooks</a> | Live Jupyter notebook <a class="reference external" href="https://mybinder.org/v2/gh/interpretML/DiCE/master?filepath=docs/source/notebooks"><img alt="Binder" src="https://mybinder.org/badge_logo.svg" /></a></p>
@@ -136,11 +138,15 @@ <h1>Diverse Counterfactual Explanations (DiCE) for ML<a class="headerlink" href=
 <p>DiCE implements <a class="reference external" href="https://arxiv.org/abs/1711.00399">counterfactual (CF) explanations</a>  that provide this information by showing feature-perturbed versions of the same person who would have received the loan, e.g., <code class="docutils literal notranslate"><span class="pre">you</span> <span class="pre">would</span> <span class="pre">have</span> <span class="pre">received</span> <span class="pre">the</span> <span class="pre">loan</span> <span class="pre">if</span> <span class="pre">your</span> <span class="pre">income</span> <span class="pre">was</span> <span class="pre">higher</span> <span class="pre">by</span> <span class="pre">$10,000</span></code>. In other words, it provides “what-if” explanations for model output and can be a useful complement to other explanation methods, both for end-users and model developers.</p>
 <p>Barring simple linear models, however, it is difficult to generate CF examples that work for any machine learning model. DiCE is based on <a class="reference external" href="https://arxiv.org/abs/1905.07697">recent research</a> that generates CF explanations for any ML model. The core idea is to setup finding such explanations as an optimization problem, similar to finding adversarial examples. The critical difference is that for explanations, we need perturbations that change the output of a machine learning model, but are also diverse and feasible to change. Therefore, DiCE supports generating a set of counterfactual explanations  and has tunable parameters for diversity and proximity of the explanations to the original input. It also supports simple constraints on features to ensure feasibility of the generated counterfactual examples.</p>
 <section id="installing-dice">
-<h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalink to this headline"></a></h2>
+<h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalink to this heading"></a></h2>
 <p>DiCE supports Python 3+. The stable version of DiCE is available on <a class="reference external" href="https://pypi.org/project/dice-ml/">PyPI</a>.</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip install dice-ml
 </pre></div>
 </div>
+<p>DiCE is also available on <a class="reference external" href="https://anaconda.org/conda-forge/dice-ml">conda-forge</a>.</p>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>conda install -c conda-forge dice-ml
+</pre></div>
+</div>
 <p>To install the latest (dev) version of DiCE and its dependencies, clone this repo and run <cite>pip install</cite> from the top-most folder of the repo:</p>
 <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip install -e .
 </pre></div>
@@ -165,7 +171,7 @@ <h2>Installing DICE<a class="headerlink" href="#installing-dice" title="Permalin
 </ul>
 </section>
 <section id="getting-started-with-dice">
-<h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-dice" title="Permalink to this headline"></a></h2>
+<h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-dice" title="Permalink to this heading"></a></h2>
 <p>With DiCE, generating explanations is a simple three-step  process: train
 mode and then invoke DiCE to generate counterfactual examples for any input.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">dice_ml</span>
@@ -218,7 +224,7 @@ <h2>Getting started with DiCE<a class="headerlink" href="#getting-started-with-d
 </ul>
 </section>
 <section id="supported-methods-for-generating-counterfactuals">
-<h2>Supported methods for generating counterfactuals<a class="headerlink" href="#supported-methods-for-generating-counterfactuals" title="Permalink to this headline"></a></h2>
+<h2>Supported methods for generating counterfactuals<a class="headerlink" href="#supported-methods-for-generating-counterfactuals" title="Permalink to this heading"></a></h2>
 <p>DiCE can generate counterfactual examples using the following methods.</p>
 <p><strong>Model-agnostic methods</strong></p>
 <ul class="simple">
@@ -235,7 +241,7 @@ <h2>Supported methods for generating counterfactuals<a class="headerlink" href="
 <p>The last two methods require a differentiable model, such as a neural network. If you are interested in a specific method, do raise an issue <a class="reference external" href="https://github.com/interpretml/DiCE/issues">here</a>.</p>
 </section>
 <section id="supported-use-cases">
-<h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="Permalink to this headline"></a></h2>
+<h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="Permalink to this heading"></a></h2>
 <p><strong>Data</strong></p>
 <p>DiCE does not need access to the full dataset. It only requires metadata properties for each feature (min, max for continuous features and levels for categorical features). Thus, for sensitive data, the dataset can be provided as:</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">d</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">Data</span><span class="p">(</span><span class="n">features</span><span class="o">=</span><span class="p">{</span>
@@ -273,7 +279,7 @@ <h2>Supported use-cases<a class="headerlink" href="#supported-use-cases" title="
 <p>We visualize explanations through a table highlighting the change in features. We plan to support an English language explanation too!</p>
 </section>
 <section id="feasibility-of-counterfactual-explanations">
-<h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasibility-of-counterfactual-explanations" title="Permalink to this headline"></a></h2>
+<h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasibility-of-counterfactual-explanations" title="Permalink to this heading"></a></h2>
 <p>We acknowledge that not all counterfactual explanations may be feasible for a
 user. In general, counterfactuals closer to an individual’s profile will be
 more feasible. Diversity is also important to help an individual choose between
@@ -308,7 +314,7 @@ <h2>Feasibility of counterfactual explanations<a class="headerlink" href="#feasi
 <p>For more details, check out <a class="reference external" href="https://github.com/interpretml/DiCE/blob/master/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb">this</a> notebook.</p>
 </section>
 <section id="the-promise-of-counterfactual-explanations">
-<h2>The promise of counterfactual explanations<a class="headerlink" href="#the-promise-of-counterfactual-explanations" title="Permalink to this headline"></a></h2>
+<h2>The promise of counterfactual explanations<a class="headerlink" href="#the-promise-of-counterfactual-explanations" title="Permalink to this heading"></a></h2>
 <p>Being truthful to the model, counterfactual explanations can be useful to all stakeholders for a decision made by a machine learning model that makes decisions.</p>
 <ul class="simple">
 <li><p><strong>Decision subjects</strong>: Counterfactual explanations can be used to explore actionable recourse for a person based on a decision received by a ML model. DiCE shows decision outcomes with <em>actionable</em> alternative profiles, to help people understand what they could have done to change their model outcome.</p></li>
@@ -321,7 +327,7 @@ <h2>The promise of counterfactual explanations<a class="headerlink" href="#the-p
 </ul>
 </section>
 <section id="roadmap">
-<h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this headline"></a></h2>
+<h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this heading"></a></h2>
 <p>Ideally, counterfactual explanations should balance between a wide range of suggested changes (<em>diversity</em>), and the relative ease of adopting those changes (<em>proximity</em> to the original input), and also follow the causal laws of the world, e.g., one can hardly lower their educational degree or change their race.</p>
 <p>We are working on adding the following features to DiCE:</p>
 <ul class="simple">
@@ -333,7 +339,7 @@ <h2>Roadmap<a class="headerlink" href="#roadmap" title="Permalink to this headli
 </ul>
 </section>
 <section id="citing">
-<h2>Citing<a class="headerlink" href="#citing" title="Permalink to this headline"></a></h2>
+<h2>Citing<a class="headerlink" href="#citing" title="Permalink to this heading"></a></h2>
 <p>If you find DiCE useful for your research work, please cite it as follows.</p>
 <p>Ramaravind K. Mothilal, Amit Sharma, and Chenhao Tan (2020). <strong>Explaining machine learning classifiers through diverse counterfactual explanations</strong>. <em>Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency</em>.</p>
 <p>Bibtex:</p>
@@ -348,7 +354,7 @@ <h2>Citing<a class="headerlink" href="#citing" title="Permalink to this headline
 </div>
 </section>
 <section id="contributing">
-<h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to this headline"></a></h2>
+<h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to this heading"></a></h2>
 <p>This project welcomes contributions and suggestions.  Most contributions require you to agree to a
 Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
 the rights to use your contribution. For details, visit <a class="reference external" href="https://cla.microsoft.com">https://cla.microsoft.com</a>.</p>
diff --git a/docs/search.html b/docs/search.html
index 37883ffb..7fa10f4f 100644
--- a/docs/search.html
+++ b/docs/search.html
@@ -3,7 +3,7 @@
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-  <title>Search &mdash; DiCE 0.8 documentation</title>
+  <title>Search &mdash; DiCE 0.9 documentation</title>
       <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
       <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
     
@@ -14,7 +14,9 @@
         <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
         <script src="_static/jquery.js"></script>
         <script src="_static/underscore.js"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
         <script src="_static/doctools.js"></script>
+        <script src="_static/sphinx_highlight.js"></script>
         <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
     <script src="_static/js/theme.js"></script>
     <script src="_static/searchtools.js"></script>
@@ -49,7 +51,7 @@
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html">Generating counterfactuals for multi-class classification and regression models</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_multiclass_classification_and_regression.html#Regression">Regression</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_model_agnostic_CFs.html">Generating counterfactual explanations with any ML model</a></li>
-<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating Counterfactual Explanations without access to training data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_private_data.html">Generating counterfactual explanations without access to training data</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_with_advanced_options.html">Advanced options to customize Counterfactual Explanations</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html">Generate feasible counterfactual explanations using a VAE</a></li>
 <li class="toctree-l1"><a class="reference internal" href="notebooks/DiCE_getting_started_feasible.html#Adding-feasibility-constraints">Adding feasibility constraints</a></li>
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 28ef4a1c..6c57bc10 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["dice_ml","dice_ml.data_interfaces","dice_ml.explainer_interfaces","dice_ml.model_interfaces","dice_ml.schema","dice_ml.utils","dice_ml.utils.sample_architecture","index","modules","notebooks/Benchmarking_different_CF_explanation_methods","notebooks/DiCE_feature_importances","notebooks/DiCE_getting_started","notebooks/DiCE_getting_started_feasible","notebooks/DiCE_model_agnostic_CFs","notebooks/DiCE_multiclass_classification_and_regression","notebooks/DiCE_with_advanced_options","notebooks/DiCE_with_private_data","notebooks/Untitled","notebooks/nb_index","readme"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,"sphinx.ext.todo":2,"sphinx.ext.viewcode":1,nbsphinx:4,sphinx:56},filenames:["dice_ml.rst","dice_ml.data_interfaces.rst","dice_ml.explainer_interfaces.rst","dice_ml.model_interfaces.rst","dice_ml.schema.rst","dice_ml.utils.rst","dice_ml.utils.sample_architecture.rst","index.rst","modules.rst","notebooks/Benchmarking_different_CF_explanation_methods.ipynb","notebooks/DiCE_feature_importances.ipynb","notebooks/DiCE_getting_started.ipynb","notebooks/DiCE_getting_started_feasible.ipynb","notebooks/DiCE_model_agnostic_CFs.ipynb","notebooks/DiCE_multiclass_classification_and_regression.ipynb","notebooks/DiCE_with_advanced_options.ipynb","notebooks/DiCE_with_private_data.ipynb","notebooks/Untitled.ipynb","notebooks/nb_index.rst","readme.rst"],objects:{"":[[0,0,0,"-","dice_ml"]],"dice_ml.Data":[[0,2,1,"","decide_implementation_type"]],"dice_ml.Dice":[[0,2,1,"","decide_implementation_type"]],"dice_ml.Model":[[0,2,1,"","decide_implementation_type"]],"dice_ml.constants":[[0,1,1,"","BackEndTypes"],[0,1,1,"","ModelTypes"],[0,1,1,"","SamplingStrategy"]],"dice_ml.constants.BackEndTypes":[[0,3,1,"","ALL"],[0,3,1,"","Pytorch"],[0,3,1,"","Sklearn"],[0,3,1,"","Tensorflow1"],[0,3,1,"","Tensorflow2"]],"dice_ml.constants.ModelTypes":[[0,3,1,"","ALL"],[0,3,1,"","Classifier"],[0,3,1,"","Regressor"]],"dice_ml.constants.SamplingStrategy":[[0,3,1,"","Genetic"],[0,3,1,"","KdTree"],[0,3,1,"","Random"]],"dice_ml.counterfactual_explanations":[[0,1,1,"","CounterfactualExplanations"]],"dice_ml.counterfactual_explanations.CounterfactualExplanations":[[0,4,1,"","cf_examples_list"],[0,2,1,"","from_json"],[0,4,1,"","local_importance"],[0,4,1,"","metadata"],[0,4,1,"","summary_importance"],[0,2,1,"","to_json"],[0,2,1,"","visualize_as_dataframe"],[0,2,1,"","visualize_as_list"]],"dice_ml.data":[[0,1,1,"","Data"],[0,5,1,"","decide"]],"dice_ml.data.Data":[[0,2,1,"","decide_implementation_type"]],"dice_ml.data_interfaces":[[1,0,0,"-","base_data_interface"],[1,0,0,"-","private_data_interface"],[1,0,0,"-","public_data_interface"]],"dice_ml.data_interfaces.private_data_interface":[[1,1,1,"","PrivateData"]],"dice_ml.data_interfaces.private_data_interface.PrivateData":[[1,2,1,"","create_ohe_params"],[1,2,1,"","de_normalize_data"],[1,2,1,"","from_dummies"],[1,2,1,"","from_label"],[1,2,1,"","get_data_params_for_gradient_dice"],[1,2,1,"","get_decimal_precisions"],[1,2,1,"","get_decoded_data"],[1,2,1,"","get_encoded_categorical_feature_indexes"],[1,2,1,"","get_indexes_of_features_to_vary"],[1,2,1,"","get_inverse_ohe_min_max_normalized_data"],[1,2,1,"","get_mads"],[1,2,1,"","get_minx_maxx"],[1,2,1,"","get_ohe_min_max_normalized_data"],[1,2,1,"","get_valid_mads"],[1,2,1,"","normalize_data"],[1,2,1,"","one_hot_encode_data"],[1,2,1,"","prepare_df_for_ohe_encoding"],[1,2,1,"","prepare_query_instance"]],"dice_ml.data_interfaces.public_data_interface":[[1,1,1,"","PublicData"]],"dice_ml.data_interfaces.public_data_interface.PublicData":[[1,2,1,"","check_features_to_vary"],[1,2,1,"","check_mad_validity"],[1,2,1,"","check_permitted_range"],[1,2,1,"","create_ohe_params"],[1,2,1,"","de_normalize_data"],[1,2,1,"","from_dummies"],[1,2,1,"","from_label"],[1,2,1,"","get_data_params_for_gradient_dice"],[1,2,1,"","get_data_type"],[1,2,1,"","get_decimal_precisions"],[1,2,1,"","get_decoded_data"],[1,2,1,"","get_encoded_categorical_feature_indexes"],[1,2,1,"","get_features_range"],[1,2,1,"","get_indexes_of_features_to_vary"],[1,2,1,"","get_inverse_ohe_min_max_normalized_data"],[1,2,1,"","get_mads"],[1,2,1,"","get_minx_maxx"],[1,2,1,"","get_ohe_min_max_normalized_data"],[1,2,1,"","get_quantiles_from_training_data"],[1,2,1,"","get_valid_feature_range"],[1,2,1,"","get_valid_mads"],[1,2,1,"","normalize_data"],[1,2,1,"","one_hot_encode_data"],[1,2,1,"","prepare_df_for_ohe_encoding"],[1,2,1,"","prepare_query_instance"]],"dice_ml.dice":[[0,1,1,"","Dice"],[0,5,1,"","decide"]],"dice_ml.dice.Dice":[[0,2,1,"","decide_implementation_type"]],"dice_ml.diverse_counterfactuals":[[0,1,1,"","CounterfactualExamples"],[0,5,1,"","json_converter"]],"dice_ml.diverse_counterfactuals.CounterfactualExamples":[[0,2,1,"","display_df"],[0,2,1,"","from_json"],[0,2,1,"","print_list"],[0,2,1,"","to_json"],[0,2,1,"","visualize_as_dataframe"],[0,2,1,"","visualize_as_list"]],"dice_ml.explainer_interfaces":[[2,0,0,"-","dice_KD"],[2,0,0,"-","dice_genetic"],[2,0,0,"-","dice_pytorch"],[2,0,0,"-","dice_random"],[2,0,0,"-","dice_tensorflow1"],[2,0,0,"-","dice_tensorflow2"],[2,0,0,"-","explainer_base"],[2,0,0,"-","feasible_base_vae"],[2,0,0,"-","feasible_model_approx"]],"dice_ml.explainer_interfaces.dice_KD":[[2,1,1,"","DiceKD"]],"dice_ml.explainer_interfaces.dice_KD.DiceKD":[[2,2,1,"","do_sparsity_check"],[2,2,1,"","duplicates"],[2,2,1,"","find_counterfactuals"],[2,2,1,"","predict_fn"],[2,2,1,"","vary_valid"]],"dice_ml.explainer_interfaces.dice_genetic":[[2,1,1,"","DiceGenetic"]],"dice_ml.explainer_interfaces.dice_genetic.DiceGenetic":[[2,2,1,"","compute_loss"],[2,2,1,"","compute_proximity_loss"],[2,2,1,"","compute_sparsity_loss"],[2,2,1,"","compute_yloss"],[2,2,1,"","do_KD_init"],[2,2,1,"","do_cf_initializations"],[2,2,1,"","do_loss_initializations"],[2,2,1,"","do_param_initializations"],[2,2,1,"","do_random_init"],[2,2,1,"","find_counterfactuals"],[2,2,1,"","get_valid_feature_range"],[2,2,1,"","label_decode"],[2,2,1,"","label_decode_cfs"],[2,2,1,"","label_encode"],[2,2,1,"","mate"],[2,2,1,"","predict_fn"],[2,2,1,"","predict_fn_scores"],[2,2,1,"","update_hyperparameters"]],"dice_ml.explainer_interfaces.dice_pytorch":[[2,1,1,"","DicePyTorch"]],"dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch":[[2,2,1,"","compute_dist"],[2,2,1,"","compute_diversity_loss"],[2,2,1,"","compute_loss"],[2,2,1,"","compute_proximity_loss"],[2,2,1,"","compute_regularization_loss"],[2,2,1,"","compute_yloss"],[2,2,1,"","do_cf_initializations"],[2,2,1,"","do_loss_initializations"],[2,2,1,"","do_optimizer_initializations"],[2,2,1,"","dpp_style"],[2,2,1,"","find_counterfactuals"],[2,2,1,"","generate_counterfactuals"],[2,2,1,"","get_model_output"],[2,2,1,"","initialize_CFs"],[2,2,1,"","predict_fn"],[2,2,1,"","predict_fn_for_sparsity"],[2,2,1,"","round_off_cfs"],[2,2,1,"","stop_loop"],[2,2,1,"","update_hyperparameters"]],"dice_ml.explainer_interfaces.dice_random":[[2,1,1,"","DiceRandom"]],"dice_ml.explainer_interfaces.dice_random.DiceRandom":[[2,2,1,"","get_continuous_samples"],[2,2,1,"","get_samples"]],"dice_ml.explainer_interfaces.dice_tensorflow1":[[2,1,1,"","DiceTensorFlow1"]],"dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1":[[2,2,1,"","compute_dist"],[2,2,1,"","compute_diversity_loss"],[2,2,1,"","compute_proximity_loss"],[2,2,1,"","compute_regularization_loss"],[2,2,1,"","compute_yloss"],[2,2,1,"","do_cf_initializations"],[2,2,1,"","do_loss_initializations"],[2,2,1,"","do_optimizer_initializations"],[2,2,1,"","dpp_style"],[2,2,1,"","find_counterfactuals"],[2,2,1,"","generate_counterfactuals"],[2,2,1,"","initialize_CFs"],[2,2,1,"","predict_fn"],[2,2,1,"","predict_fn_for_sparsity"],[2,2,1,"","round_off_cfs"],[2,2,1,"","scipy_optimizers"],[2,2,1,"","stop_loop"],[2,2,1,"","tensorflow_optimizers"],[2,2,1,"","update_hyperparameters"]],"dice_ml.explainer_interfaces.dice_tensorflow2":[[2,1,1,"","DiceTensorFlow2"]],"dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2":[[2,2,1,"","compute_dist"],[2,2,1,"","compute_diversity_loss"],[2,2,1,"","compute_loss"],[2,2,1,"","compute_proximity_loss"],[2,2,1,"","compute_regularization_loss"],[2,2,1,"","compute_yloss"],[2,2,1,"","do_cf_initializations"],[2,2,1,"","do_loss_initializations"],[2,2,1,"","do_optimizer_initializations"],[2,2,1,"","dpp_style"],[2,2,1,"","find_counterfactuals"],[2,2,1,"","generate_counterfactuals"],[2,2,1,"","initialize_CFs"],[2,2,1,"","predict_fn"],[2,2,1,"","predict_fn_for_sparsity"],[2,2,1,"","round_off_cfs"],[2,2,1,"","stop_loop"],[2,2,1,"","update_hyperparameters"]],"dice_ml.explainer_interfaces.explainer_base":[[2,1,1,"","ExplainerBase"]],"dice_ml.explainer_interfaces.explainer_base.ExplainerBase":[[2,2,1,"","build_KD_tree"],[2,2,1,"","check_permitted_range"],[2,2,1,"","check_query_instance_validity"],[2,2,1,"","decide_cf_validity"],[2,2,1,"","deserialize_explainer"],[2,2,1,"","do_binary_search"],[2,2,1,"","do_linear_search"],[2,2,1,"","do_posthoc_sparsity_enhancement"],[2,2,1,"","feature_importance"],[2,2,1,"","generate_counterfactuals"],[2,2,1,"","get_model_output_from_scores"],[2,2,1,"","global_feature_importance"],[2,2,1,"","infer_target_cfs_class"],[2,2,1,"","infer_target_cfs_range"],[2,2,1,"","is_cf_valid"],[2,2,1,"","local_feature_importance"],[2,2,1,"","misc_init"],[2,2,1,"","predict_fn"],[2,2,1,"","predict_fn_for_sparsity"],[2,2,1,"","round_to_precision"],[2,2,1,"","serialize_explainer"],[2,2,1,"","setup"],[2,2,1,"","sigmoid"]],"dice_ml.explainer_interfaces.feasible_base_vae":[[2,1,1,"","FeasibleBaseVAE"]],"dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE":[[2,2,1,"","compute_loss"],[2,2,1,"","generate_counterfactuals"],[2,2,1,"","train"]],"dice_ml.explainer_interfaces.feasible_model_approx":[[2,1,1,"","FeasibleModelApprox"]],"dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox":[[2,2,1,"","train"]],"dice_ml.model":[[0,1,1,"","Model"],[0,5,1,"","decide"]],"dice_ml.model.Model":[[0,2,1,"","decide_implementation_type"]],"dice_ml.model_interfaces":[[3,0,0,"-","base_model"],[3,0,0,"-","keras_tensorflow_model"],[3,0,0,"-","pytorch_model"]],"dice_ml.model_interfaces.base_model":[[3,1,1,"","BaseModel"]],"dice_ml.model_interfaces.base_model.BaseModel":[[3,2,1,"","get_gradient"],[3,2,1,"","get_num_output_nodes"],[3,2,1,"","get_num_output_nodes2"],[3,2,1,"","get_output"],[3,2,1,"","load_model"]],"dice_ml.model_interfaces.keras_tensorflow_model":[[3,1,1,"","KerasTensorFlowModel"]],"dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel":[[3,2,1,"","get_gradient"],[3,2,1,"","get_num_output_nodes"],[3,2,1,"","get_output"],[3,2,1,"","load_model"]],"dice_ml.model_interfaces.pytorch_model":[[3,1,1,"","PyTorchModel"]],"dice_ml.model_interfaces.pytorch_model.PyTorchModel":[[3,2,1,"","get_gradient"],[3,2,1,"","get_num_output_nodes"],[3,2,1,"","get_output"],[3,2,1,"","load_model"],[3,2,1,"","set_eval_mode"]],"dice_ml.utils":[[5,0,0,"-","exception"],[5,0,0,"-","helpers"],[6,0,0,"-","sample_architecture"],[5,0,0,"-","serialize"]],"dice_ml.utils.exception":[[5,6,1,"","SystemException"],[5,6,1,"","UserConfigValidationException"]],"dice_ml.utils.helpers":[[5,1,1,"","DataTransfomer"],[5,5,1,"","get_adult_data_info"],[5,5,1,"","get_adult_income_modelpath"],[5,5,1,"","get_base_gen_cf_initialization"],[5,5,1,"","get_custom_dataset_modelpath_pipeline"],[5,5,1,"","get_custom_dataset_modelpath_pipeline_binary"],[5,5,1,"","get_custom_dataset_modelpath_pipeline_multiclass"],[5,5,1,"","get_custom_dataset_modelpath_pipeline_regression"],[5,5,1,"","get_custom_vars_dataset_modelpath_pipeline"],[5,5,1,"","load_adult_income_dataset"],[5,5,1,"","load_custom_testing_dataset"],[5,5,1,"","load_custom_testing_dataset_binary"],[5,5,1,"","load_custom_testing_dataset_multiclass"],[5,5,1,"","load_custom_testing_dataset_regression"],[5,5,1,"","load_min_max_equal_dataset"],[5,5,1,"","load_outcome_not_last_column_dataset"],[5,5,1,"","ohe_min_max_transformation"]],"dice_ml.utils.helpers.DataTransfomer":[[5,2,1,"","feed_data_params"],[5,2,1,"","initialize_transform_func"],[5,2,1,"","inverse_transform"],[5,2,1,"","transform"]],"dice_ml.utils.sample_architecture":[[6,0,0,"-","vae_model"]],"dice_ml.utils.sample_architecture.vae_model":[[6,1,1,"","AutoEncoder"],[6,1,1,"","CF_VAE"]],"dice_ml.utils.sample_architecture.vae_model.AutoEncoder":[[6,2,1,"","decoder"],[6,2,1,"","encoder"],[6,2,1,"","forward"],[6,2,1,"","normal_likelihood"],[6,2,1,"","sample_latent_code"]],"dice_ml.utils.sample_architecture.vae_model.CF_VAE":[[6,2,1,"","compute_elbo"],[6,2,1,"","decoder"],[6,2,1,"","encoder"],[6,2,1,"","forward"],[6,2,1,"","normal_likelihood"],[6,2,1,"","sample_latent_code"]],"dice_ml.utils.serialize":[[5,1,1,"","DummyDataInterface"]],"dice_ml.utils.serialize.DummyDataInterface":[[5,2,1,"","to_json"]],dice_ml:[[0,1,1,"","Data"],[0,1,1,"","Dice"],[0,1,1,"","Model"],[0,0,0,"-","constants"],[0,0,0,"-","counterfactual_explanations"],[0,0,0,"-","data"],[1,0,0,"-","data_interfaces"],[0,0,0,"-","dice"],[0,0,0,"-","diverse_counterfactuals"],[2,0,0,"-","explainer_interfaces"],[0,0,0,"-","model"],[3,0,0,"-","model_interfaces"],[4,0,0,"-","schema"],[5,0,0,"-","utils"]]},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","attribute","Python attribute"],"4":["py","property","Python property"],"5":["py","function","Python function"],"6":["py","exception","Python exception"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:attribute","4":"py:property","5":"py:function","6":"py:exception"},terms:{"0":[0,1,2,7,9,10,11,12,13,14,15,16,19],"00":[9,10,11,13,14,15,16],"000":[7,19],"001":[7,19],"01":[7,9,10,11,13,14,15,19],"01292":2,"019":[11,15,16],"02":[9,13,14],"023810":14,"02584":2,"026217":14,"02d":9,"03":9,"03277":12,"039710699999995":14,"04it":13,"05":[1,2,9,11,15,16],"06":[9,15],"073059":14,"073446":14,"08":[9,11,15],"081081":14,"0918301":14,"09it":[10,11],"1":[1,2,6,7,9,10,11,12,14,16,17,18,19],"10":[2,7,9,10,11,12,13,14,15,17,19],"100":[7,9,10,11,13,14,19],"1000":2,"1000k":2,"109842":14,"10it":9,"10k":2,"11":[9,10,11,12,13,14,15,16],"115":14,"117":14,"118":14,"119":14,"12":[9,10,11,12,13,14,15,16],"121":[12,14],"122":14,"13":[7,9,11,13,14,15,19],"139":12,"13it":13,"14":[9,10,11,13,14,15],"14296":9,"149":14,"14it":9,"15":[11,13,14,15],"150":14,"151":[11,15,16],"1543":14,"155":11,"1554":14,"156":[11,15,16],"15788":13,"15831":13,"16":[11,13,14,15],"165":12,"1676":9,"169":17,"17":[7,10,11,13,14,15,16,19],"17378":13,"1738":9,"1771361283":17,"18":[11,13],"181467":14,"19":[10,11,13,14],"1907":2,"1912":12,"1e":[2,12],"2":[2,7,9,10,11,12,14,16,17,18,19],"20":[7,9,11,12,13,15,19],"200001":14,"2019":[7,19],"2020":[7,19],"2022":[11,15,16],"202814":16,"203128":16,"203353":16,"204072":16,"2048":12,"20639":14,"20640":14,"20695":13,"21":[10,11,13,14],"2101":2,"22":[7,11,13,14,15,16,19],"22027":[9,13],"22201":13,"23":[10,11,13,14],"235617":5,"23580":13,"238137":14,"23876":13,"24":[10,11,13,14,15],"2401":14,"2457":13,"24it":10,"25":[11,12,13,14],"2574":14,"26":[9,13],"26048":12,"269":[11,15,16],"27":[9,13,15],"27it":10,"28":[9,10,11,12,13,14,15],"281853":14,"288136":14,"29":[11,12,14,15,16],"295":11,"3":[7,9,10,11,12,14,16,18,19],"30":[9,10,11,12,13,15],"3014":14,"303":[11,15,16],"31":[9,11,13],"316901":14,"31it":13,"32":[9,11,12,13,15],"322":14,"3252":14,"33":[10,14],"33it":11,"34":[10,12,14,17],"342795":11,"344":12,"3441":17,"345915":11,"346592":11,"3487":14,"34it":11,"35":[9,10,11,12,13,15],"353536":11,"3564200999999985":14,"36":[11,13,15],"3682":14,"37":[10,14],"38":[10,11,12,14,15,16],"39":[10,11,12,14,15,16,17],"390":14,"393":14,"394":14,"39it":[11,13],"4":[7,9,10,11,12,13,14,15,16,19],"40":[9,10,12,13],"41":[9,11,12,13,14,15],"413":14,"41it":13,"42":[10,12,13,14],"422":14,"43":[10,13,14,16],"437557":15,"44":[10,11,12,15],"445164":15,"445531":15,"446615":15,"44691":14,"45":[7,10,11,12,14,15,16,19],"4511":14,"46":10,"466381":11,"466596":11,"47":[10,11,14,15],"48":[10,13],"49":[10,15],"496":14,"5":[2,7,9,10,11,12,13,14,15,16,19],"50":[7,9,10,11,12,13,15,19],"500":2,"5000":[2,10],"503225":16,"503642":16,"50it":[13,14],"50k":[10,11,12],"51":[10,11,13,15],"516":13,"5173":14,"52":[10,11,14],"521":14,"525":16,"526":14,"53":[10,13],"54":10,"547945":14,"55":[10,13,15,16],"555556":14,"558":14,"55it":11,"56":10,"565":14,"57":10,"58":[10,13],"585":14,"59":[10,13,16],"599998":14,"6":[9,10,11,12,13,14,15,16],"60":[9,10,11,12,13,15,16],"607":[7,19],"61":14,"617":[7,19],"6184":14,"62":[10,11,15],"64":[11,15,16],"6431":14,"65":[9,10,11,12,13,15],"650002":14,"67":[10,13],"671":12,"68":10,"69":[10,13],"7":[9,10,11,12,13,14,15,16],"70":[11,13,15,16],"71":[10,13],"710724":15,"710950":15,"72":11,"73":[10,11,15,16],"73it":[9,13],"74":[10,16],"746479":14,"75":10,"755":16,"75it":9,"76":12,"77":[10,13],"78":10,"79":10,"8":[9,10,11,12,13,14,15,16,17],"80":10,"802260":14,"81":14,"817352":14,"82":[10,13],"839996":14,"84":10,"8462":14,"85":[10,13,14],"86":[10,14],"87":[12,13],"88":[10,14],"88245":14,"89":10,"9":[9,10,11,12,13,14,15,17],"90":[7,10,15,16,19],"91":10,"910112":14,"911":16,"9167":14,"92":[10,14],"93":10,"930712":14,"95":[7,10,19],"96":10,"9608":9,"96489929999999":14,"971880":14,"984127":14,"99":[7,15,16,19],"992958":14,"boolean":[2,3],"case":[10,11,12,15,16],"class":[0,1,2,3,5,6,7,10,11,12,13,18,19],"default":[2,7,11,12,13,15,16,19],"do":[1,7,11,13,15,16,19],"final":[2,7,11,19],"float":[2,12],"function":[0,1,2,5,7,9,10,11,12,13,15,16,19],"import":[0,2,7,9,12,13,14,15,16,17,18,19],"new":[0,2,7,10,11,12,13,14,15,16,19],"null":[10,14],"public":[0,1],"return":[0,1,2,3,5,9,11,12],"static":[0,2],"super":12,"throw":1,"true":[0,1,2,3,5,10,11,12,13,14,15,16],"try":[7,9,11,12,13,15,19],"while":[11,12],A:[0,1,2,5,7,9,11,12,15,19],As:[14,15,16],Being:[7,19],By:[2,7,15,19],For:[2,7,9,10,11,12,14,15,19],If:[1,2,7,11,13,16,19],In:[7,9,11,12,13,15,19],It:[7,11,12,13,15,19],No:[11,13,15,16],OR:3,Of:15,One:1,That:[10,11,12],The:[0,2,11,12,13,14,15,16],These:[2,10,11],To:[0,7,11,12,15,16,19],With:[7,19],_2node:12,_:[1,7,9,19],__version__:[11,15,16],_basedata:[0,1],_generate_counterfactu:1,_setitem_single_column:9,ab:12,abc:2,about:[0,1,12,16],abov:[11,12,15,16],absenc:11,absolut:[1,2,7,15,16,19],accept:2,access:[0,7,11,12,18,19],account:[7,19],accuraci:[7,11,12,16,19],achiev:11,acknowledg:[7,15,19],across:[7,13,19],action:[7,19],activ:[7,12,19],actual:[2,7,19],ad:[7,18,19],adam:[2,7,19],adapt:12,add:[0,1,2,7,11,19],addit:[7,11,12,19],addition:[7,19],adher:1,adopt:[7,19],adpat:12,adult:[5,9,12,13,15,16],adult_data:5,adult_info:[11,12],advanc:[7,12,16,18],adversari:[7,19],affect:15,after:1,ag:[7,9,10,11,12,13,15,16,19],again:[2,12,13],aggreg:[7,11,19],agnost:[7,9,11,19],agre:[7,19],agreement:[7,19],aim:[7,19],al:[7,19],algorithm:[2,7,9,11,14,18,19],all:[0,1,2,3,7,9,10,11,14,15,16,19],allow:[2,7,11,12,15,19],alreadi:1,also:[2,7,10,11,12,13,15,19],altern:[7,19],amit:[7,19],among:11,amshar:[9,11,12,15,16,17],an:[0,1,2,3,5,7,10,11,12,13,15,16,19],analysi:5,analyt:[7,19],ani:[6,7,10,11,14,18,19],ann_model:[7,19],anoth:[11,12],answer:11,appear:[11,15,16],append:[9,10,11,13,14],appli:[7,11,19],approach:12,appropri:[0,7,11,15,16,19],approv:[7,19],approxim:[7,15,19],ar:[0,1,2,3,7,11,12,13,15,16,19],archiv:[5,9,11,12,13,15,16],arg:6,argument:[10,11,12,14],around:11,arrai:[1,3],artifici:15,arug:12,arxiv:[2,12],as_fram:14,ascend:2,assess:[7,19],assign:[2,7,15,19],assoc:[7,9,10,11,12,13,15,16,19],assum:1,assumpt:12,attribut:[2,7,12,18,19],author:[7,19],autoencod:[6,7,19],automat:[7,19],autoreload:[9,10,11,12,13,14,15,16,17],avail:[0,7,16,19],avebedrm:14,aveoccup:14,averoom:14,avg_dist:2,avoid:[2,12],avx2:[11,15,16],axi:[9,10,11,13,14],bachelor:[7,9,10,11,12,13,15,16,19],back:[1,2],backend:[0,3,5,9,10,11,12,13,14,15,16,17],backendtyp:0,balanc:[7,19],bar:[7,19],base:[0,1,2,3,5,6,7,11,12,15,19],base_data_interfac:[0,8],base_model:[0,8],baselin:[11,12,16],basemodel:3,baseva:[7,12,19],basic:16,batch_siz:12,bayesian:[7,19],becaus:12,been:[7,12,15,19],befor:15,behavior:15,behind:13,being:[7,11,19],belong:2,below:[0,10,11,12,13,14,15,16],best:13,better:[7,11,19],between:[1,2,7,11,16,18,19],bia:12,bibtex:[7,19],binar:[11,12],binari:[2,7,11,12,15,16,19],binary_crossentropi:[7,19],black:11,blank:10,blog:[7,19],blue:[7,9,10,11,12,13,16,19],book:[7,19],booktitl:[7,19],bool:2,bot:[7,19],both:[1,7,9,10,12,13,14,15,19],box:11,bring:11,build:[10,13],build_kd_tre:2,built:16,c:[6,12,17],calcul:10,california:14,call:[2,5,11,12,15,16,17],can:[0,2,7,9,10,11,12,13,14,16,19],cannot:[11,15,16],captur:[15,16],cat:[9,10,11,13,14,17],cat_tran:17,categor:[0,1,2,7,9,10,11,13,14,15,16,17,19],categori:[15,16],categorical_featur:14,categorical_feature_nam:9,categorical_penalti:2,categorical_transform:[9,10,11,13,14],categoricalnum:17,caus:[10,11,12],causal:[7,19],cause1:2,cause2:2,cause_1:12,cause_n:12,caveat:9,cc:[11,15,16],certain:11,cf:[2,7,11,12,13,14,19],cf_example_json_str:0,cf_examples_list:[0,2,7,10,19],cf_ix:2,cf_vae:6,cfs_arr:2,cfs_list:10,chanc:[7,19],chang:[2,7,10,11,12,18,19],changeabl:[7,19],check:[1,2,7,9,11,19],check_features_to_vari:1,check_mad_valid:1,check_permitted_rang:[1,2],check_query_instance_valid:2,chenhao:[7,19],choic:[9,12],choos:[7,15,19],cla:[7,19],class_weight:[7,19],classif:[2,7,11,18],classifi:[0,2,3,7,9,10,11,13,14,19],clf:[9,10,11,13,17],clf_iri:14,clone:[7,12,19],close:[2,11,13],closer:[7,15,19],closest:13,cm:14,cobj:10,code:[2,7,11,12,14,17,19],code_obj:17,col:1,col_index:9,collar:[7,9,10,11,12,13,15,16,19],colleg:[7,9,10,11,12,13,15,16,19],column:[1,7,9,10,11,12,13,14,19],columntransform:[9,10,11,13,14,17],com:[5,7,19],combin:[10,15],come:16,comment:[1,2,7,19],compani:[7,19],compar:[11,12,15,16],compat:[11,15,16],compil:[7,11,15,16,19],complement:[7,19],complet:[13,14],complex:[11,12],compon:11,compos:[9,10,11,13,14,17],comput:[1,2,7,11,15,19],compute_dist:2,compute_diversity_loss:2,compute_elbo:6,compute_loss:2,compute_proximity_loss:2,compute_regularization_loss:2,compute_sparsity_loss:2,compute_yloss:2,concept:11,condit:[2,11],conduct:[7,19],confer:[7,19],configur:[5,11,13],consequ:11,conserv:[2,11],consid:[7,19],consider:11,consist:14,constant:[7,8,11,16,17],constrain:[11,12,13],constraint:[2,7,11,18,19],constraint_direct:2,constraint_reg:2,constraint_typ:2,constraint_vari:2,construct:[7,11,12,19],cont_maxx:5,cont_minx:5,contact:[7,19],contain:[0,1,2,3,12,14],containt:5,content:[7,8],continu:[0,1,2,7,11,12,13,15,16,19],continuous_featur:[7,9,10,11,12,13,14,15,17,19],continuous_features_h:14,continuous_features_iri:14,contrast:13,contributor:[7,19],control:13,convei:15,conveni:[11,12],converg:[2,11,13],convert:[0,7,18],copi:[9,12],core:[7,9,11,14,15,16,17,19],correct:[2,16],correspond:2,could:[7,11,15,16,19],count:14,counterfactu:[0,2,18],counterfactual_explan:[7,8],counterfactualexampl:[0,2],counterfactualexplan:[0,2],cours:15,cpu:[11,15,16],cpu_feature_guard:[11,15,16],creat:[1,7,9,10,11,13,14,15,19],create_ohe_param:1,credit:[7,19],crimin:[7,19],criterion:11,critic:[7,11,15,16,19],csv:[7,19],cuda:[11,15,16],cuda_diagnost:[11,15,16],cuda_driv:[11,15,16],cudart:[11,15,16],cudart_stub:[11,15,16],cuinit:[11,15,16],current:[2,9,11,13],current_pr:2,current_pred_orig:2,custom:[7,11,18],custom_model:17,d:[2,7,9,10,11,12,13,15,16,17,19],d_hous:14,d_iri:14,data:[1,2,3,5,7,8,9,11,12,13,14,15,17,18,19],data_df:[5,10],data_df_copi:2,data_interfac:[0,2,5,8,10],data_nam:12,datafram:[1,2,7,9,10,11,12,13,14,15,17,19],dataset:[2,5,7,10,14,16,17,18,19],datasetx:[9,10,13,14],datatransfom:5,de:1,de_normalize_data:1,debug:[7,19],decid:[0,2,7,15,19],decide_cf_valid:2,decide_implementation_typ:0,decimal_prec:2,decis:[7,11,19],declar:[2,7,19],decod:[6,12],decor:[7,19],decreas:12,deep:[7,15,16,18,19],deeplearn:[7,19],default_tim:9,defin:[1,2,5,7,11,15,18],definit:11,degre:[7,19],demonstr:[9,11,12,13,14,15],denot:11,dens:[7,19],depend:[7,19],dependendi:[7,19],deprec:[11,12,15,16],deriv:11,descent:2,describ:[5,7,9,11,12,13,19],descript:[11,12],deseri:0,deserialize_explain:2,desir:[2,7,11,13,14,19],desired_class:[0,2,7,9,10,11,12,13,14,15,16,19],desired_class_input:2,desired_rang:[0,2,10,14],desired_range_input:2,deta:5,detach:12,detail:[2,7,11,12,15,19],determin:[2,3,7,12,19],dev:[7,19],develop:[7,19],deviat:[1,7,15,16,19],devid:2,df:[0,1],df_hous:14,df_iri:14,dice:[1,8,9,12,13,14,15,16,17,18],dice_exp:[7,9,11,12,15,16,19],dice_exp_genet:13,dice_exp_kd:13,dice_exp_random:[9,13],dice_genet:[0,8],dice_getting_start:16,dice_interfac:11,dice_kd:[0,8,9],dice_ml:[7,9,10,11,12,13,14,15,16,17,19],dice_pytorch:[0,8],dice_random:[0,8],dice_tensorflow1:[0,8],dice_tensorflow2:[0,8],dice_tensorflow:11,dicegenet:[0,2,13],dicekd:[0,2,13],dicepytorch:2,dicerandom:2,dicetensorflow1:2,dicetensorflow2:2,dict:[1,11],dictionari:[2,11,12,15,16],diff:2,differ:[0,2,3,7,10,11,12,13,14,16,19],differenti:[7,11,19],difficult:[7,15,19],difficulti:[7,15,19],dim:12,dimens:12,direct:12,directli:[10,16],directori:[11,15,16],discret:[1,11,12],discuss:[15,16],disk:[7,19],displai:13,display_df:0,display_sparse_df:0,display_warn:1,distanc:[2,7,11,15,16,19],distribut:[7,19],divers:[2,9,10,11,14,18],diverse_counterfactu:[2,7,8],diversecf:2,diversity_loss_typ:2,diversity_weight:[2,7,15,19],divid:[7,15,19],divmod:9,divorc:[7,10,11,12,13,16,19],dlerror:[11,15,16],do_binary_search:2,do_cf_initi:2,do_kd_init:2,do_linear_search:2,do_loss_initi:2,do_optimizer_initi:2,do_param_initi:2,do_posthoc_sparsity_enhanc:2,do_random_init:2,do_sparsity_check:2,doc:[7,9,19],doctor:[7,10,11,12,13,15,16,19],document:9,doe:[7,11,15,16,19],domain:[7,19],done:[7,16,19],downsampl:10,downstream:2,dpp:2,dpp_style:2,driver:[11,15,16],drop:[9,10,11,13,14],dso_load:[11,15,16],dtype:[12,14,17],due:[7,19],dummi:1,dummy_data:10,dummydatainterfac:5,dump:17,dump_patch:12,duplic:2,dure:[5,13],dynam:[11,15,16],e1:[10,11],e2:11,e3:11,e:[7,11,15,19],each:[0,2,7,9,10,11,12,13,16,19],eager:[11,16],eas:[7,15,19],easi:11,easili:11,ed:12,edu:[5,9,11,12,13,15,16],educ:[7,9,10,11,12,13,15,16,19],education_assoc:12,education_bachelor:12,education_doctor:12,education_h:12,education_mast:12,education_prof:12,education_school:12,education_som:12,effect:[2,12],effici:13,either:[2,11],elapsed_genet:9,elapsed_kd:9,elapsed_random:9,elif:0,els:[1,2,9,12],emploi:[7,9,10,11,12,13,15,16,19],enabl:[7,11,15,16,19],encod:[1,2,5,6,12,15],encoded_s:[5,12],encourag:2,end:[7,11,19],english:[7,19],enhanc:2,enough:[7,19],ensembl:[9,10,11,13,14,17],ensur:[2,7,13,19],entri:14,environ:[9,12,17],epoch:[5,7,12,19],equal:[2,15,16],error:[5,11,15,16],especi:[7,19],estim:[0,2,7,11,18,19],et:[7,19],evalu:[7,19],even:[7,11,12,19],everi:[2,11],exampl:[0,2,7,10,12,13,16,18,19],except:[0,8,11],exception_messag:5,exec:17,execut:[5,11,16],exist:[2,11,15,16],exp:[7,10,11,12,15,16,17,19],exp_genet:[9,13],exp_genetic_h:14,exp_genetic_iri:14,exp_kd:[9,13],exp_random:[9,13],experi:12,experiment:11,explain:[1,2,7,18,19],explainer_bas:[0,8],explainer_interfac:[0,8],explainerbas:[0,2],explan:[0,2,18],explicit:[7,11,19],explor:[7,11,19],extrem:15,face:[7,19],factor:15,fail:[11,15,16],fair:[7,19],fall:[1,15],fals:[0,1,2,3,7,9,11,13,19],faq:[7,19],fast:12,fat:[7,19],feasibl:[11,13,15,18],feasible_base_va:[0,8,12],feasible_model_approx:[0,8,12],feasiblebaseva:[2,12],feasiblemodelapprox:[2,7,18],featur:[0,1,2,7,9,12,14,16,18,19],feature_import:2,feature_nam:[10,14],feature_names_including_target:10,feature_rang:2,feature_range_input:1,feature_ranges_orig:2,feature_weight:[1,2,7,15,16,19],features_to_vari:[1,2,7,10,11,13,19],fed:[1,2,5],feed_data_param:5,femal:[7,9,10,11,12,13,15,16,19],fetch_california_h:14,few:[0,15],file:[2,11,15,16,17],filenam:17,fill_valu:17,final_cfs_df:[0,7,19],final_cfs_df_spars:0,final_cfs_spars:2,final_indic:2,financ:[7,19],financi:[7,19],find:[2,7,11,13,16,19],find_counterfactu:2,first:[2,10,11,12],fit:[7,9,10,11,12,13,14,17,19],fixed_features_valu:2,flag:[2,11,15,16],flip:[7,19],float64:14,fma:[11,15,16],folder:[7,19],follow:[2,7,11,15,16,19],form:[1,11,12,15,16],formal:11,format:[1,2,12],formul:11,forward:6,found:[11,12,13,15,16],four:11,fourth:12,frame:14,framework:[0,2,3,12,13,15],freeli:13,frequenc:11,from:[1,2,5,7,9,10,11,12,13,14,15,16,17,19],from_dummi:1,from_json:[0,10],from_label:1,full:[7,9,10,11,12,13,14,19],func:[0,3,5],functiontransform:5,further:13,futur:[7,11,19],g:[7,11,15,19],geco:2,gender:[7,9,10,11,12,13,15,16,19],gender_femal:12,gender_mal:12,gener:[2,5,10,18],generate_counterfactu:[2,7,9,10,11,12,13,14,15,16,19],genet:[0,2,7,9,11,14,18,19],genetic_h:14,genetic_iri:14,get:[1,2,5,15],get_adult_data_info:[5,10,11,12],get_adult_income_modelpath:[5,7,11,12,15,16,19],get_base_gen_cf_initi:5,get_continuous_sampl:2,get_custom_dataset_modelpath_pipelin:[5,17],get_custom_dataset_modelpath_pipeline_binari:5,get_custom_dataset_modelpath_pipeline_multiclass:5,get_custom_dataset_modelpath_pipeline_regress:5,get_custom_vars_dataset_modelpath_pipelin:5,get_data_params_for_gradient_dic:1,get_data_typ:1,get_decimal_precis:1,get_decoded_data:1,get_encoded_categorical_feature_index:1,get_features_rang:1,get_gradi:3,get_indexes_of_features_to_vari:1,get_inverse_ohe_min_max_normalized_data:1,get_mad:[1,15],get_minx_maxx:1,get_model_output:2,get_model_output_from_scor:2,get_num_output_nod:3,get_num_output_nodes2:3,get_ohe_min_max_normalized_data:1,get_output:3,get_quantiles_from_training_data:1,get_sampl:2,get_valid_feature_rang:[1,2],get_valid_mad:1,give:[11,13],given:[2,7,10,11,12,13,14,19],global:[0,2,7,18,19],global_feature_import:[2,10,11],global_import:2,goal:[7,13,18],govern:[7,10,11,12,13,16,19],gpu:[11,15,16],grad:[7,9,10,11,12,13,15,16,19],gradient:[0,2,7,11,19],gradientdesc:2,grant:[7,19],graph:[11,16],greater:[11,16],greedi:2,greedili:2,gt:[10,11,12,14,17],guid:2,h5py:[7,19],h_zhu:5,ha:[2,7,11,12,19],handl:15,handle_unknown:[9,10,11,13,14,17],happen:5,harder:[7,15,19],hardli:[7,19],have:[7,9,10,11,12,13,14,15,16,19],head:[9,11,12,13,14,15],healthcar:[7,19],help:[7,11,15,19],helper:[0,7,8,9,10,11,12,13,15,16,17,19],henc:[0,15,16],here:[7,12,13,15,19],high:[2,7,11,12,16,19],higher:[7,11,15,19],highlight:[7,11,19],hinge_loss:[2,9],histori:[7,19],hoc:2,hold:2,home:[9,12,17],host:[11,15,16],hot:[1,2,5,15],hotel:[7,19],hour:[7,10,11,12,15,19],hours_per_week:[7,9,10,11,12,13,15,16,19],hous:14,houseag:14,housing_data:14,how:[7,10,11,12,13,14,15,19],howev:[7,11,12,15,16,19],hs:[7,9,10,11,12,13,15,16,19],html:[5,9,14],http:[2,5,7,9,11,12,13,14,15,16,19],hyperparamet:2,hyperparamt:2,i:[2,9,11,15,16],ic:[5,9,11,12,13,15,16],idea:[7,13,19],ideal:[7,11,19],ident:14,ignor:[2,9,10,11,13,14,15,16,17],iloc:9,imp:[10,11],imp_r:10,implement:[0,2,3,7,9,11,13,16,19],impli:[12,15],implicit:12,imposs:[7,11,19],improv:[7,19],imput:17,in_featur:12,includ:[2,11,12],incom:[2,5,7,9,10,11,12,13,15,16,19],increas:[12,13,15],independ:[7,9,18],index:[1,7,9,12,17,19],indic:[2,3,5,11,16],individu:[7,11,15,19],industri:[10,11,12],infeas:12,infer:[1,2,12],infer_target_cfs_class:2,infer_target_cfs_rang:2,info:[11,14],inform:[0,1,7,14,16,19],init_near_query_inst:2,initi:[2,11,12,13,14,15,16],initialize_cf:2,initialize_transform_func:5,initil:[7,18],inp_siz:3,inproceed:[7,19],input:[0,1,2,3,7,10,11,12,14,15,19],input_inst:[2,3],input_shap:[7,19],input_tensor:3,inspect:11,instanc:[0,1,2,7,10,11,12,13,14,15,16,19],instanti:[11,12],instead:[1,9],instruct:[7,11,15,16,19],int64:14,intend:12,interactivesess:[7,19],interactiveshel:17,interest:[2,7,11,19],interfac:[0,1,2,3,11,16],intermedi:2,intern:[5,7,14,15,19],interpret:[2,7,10,19],interv:2,intial:2,introduct:[7,18],intuit:[10,11],invalid:17,invers:[2,15,16],inverse_dist:2,inverse_mad:2,inverse_transform:5,invok:[7,19],ipykernel_3518:17,ipython:17,iri:14,iris:14,is_cf_valid:2,issu:[7,13,19],iter:2,itr:2,its:[2,7,12,19],itself:13,json:[0,7,18],json_convert:0,json_str:[0,10],jsonschema:[7,19],judg:[7,19],jupyt:[7,19],just:[11,14],justic:[7,19],k1:2,k2:2,k:[1,2,7,9,13,19],kb:14,kd:[2,7,9,11,18,19],kd_query_inst:2,kdtree:[0,2,9,13,14,17],keep:11,kei:[2,11,12,15,16],kera:[3,7,19],keras_tensorflow_model:[0,8],kerastensorflowmodel:3,kernel:[11,15,16],kernel_regular:[7,19],kind:[7,11,19],know:[11,16],known:11,kw_arg:[0,3,5],kwarg:[0,2,6],l1:[7,19],l2_loss:2,label:[1,2,7,19],label_decod:2,label_decode_cf:2,label_encod:2,labelled_input:2,languag:[7,19],larg:2,larger:[2,11],last:[7,11,17,19],latest:[7,12,19],latitud:14,law:[7,19],layer:[7,19],lead:[7,11,19],learn:[2,5,7,9,12,13,14,15,16,18,19],learning_r:[2,5],leav:10,length:14,less:[2,11,13,15],let:15,level:[0,1,2,7,10,11,12,15,19],li:0,lib:[9,12,17],libcuda:[11,15,16],libcudart:[11,15,16],librari:[11,12,14,15,16],licens:[7,19],lie:14,like:[7,10,11,12,19],likelihood:11,lime:[7,11,19],limit:11,line:17,linear:[2,7,12,19],list:[0,1,2,7,12,19],live:[7,19],load:[5,7,17,18],load_adult_income_dataset:[5,7,9,10,11,12,13,15,19],load_custom_testing_dataset:[5,17],load_custom_testing_dataset_binari:5,load_custom_testing_dataset_multiclass:5,load_custom_testing_dataset_regress:5,load_ext:[9,10,11,12,13,14,15,16,17],load_iri:14,load_min_max_equal_dataset:5,load_model:[3,12],load_outcome_not_last_column_dataset:5,loaded_model:17,loan:[7,19],loc:[7,9,19],local:[0,2,7,12,18,19],local_feature_import:[2,10,11],local_import:[0,2,10,11],log:[11,15,16],log_loss:2,logic:11,logvar:6,longitud:14,loop:[0,9],loss:[2,7,11,19],loss_converge_maxit:[2,11],loss_diff:2,loss_diff_thr:2,low:[2,7,11,12,19],lower:[7,19],lr:12,lt:[9,10,11,12,13,14,17],m:[7,9,10,11,12,13,15,16,17,19],m_genet:9,m_hous:14,m_iri:14,m_kd:9,m_random:9,machin:[7,9,11,12,13,15,16,19],mad:[1,2,7,15,16,19],made:[7,11,19],mahajan:[7,19],mai:[7,11,15,19],main:2,make:[1,7,13,19],maker:[7,19],male:[7,9,10,11,12,13,15,16,19],mani:[2,11],manual:[7,16,19],margin:[5,12],marit:[10,11,12],marital_statu:[7,9,10,11,12,13,15,16,19],marital_status_divorc:12,marital_status_marri:12,marital_status_separ:12,marital_status_singl:12,marital_status_widow:12,marri:[7,9,10,11,12,13,15,16,19],master:[7,10,11,12,15,16,19],mate:2,matrix:2,max:[1,2,5,7,9,19],max_it:2,maximum:2,maxiter:2,mb:14,mead:2,mean:[6,7,11,12,15,19],measur:[7,10,15,19],median:[1,2,7,15,16,17,19],medinc:14,memori:[2,14],messag:[2,5],meta:[0,1,5,7,18],metadata:[0,7,10,16,19],method:[0,1,2,3,10,11,12,13,14,16,17],method_nam:13,metric:[2,7,11,19],microsoft:[7,19],might:12,min:[1,2,5,7,9,11,13,15,16,19],min_it:2,minim:11,minimum:2,misc_init:2,miss:17,ml:[0,1,2,3,5,18],ml_modelpath:[11,12,15,16,17],mnt:[12,17],mode:[3,7,19],model:[2,3,5,7,8,17,18,19],model_h:14,model_interfac:[0,2,8],model_iri:14,model_out:2,model_output:2,model_path:[0,3,7,11,12,15,16,17,19],model_scor:[2,3],model_select:[9,10,11,13,14,17],model_typ:[0,2,10,14],modelapprox:[7,18],modeltyp:0,modifi:9,modul:[7,8,9,11,12,13,14,15,17],monoton:[2,12],more:[0,2,7,10,12,14,15,18,19],most:[7,15,17,19],mothil:[7,19],mothilal2020dic:[7,19],move:2,msg:12,multi:[7,11,18,19],multiclass:[2,7,18],multipl:[7,11,14,15,19],name:[0,1,2,11,12,15,16],nearbi:11,nearest:2,necess:[7,10,11,19],necessari:[1,2,11],need:[1,7,10,11,12,19],neg:2,neither:11,nelder:2,network:[7,11,15,16,19],neural:[7,11,15,16,19],never:12,next:[7,18,19],nn:[6,7,12,19],non:[14,15],none:[0,1,2,3,5,10,12],nonetheless:16,nor:11,normal:[1,2,5,15,16],normal_likelihood:6,normalize_data:[1,7,19],note:[11,12,13,15,16],notebook:[9,11,12,13,14,16,19],notic:12,now:[7,9,10,11,12,13,14,15,19],np:9,num:[9,10,13,14,17],num_init:2,num_loop:9,num_output_nod:2,number:[0,1,2,9,11,15],numer:[1,9,10,11,13,14,17],numeric_tran:17,numeric_transform:[9,10,13,14],numpi:[7,9,15,19],nvidia:[11,15,16],o:10,obj:0,object:[0,2,3,5,7,11,12,13,15,16,17,18],observ:[13,15,16],obtain:11,occup:[7,9,10,11,12,13,15,16,19],occupation_blu:12,occupation_oth:12,occupation_profession:12,occupation_sal:12,occupation_servic:12,occupation_whit:12,odd:15,off:[2,7,18],offspr:2,often:[10,11],oh:1,ohe_min_max_transform:5,onc:[7,14,19],one:[0,1,2,5,7,11,15,19],one_hot_encode_data:1,one_hot_encoded_data:[7,19],oneapi:[11,15,16],onednn:[11,15,16],onehot:[9,10,11,13,14,17],onehotencod:[9,10,11,13,14,17],onli:[0,2,7,11,12,13,16,19],only_train:5,open:[7,11,15,16,17,19],opencod:[7,19],oper:[2,11,15,16],operation:11,opposit:[0,2,7,10,11,12,13,15,16,19],optim:[2,7,11,12,15,16,19],option:[2,7,11,18,19],oraclegencf:12,order:[2,15,16],ordereddict:16,org:[2,5,9,12,14],origin:[1,2,7,10,11,12,13,14,15,16,19],original_pr:2,other:[2,7,9,10,11,12,13,15,16,19],other_paramet:2,our:[7,11,12,13,15,16,19],out:[7,11,19],out_featur:12,outcom:[2,5,7,10,11,12,13,14,15,16,17,19],outcome_nam:[5,7,9,10,11,12,13,14,15,16,17,19],outlier:15,output:[0,2,3,7,11,12,13,18,19],output_typ:1,outsid:11,over:[2,7,15,18],overal:2,packag:[8,9,11,12,16,17,19],page:[7,19],panda:[2,7,9,14,17,19],paper:[2,7,11,12,15,16,19],param:[0,1],paramet:[0,2,3,5,7,11,13,14,15,16,19],parameter:11,part:2,particular:[7,10,11,15,16,19],pass:13,patch:12,path:2,path_or_buf:[7,19],pd:[14,17],pdf:2,penalti:12,peopl:[7,19],per:[2,7,10,11,12,15,19],perform:[2,11,15,16],perhap:13,permiss:[7,19],permit:[2,11,13],permitted_rang:[1,2,7,10,11,13,19],permitted_range_input:1,person:[7,11,15,19],perturb:[7,11,12,15,19],petal:14,phrase:[7,19],pi:9,pickl:17,pip:[7,19],pipelin:[9,10,11,13,14,17],plan:[7,19],plant:14,platform:[11,15,16],pleas:[7,13,16,19],point:[0,2,10,11,12,13],poor:[7,19],popul:14,popular:16,posit:2,possibl:[7,11,15,19],post:[2,7,19],posthoc_sparsity_algorithm:2,posthoc_sparsity_param:[0,2,10],potenti:[7,19],pp:17,pr:[7,19],practic:[1,7,11,19],pre:[2,7,11,12,19],pre_train:[2,12],precis:[1,2],precomput:2,pred_model:6,predict:[2,3,5,7,9,10,11,12,13,14,17,19],predict_fn:2,predict_fn_for_spars:2,predict_fn_scor:2,predicted_outcome_nam:2,prefer:2,prefix_sep:1,preliminari:[7,18],prepar:[1,5],prepare_df_for_ohe_encod:1,prepare_query_inst:1,preprocess:[5,9,10,11,13,14,17],preprocessor:[9,10,11,13,14,17],present:12,preserv:12,preval:[15,16],previous:13,price:14,print:[2,9,10,11,12,15],print_list:0,privaci:11,privat:[0,1,7,9,10,11,12,13,15,16,19],private_data_interfac:[0,8],privatedata:1,probabl:[2,3],probe:[7,19],problem:[2,7,19],problemat:[7,19],proc:[11,15,16],proceed:[7,19],process:[7,19],prodcu:12,produc:[2,11,12,13,16],prof:[7,10,11,12,13,15,16,19],profession:[7,9,10,11,12,13,15,16,19],profil:[7,15,19],project:[2,7,19],project_it:2,promot:13,properti:[0,7,19],prototyp:2,provid:[1,2,7,10,11,12,13,14,15,16,19],proxim:[7,10,11,18,19],proximity_weight:[2,7,15,19],pth:12,public_data_interfac:[0,8],publicdata:1,pull:[7,19],purpos:[9,11,12,15],py:[2,9,11,12,17],pydata:9,pypi:[7,19],pyt:[0,3,11,12,16],python3:[9,12,17],python:[7,9,12,16,17,19],pytorch:[0,2,3,7,9,12,13,16,18,19],pytorch_model:[0,8,12],pytorchmodel:[3,12],q:9,qualiti:2,quantil:1,queri:[2,7,9,10,11,12,14,15,16,18],query_inst:[1,2,7,9,10,11,12,13,15,16,19],query_instance_df_dummi:2,query_instance_norm:2,query_instance_orig:2,query_instances_h:14,query_instances_iri:14,question:[7,11,19],quick:[7,18],quickli:13,r:[7,19],race:[7,9,10,11,12,13,15,16,19],race_oth:12,race_whit:12,rais:[7,19],ramaravind:[7,19],random:[0,2,7,9,10,11,14,15,18,19],random_se:[2,13],random_st:[9,10,11,13,14],randomforestclassifi:[9,10,11,13,14,17],randomforestregressor:14,randominitcf:2,randomli:13,randomsampl:0,rang:[0,1,2,7,9,11,14,15,16,19],rangeindex:14,rank:11,rate:2,rather:[11,12],raw:1,raxi:6,rb:17,re:12,reach:15,read:2,real:2,reason:[11,15],rebuild:[11,15,16],receiv:[7,11,19],recent:[7,17,19],recommend:12,recours:[7,19],reduc:10,refer:[11,12],refin:11,reflect:[7,15,19],regr_hous:14,regress:[2,7,10,11,18],regressor:[0,3,7,11,14,17,19],regular:[7,19],reject:[7,19],rel:[7,11,15,16,19],relat:[1,2,11],relationship:2,releas:11,reload:2,relu:[7,12,19],remain:1,remov:[1,2],repeat:12,replic:11,repo:[7,19],repositori:[9,11,12,13,15,16],repres:10,reproduc:[2,15],request:[7,19],requir:[0,1,2,3,7,11,12,13,16,19],requires_grad_:12,research:[7,19],resourc:[7,18],respect:[15,16],rest:14,restrict:11,result:[0,2,11,12,16],resutl:15,retriev:12,return_mad:1,revers:11,revert:12,ride:15,right:[7,19],rigor:11,robust:15,round:[2,15],round_off_cf:2,round_to_precis:2,row:[2,11],row_index:9,rpub:5,run:[2,7,11,12,15,16,19],run_cod:17,runtim:9,s:[1,2,7,9,10,12,13,14,15,16,18,19],s_genet:9,s_kd:9,s_random:9,sale:[7,9,10,11,12,13,16,19],same:[1,2,7,11,12,13,16,19],sampl:[2,7,9,10,11,12,16,18,19],sample_architectur:[0,5,12],sample_latent_cod:6,sample_s:2,sampling_random_se:2,sampling_s:2,samplingstrategi:0,sav:17,save:[7,19],save_custom_vars_dataset_model:17,scale:[15,16],scaler:[9,10,13,14,17],scenario:11,schema:[0,8],school:[7,9,10,11,12,13,15,16,19],scienc:[7,19],scikit:[5,7,9,13,14,19],scipy_optim:2,scmgencf:12,score:[0,2,3,7,18,19],search:[2,7,11],sec:[9,11,13,15,16],second:[2,12],section:12,see:[2,7,9,11,12,14,15,19],seed:[2,13,15],select:[7,15,19],self:[7,9,10,11,12,13,15,16,17,19],sens:13,sensit:[7,11,19],sepal:14,separ:[7,10,11,12,13,16,19],sequenti:[7,12,19],seri:14,serial:[0,2,8,12],serialization_vers:0,serialize_explain:2,servic:[7,9,10,11,12,13,15,16,19],sess:[7,19],set:[0,1,2,7,9,10,11,12,13,14,15,16,19],set_eval_mod:3,set_random_se:15,set_se:15,set_verbos:[11,15,16],setosa:14,settingwithcopywarn:9,setup:[2,7,19],seven:15,shap:[7,11,19],shape:[7,12,19],share:[2,11,15,16],sharma:[7,19],should:[1,2,7,11,16,19],show:[7,9,10,11,12,13,15,16,19],show_only_chang:[0,10,11,12,13,14,15,16],shown:[0,11,13,16],sigmoid:[2,7,19],significantli:[10,11,16],similar:[2,7,12,19],similarli:11,simpl:[2,7,11,12,19],simpleimput:17,simplest:11,simpli:[7,11,19],simul:16,sinc:[11,12,13,15,16],singl:[1,2,7,9,10,11,12,13,14,15,16,19],singleton:3,site:[9,12,17],size:[0,2],sklearn:[0,3,5,7,9,10,11,12,13,14,17,19],slice:9,slightli:11,slower:11,snippet:11,so:[11,15,16],societ:[7,19],softmax:12,some:[5,7,9,10,11,12,13,15,16,19],soon:[9,12,13],sound:15,sourc:[0,1,2,3,5,6,7,12,19],sourcechangewarn:12,sourcetensor:12,space:11,spars:[11,13],sparsiti:[2,11,13,16],sparsity_weight:2,specif:[2,7,14,19],specifi:[0,2,7,11,12,15,19],split:[9,10,11,13,14],split_data:[7,19],stabl:[5,7,9,14,19],stakehold:[7,19],standard:15,standardscal:[9,10,13,14,17],start_tim:9,statu:[10,11,12],step:[7,9,10,11,13,14,15,17,19],still:[12,16],stop:2,stop_loop:2,stopping_threshold:2,store:[0,2],str:5,strategi:17,stratifi:[9,10,11,13,14],stream_executor:[11,15,16],string:[0,2],studi:[7,19],style:[11,16],subclass:[2,3],subject:[7,19],submethod:2,submit:[7,19],submodul:[7,8],subpackag:[7,8],success:2,suffici:[7,11,19],suggest:[7,19],sum:2,summar:[2,11],summari:[10,11],summary_import:[0,10,11],support:[1,2,9,11,12,13],supress:[11,15,16],syntax:17,syntaxerror:17,system:[5,7,19],systemexcept:5,tabl:[15,19],take:[2,15],taken:[9,11,13,15,16],tan:[7,19],target:[2,9,10,11,13,14],target_label:2,templat:[2,3],tend:11,tensor:12,tensorflow1:0,tensorflow2:[0,15],tensorflow:[0,2,3,7,9,12,13,15,16,18,19],tensorflow_optim:2,term:11,test:[1,2,3,7,9,10,11,13,14,16,19],test_data:10,test_dataset:11,test_instance_df:0,test_pr:2,test_siz:[9,10,11,12,13,14],tf1:[0,3,5,11,12,15,16],tf2:[0,3,11,12,16],tf:[2,7,11,15,16,19],than:[7,11,12,13,15,16,19],thei:[1,7,11,13,19],them:[1,11,15,16],therefor:[7,11,19],thi:[1,2,5,7,9,10,11,12,13,14,15,16,19],third:[2,12],those:[7,10,11,16,19],three:[7,9,11,13,15,19],thresh:2,threshold:2,through:[2,7,11,15,16,19],thu:[7,15,19],tie_random:2,time:[2,9,10,11,12,13,15,16],timeit:9,titan:[7,19],titl:[7,19],tmp:17,to_csv:[7,19],to_json:[0,5,10],todo:[1,2],tolist:[9,14],too:[7,12,19],tool:12,top:[7,19],torch:[6,12],total:[2,9,10,11,12,13,14,15,16],total_cf:[2,7,9,10,11,12,13,14,15,16,19],toward:[2,7,11,12,19],toy_dataset:14,tqdm:[7,19],traceback:17,trade:[7,18],train:[0,1,2,3,7,10,12,14,15,18,19],train_dataset:11,train_test_split:[9,10,11,13,14,17],tran:17,transform:[1,2,3,5,9,10,11,12,13,14,15,17],transform_data:3,transformed_data:1,translat:11,transpar:[7,19],tree:[2,7,9,11,18,19],trust:[7,19],truth:[7,19],tunabl:[2,7,15,19],two:[2,7,11,12,16,19],txt:[7,19],type:[0,1,10,11,12,14,16],typic:[7,19],uci:[5,9,11,12,13,15,16],unari:[2,12],uncov:[7,19],under:12,understand:[7,11,19],unifi:11,uniform:9,uniqu:9,unit:[7,15,19],unknown:[7,10,11,12,13,15,16,19],unlik:12,until:2,up:[11,15,16],updat:2,update_hyperparamet:2,us:[0,1,2,9,13,14,15,16,18],usag:14,user:[1,2,5,7,12,15,17,19],user_global_n:17,user_guid:9,user_n:17,userconfigvalidationexcept:5,userwarn:12,util:[0,7,8,9,10,11,12,13,15,16,17,19],v1:[11,15,16],vae:[2,7,11,18,19],vae_model:[0,5,12],valid:[1,5,7,11,19],validation_split:[7,19],validity_reg:[5,12],valu:[1,2,3,7,9,10,11,12,14,15,16,19],vari:[2,7,11,15,19],variabl:[2,11,12,15,16],variat:[7,12,19],vary_valid:2,vector:2,verbos:[2,7,9,13,19],veri:15,versa:[1,12],versicolour:14,version:[0,7,10,11,15,16,19],versu:9,vice:[1,12],vidhya:[7,19],view:9,virginica:14,visit:[7,19],visual:[0,2,7,11,12,15,16,19],visualize_as_datafram:[0,7,10,11,12,13,14,15,16,19],visualize_as_list:0,vpy38:[9,12,17],vs:[10,11,12],w:[11,15,16],wa:[7,11,16,19],wai:[7,11,12,15,19],want:[11,13,16],warn:[1,11,12,15,16],wb:17,we:[2,7,9,10,11,12,13,14,15,16,19],week:[7,10,11,12,15,19],weigh:11,weight:[2,7,12,16,18,19],welcom:[7,19],well:[7,19],what:[7,15,18,19],when:[1,2,7,11,15,16,19],where:[1,2,11,12,15,16],whether:[2,7,11,12,19],which:[2,7,11,12,16,19],white:[7,9,10,11,12,13,15,16,19],who:[7,19],whose:[0,11,12],why:[7,15,19],wide:[7,19],widow:[7,10,11,12,16,19],width:14,wish:13,within:[7,11,13,19],without:[7,11,12,18],wm1:[5,12],wm2:[5,12],wm3:[5,12],word:[7,19],work:[1,7,9,10,12,13,15,18,19],workclass:[7,9,10,11,12,13,15,16,19],workclass_govern:12,workclass_oth:12,workclass_priv:12,workclass_self:12,world:[7,19],worsen:13,would:[7,11,12,15,19],x1:2,x:[2,6,7,11,12,16,19],x_hat:2,x_hat_unnorm:2,x_i:11,x_test:[9,10,11,13,14],x_train:[7,9,10,11,13,14,19],y:[2,7,11,19],y_test:[9,10,11,13,14],y_train:[7,9,10,11,13,14,19],year:[7,11,19],yet:[7,19],yield:10,yloss_typ:[2,9],you:[7,9,11,12,13,14,15,16,19],your:[7,11,15,16,19],z840:[11,15,16],z:[2,6]},titles:["dice_ml package","dice_ml.data_interfaces package","dice_ml.explainer_interfaces package","dice_ml.model_interfaces package","dice_ml.schema package","dice_ml.utils package","dice_ml.utils.sample_architecture package","Diverse Counterfactual Explanations (DiCE) for ML","dice_ml","Benchmarking different CF explanation methods","Estimating local and global feature importance scores using DiCE","Quick introduction to generating counterfactual explanations using DiCE","Generate feasible counterfactual explanations using a VAE","Generating counterfactual explanations with any ML model","Generating counterfactuals for multi-class classification and regression models","Advanced options to customize Counterfactual Explanations","Generating Counterfactual Explanations without access to training data","&lt;no title&gt;","&lt;no title&gt;","Diverse Counterfactual Explanations (DiCE) for ML"],titleterms:{"1":[13,15],"2":[13,15],"3":[13,15],"case":[7,19],"class":14,"import":[10,11],The:[7,19],access:16,ad:12,adult:11,advanc:15,algorithm:13,ani:13,attribut:11,base_data_interfac:1,base_model:3,benchmark:9,between:15,cf:9,chang:15,choos:13,cite:[7,19],classif:14,constant:0,constraint:12,content:[0,1,2,3,4,5,6],contribut:[7,19],convert:10,counterfactu:[7,9,10,11,12,13,14,15,16,19],counterfactual_explan:0,custom:[13,15],data:[0,10,16],data_interfac:1,dataset:[9,11,12,13,15],deep:11,defin:16,dice:[0,7,10,11,19],dice_genet:2,dice_kd:2,dice_ml:[0,1,2,3,4,5,6,8],dice_pytorch:2,dice_random:2,dice_tensorflow1:2,dice_tensorflow2:2,differ:9,divers:[7,13,15,16,19],diverse_counterfactu:0,estim:10,exampl:11,except:5,explain:[11,12],explainer_bas:2,explainer_interfac:2,explan:[7,9,11,12,13,15,16,19],feasibl:[7,12,19],feasible_base_va:2,feasible_model_approx:2,feasiblemodelapprox:12,featur:[10,11,13,15],gener:[7,9,11,12,13,14,15,16,19],genet:13,get:[7,19],global:[10,11],goal:15,helper:5,independ:13,indic:7,initi:9,initil:12,instal:[7,19],introduct:11,json:10,kd:13,keras_tensorflow_model:3,learn:11,load:[9,10,11,12,13,15,16],local:[10,11],meta:16,method:[7,9,19],ml:[7,9,10,11,12,13,15,16,19],model:[0,9,10,11,12,13,14,15,16],model_interfac:3,modelapprox:12,modul:[0,1,2,3,4,5,6],more:11,multi:14,multiclass:14,next:11,notebook:[7,18],object:10,off:15,option:15,output:10,over:11,packag:[0,1,2,3,4,5,6,7],preliminari:[10,11],private_data_interfac:1,promis:[7,19],proxim:15,public_data_interfac:1,pytorch:11,pytorch_model:3,queri:13,quick:11,random:13,rang:13,regress:14,resourc:11,roadmap:[7,19],s:11,sampl:13,sample_architectur:6,schema:4,score:[10,11],select:13,serial:5,start:[7,19],submodul:[0,1,2,3,5,6],subpackag:[0,5],support:[7,19],tabl:7,tensorflow:11,trade:15,train:[9,11,13,16],tree:13,us:[7,10,11,12,19],util:[5,6],vae:12,vae_model:6,vari:13,weight:15,what:11,without:16,work:11}})
\ No newline at end of file
+Search.setIndex({"docnames": ["dice_ml", "dice_ml.data_interfaces", "dice_ml.explainer_interfaces", "dice_ml.model_interfaces", "dice_ml.schema", "dice_ml.utils", "dice_ml.utils.sample_architecture", "index", "modules", "notebooks/Benchmarking_different_CF_explanation_methods", "notebooks/DiCE_feature_importances", "notebooks/DiCE_getting_started", "notebooks/DiCE_getting_started_feasible", "notebooks/DiCE_model_agnostic_CFs", "notebooks/DiCE_multiclass_classification_and_regression", "notebooks/DiCE_with_advanced_options", "notebooks/DiCE_with_private_data", "notebooks/nb_index", "readme"], "filenames": ["dice_ml.rst", "dice_ml.data_interfaces.rst", "dice_ml.explainer_interfaces.rst", "dice_ml.model_interfaces.rst", "dice_ml.schema.rst", "dice_ml.utils.rst", "dice_ml.utils.sample_architecture.rst", "index.rst", "modules.rst", "notebooks/Benchmarking_different_CF_explanation_methods.ipynb", "notebooks/DiCE_feature_importances.ipynb", "notebooks/DiCE_getting_started.ipynb", "notebooks/DiCE_getting_started_feasible.ipynb", "notebooks/DiCE_model_agnostic_CFs.ipynb", "notebooks/DiCE_multiclass_classification_and_regression.ipynb", "notebooks/DiCE_with_advanced_options.ipynb", "notebooks/DiCE_with_private_data.ipynb", "notebooks/nb_index.rst", "readme.rst"], "titles": ["dice_ml package", "dice_ml.data_interfaces package", "dice_ml.explainer_interfaces package", "dice_ml.model_interfaces package", "dice_ml.schema package", "dice_ml.utils package", "dice_ml.utils.sample_architecture package", "Diverse Counterfactual Explanations (DiCE) for ML", "dice_ml", "Benchmarking different CF explanation methods", "Estimating local and global feature importance scores using DiCE", "Quick introduction to generating counterfactual explanations using DiCE", "Generate feasible counterfactual explanations using a VAE", "Generating counterfactual explanations with any ML model", "Generating counterfactuals for multi-class classification and regression models", "Advanced options to customize Counterfactual Explanations", "Generating counterfactual explanations without access to training data", "&lt;no title&gt;", "Diverse Counterfactual Explanations (DiCE) for ML"], "terms": {"data_interfac": [0, 2, 5, 8, 10, 15, 16], "base_data_interfac": [0, 8, 15], "private_data_interfac": [0, 8, 16], "privatedata": [0, 1], "create_ohe_param": [0, 1], "de_normalize_data": [0, 1], "fit_label_encod": [0, 1], "from_dummi": [0, 1], "from_label": [0, 1], "get_all_dummy_colnam": [0, 1], "get_data_params_for_gradient_dic": [0, 1], "get_decimal_precis": [0, 1], "get_decoded_data": [0, 1], "get_encoded_categorical_feature_index": [0, 1], "get_features_rang": [0, 1], "get_indexes_of_features_to_vari": [0, 1], "get_inverse_ohe_min_max_normalized_data": [0, 1], "get_mad": [0, 1, 15], "get_minx_maxx": [0, 1], "get_ohe_min_max_normalized_data": [0, 1], "get_valid_feature_rang": [0, 1, 2], "get_valid_mad": [0, 1], "normalize_data": [0, 1, 7, 18], "one_hot_encode_data": [0, 1], "prepare_df_for_ohe_encod": [0, 1], "prepare_query_inst": [0, 1], "public_data_interfac": [0, 8], "publicdata": [0, 1], "get_data_typ": [0, 1], "get_quantiles_from_training_data": [0, 1], "explainer_interfac": [0, 8, 15], "dice_kd": [0, 8, 9], "dicekd": [0, 2, 13], "do_sparsity_check": [0, 2], "duplic": [0, 2], "find_counterfactu": [0, 2], "predict_fn": [0, 2], "vary_valid": [0, 2], "dice_genet": [0, 8], "dicegenet": [0, 2, 13], "compute_loss": [0, 2], "compute_proximity_loss": [0, 2], "compute_sparsity_loss": [0, 2], "compute_yloss": [0, 2], "do_kd_init": [0, 2], "do_cf_initi": [0, 2], "do_loss_initi": [0, 2], "do_param_initi": [0, 2], "do_random_init": [0, 2], "label_decod": [0, 2], "label_decode_cf": [0, 2], "label_encod": [0, 2], "mate": [0, 2], "predict_fn_scor": [0, 2], "update_hyperparamet": [0, 2], "dice_pytorch": [0, 8], "dicepytorch": [0, 2], "compute_dist": [0, 2], "compute_diversity_loss": [0, 2], "compute_regularization_loss": [0, 2], "do_optimizer_initi": [0, 2], "dpp_style": [0, 2], "get_model_output": [0, 2], "initialize_cf": [0, 2], "predict_fn_for_spars": [0, 2], "round_off_cf": [0, 2], "stop_loop": [0, 2], "dice_random": [0, 8], "dicerandom": [0, 2], "get_continuous_sampl": [0, 2], "get_sampl": [0, 2], "dice_tensorflow1": [0, 8], "dicetensorflow1": [0, 2], "generate_counterfactu": [0, 2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "scipy_optim": [0, 2], "tensorflow_optim": [0, 2], "dice_tensorflow2": [0, 8], "dicetensorflow2": [0, 2], "explainer_bas": [0, 8, 15], "explainerbas": [0, 2, 15], "build_kd_tre": [0, 2], "check_permitted_rang": [0, 2], "check_query_instance_valid": [0, 2], "decide_cf_valid": [0, 2], "deserialize_explain": [0, 2], "do_binary_search": [0, 2], "do_linear_search": [0, 2], "do_posthoc_sparsity_enhanc": [0, 2], "feature_import": [0, 2], "get_model_output_from_scor": [0, 2], "global_feature_import": [0, 2, 10, 11], "infer_target_cfs_class": [0, 2], "infer_target_cfs_rang": [0, 2], "is_cf_valid": [0, 2], "local_feature_import": [0, 2, 10, 11], "misc_init": [0, 2], "round_to_precis": [0, 2], "serialize_explain": [0, 2], "setup": [0, 2, 7, 18], "sigmoid": [0, 2, 7, 18], "feasible_base_va": [0, 8, 12], "feasiblebaseva": [0, 2, 12], "train": [0, 1, 2, 3, 5, 6, 7, 10, 12, 14, 15, 17, 18], "feasible_model_approx": [0, 8, 12], "feasiblemodelapprox": [0, 2, 7, 17], "model_interfac": [0, 2, 8], "base_model": [0, 8], "basemodel": [0, 3], "get_gradi": [0, 3], "get_num_output_nod": [0, 3], "get_num_output_nodes2": [0, 3], "get_output": [0, 3], "load_model": [0, 3, 12], "keras_tensorflow_model": [0, 8], "kerastensorflowmodel": [0, 3], "pytorch_model": [0, 8, 12], "pytorchmodel": [0, 3, 12], "set_eval_mod": [0, 3], "schema": [0, 8], "util": [0, 7, 8, 9, 10, 11, 12, 13, 15, 16, 18], "sample_architectur": [0, 5], "vae_model": [0, 5], "except": [0, 8, 11, 12], "systemexcept": [0, 5], "userconfigvalidationexcept": [0, 5], "helper": [0, 7, 8, 9, 10, 11, 12, 13, 15, 16, 18], "datatransfom": [0, 5], "feed_data_param": [0, 5], "initialize_transform_func": [0, 5], "inverse_transform": [0, 5], "transform": [0, 1, 2, 3, 5, 9, 10, 11, 12, 13, 14, 15], "get_adult_data_info": [0, 5, 10, 11, 12], "get_adult_income_modelpath": [0, 5, 7, 11, 12, 15, 16, 18], "get_base_gen_cf_initi": [0, 5], "get_custom_dataset_modelpath_pipelin": [0, 5], "get_custom_dataset_modelpath_pipeline_binari": [0, 5], "get_custom_dataset_modelpath_pipeline_multiclass": [0, 5], "get_custom_dataset_modelpath_pipeline_regress": [0, 5], "get_custom_vars_dataset_modelpath_pipelin": [0, 5], "inverse_ohe_min_max_transform": [0, 5], "load_adult_income_dataset": [0, 5, 7, 9, 10, 11, 12, 13, 15, 18], "load_custom_testing_dataset": [0, 5], "load_custom_testing_dataset_binari": [0, 5], "load_custom_testing_dataset_multiclass": [0, 5], "load_custom_testing_dataset_regress": [0, 5], "load_min_max_equal_dataset": [0, 5], "load_outcome_not_last_column_dataset": [0, 5], "ohe_min_max_transform": [0, 5], "save_adult_income_model": [0, 5], "neuralnetwork": [0, 8], "ffnetwork": [0, 5], "forward": [0, 5, 6], "serial": [0, 2, 8, 12], "dummydatainterfac": [0, 5], "to_json": [0, 5, 8, 10], "ml": [0, 1, 2, 3, 5, 16, 17], "class": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 17, 18], "backendtyp": [0, 8], "sourc": [0, 1, 2, 3, 5, 6, 7, 12, 18], "base": [0, 1, 2, 3, 5, 6, 7, 9, 11, 12, 13, 15, 16, 18], "object": [0, 2, 3, 5, 7, 9, 11, 12, 13, 15, 16, 17], "all": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 14, 15, 16, 18], "sklearn": [0, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18], "tf1": [0, 3, 5, 11, 12, 15, 16], "tf2": [0, 3, 11, 12, 16], "pyt": [0, 3, 11, 12, 16], "pytorch": [0, 2, 3, 7, 8, 9, 12, 13, 16, 17, 18], "tensorflow1": [0, 8], "tensorflow2": [0, 8, 15], "modeltyp": [0, 8], "classifi": [0, 2, 3, 7, 8, 9, 10, 11, 13, 14, 18], "regressor": [0, 3, 7, 8, 11, 14, 18], "samplingstrategi": [0, 8], "genet": [0, 2, 7, 8, 9, 11, 14, 16, 17, 18], "gradient": [0, 2, 7, 8, 11, 16, 18], "kdtree": [0, 2, 8, 9, 13, 14, 16], "random": [0, 2, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "counterfactualexplan": [0, 2, 8], "cf_examples_list": [0, 2, 7, 8, 10, 18], "local_import": [0, 2, 8, 10, 11], "none": [0, 1, 2, 3, 5, 10, 12], "summary_import": [0, 8, 10, 11], "version": [0, 7, 10, 11, 12, 15, 16, 18], "A": [0, 1, 2, 5, 7, 11, 12, 15, 18], "store": [0, 2], "counterfactu": [0, 2, 17], "exampl": [0, 2, 7, 10, 12, 13, 16, 17, 18], "one": [0, 1, 2, 5, 6, 7, 11, 15, 18], "more": [0, 2, 7, 10, 12, 14, 15, 16, 17, 18], "input": [0, 1, 2, 3, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "featur": [0, 1, 2, 7, 9, 12, 14, 16, 17, 18], "import": [0, 2, 7, 9, 12, 13, 14, 15, 16, 17, 18], "score": [0, 2, 3, 7, 17, 18], "paramet": [0, 2, 3, 5, 7, 11, 13, 14, 15, 16, 18], "list": [0, 1, 2, 7, 12, 18], "counterfactualexampl": [0, 2, 8], "instanc": [0, 1, 2, 6, 7, 10, 11, 12, 14, 15, 16, 18], "estim": [0, 2, 7, 11, 16, 17, 18], "local": [0, 2, 7, 12, 17, 18], "The": [0, 2, 11, 12, 13, 14, 15, 16], "size": [0, 2], "i": [0, 1, 2, 3, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "number": [0, 1, 2, 9, 11, 15], "each": [0, 2, 7, 9, 10, 11, 12, 13, 16, 18], "contain": [0, 1, 2, 3, 12, 14], "global": [0, 2, 7, 17, 18], "set": [0, 1, 2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "properti": [0, 7, 18], "static": [0, 2], "from_json": [0, 8, 10], "json_str": [0, 10], "deseri": 0, "json": [0, 7, 17], "string": [0, 2], "metadata": [0, 7, 8, 10, 16, 18], "explan": [0, 2, 17], "visualize_as_datafram": [0, 7, 8, 10, 11, 12, 13, 14, 15, 16, 18], "display_sparse_df": 0, "true": [0, 1, 2, 3, 5, 9, 10, 11, 12, 13, 14, 15, 16], "show_only_chang": [0, 10, 11, 12, 13, 14, 15, 16], "fals": [0, 1, 2, 3, 7, 9, 11, 12, 13, 16, 18], "visualize_as_list": [0, 8], "point": [0, 2, 10, 11, 12, 13, 15, 16], "differ": [0, 2, 3, 7, 10, 11, 12, 13, 14, 15, 16, 18], "implement": [0, 2, 3, 7, 9, 11, 13, 16, 18], "requir": [0, 1, 2, 3, 7, 11, 12, 16, 18], "onli": [0, 2, 7, 11, 12, 13, 16, 18], "few": [0, 15], "about": [0, 1, 12, 16], "rang": [0, 1, 2, 7, 9, 11, 14, 15, 16, 18], "continu": [0, 1, 2, 7, 11, 12, 13, 15, 16, 18], "level": [0, 1, 2, 7, 10, 11, 12, 15, 18], "categor": [0, 1, 2, 7, 9, 10, 11, 13, 14, 15, 16, 18], "henc": [0, 15, 16], "can": [0, 2, 7, 9, 10, 11, 12, 13, 14, 16, 18], "us": [0, 2, 9, 13, 14, 15, 16, 17], "privat": [0, 1, 7, 10, 11, 12, 15, 16, 18], "whose": [0, 11, 12], "meta": [0, 1, 5, 7, 17], "ar": [0, 1, 2, 3, 7, 11, 12, 13, 15, 16, 18], "avail": [0, 7, 16, 18], "name": [0, 1, 2, 9, 11, 12, 13, 15, 16], "specifi": [0, 2, 7, 11, 12, 15, 16, 18], "appropri": [0, 7, 11, 15, 16, 18], "param": [0, 1], "_basedata": [0, 1, 15], "inform": [0, 1, 7, 14, 16, 18], "decide_implementation_typ": [0, 8], "decid": [0, 2, 7, 8, 15, 18], "public": [0, 1], "To": [0, 7, 11, 15, 16, 18], "add": [0, 2, 7, 11, 18], "new": [0, 2, 7, 10, 11, 12, 14, 16, 18], "return": [0, 1, 2, 3, 5, 9, 11, 12, 13], "an": [0, 1, 2, 3, 5, 7, 10, 11, 12, 13, 15, 16, 18], "elif": 0, "loop": [0, 2, 9], "shown": [0, 11, 13, 16], "below": [0, 10, 11, 12, 13, 14, 15, 16], "method": [0, 1, 2, 3, 10, 11, 12, 13, 14, 16], "framework": [0, 2, 3, 12, 13, 15], "tensorflow": [0, 2, 3, 7, 9, 12, 13, 15, 16, 17, 18], "randomsampl": 0, "kwarg": [0, 2, 5, 15], "interfac": [0, 1, 2, 3, 11, 16], "type": [0, 1, 10, 11, 12, 14, 16], "final_cfs_df": [0, 7, 18], "test_instance_df": 0, "final_cfs_df_spars": 0, "posthoc_sparsity_param": [0, 2, 10, 15], "0": [0, 1, 2, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "desired_rang": [0, 2, 10, 14, 15], "desired_class": [0, 2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "opposit": [0, 2, 7, 10, 11, 12, 13, 15, 16, 18], "model_typ": [0, 2, 10, 14], "visual": [0, 2, 7, 11, 12, 15, 16, 18], "result": [0, 2, 11, 12, 15, 16], "display_df": [0, 8], "df": [0, 1], "cf_example_json_str": 0, "print_list": [0, 8], "li": 0, "serialization_vers": 0, "json_convert": [0, 8], "obj": 0, "function": [0, 2, 5, 6, 7, 9, 10, 11, 12, 13, 15, 16, 18], "convert": [0, 7, 9, 11, 12, 13, 17], "access": [0, 7, 11, 12, 17, 18], "output": [0, 2, 3, 7, 11, 12, 13, 17, 18], "model_path": [0, 3, 7, 11, 12, 15, 16, 18], "backend": [0, 3, 5, 9, 10, 11, 12, 13, 14, 15, 16], "func": [0, 3, 5, 11, 12, 16], "kw_arg": [0, 3, 5], "data": [1, 2, 3, 5, 7, 8, 9, 11, 12, 13, 14, 15, 17, 18], "dice": [1, 8, 9, 12, 13, 14, 15, 16, 17], "one_hot_encoded_data": [1, 7, 18], "de": 1, "normal": [1, 2, 5, 15, 16], "from": [1, 2, 5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "1": [1, 2, 6, 7, 9, 10, 11, 12, 14, 16, 17, 18], "origin": [1, 2, 7, 10, 11, 12, 14, 15, 16, 18], "prefix_sep": 1, "_": [1, 7, 9, 18], "get": [1, 2, 5, 12, 15], "dummi": 1, "encod": [1, 2, 5, 6, 9, 11, 12, 13, 15], "k": [1, 2, 7, 9, 13, 18], "label": [1, 2, 7, 18], "back": [1, 2], "valu": [1, 2, 3, 7, 9, 10, 11, 12, 14, 15, 16, 18], "relat": [1, 2, 11], "output_typ": 1, "precis": [1, 2], "hot": [1, 2, 5, 11, 15], "column": [1, 7, 9, 10, 11, 12, 13, 14, 15, 18], "index": [1, 7, 9, 16, 18], "after": 1, "permitted_range_input": 1, "features_dict": 1, "features_to_vari": [1, 2, 7, 10, 11, 13, 15, 18], "transformed_data": 1, "min": [1, 2, 5, 7, 9, 11, 16, 18], "max": [1, 2, 5, 7, 9, 11, 16, 18], "raw": 1, "user": [1, 2, 5, 7, 9, 12, 13, 15, 16, 18], "fed": [1, 2, 5], "format": [1, 2, 11, 12], "should": [1, 2, 6, 7, 11, 16, 18], "datafram": [1, 2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "arrai": [1, 3], "comput": [1, 2, 6, 7, 11, 15, 16, 18], "median": [1, 2, 7, 15, 16, 18], "absolut": [1, 2, 7, 15, 16, 18], "deviat": [1, 7, 15, 16, 18], "form": [1, 11, 12, 15, 16], "query_inst": [1, 2, 7, 9, 10, 11, 12, 13, 15, 16, 18], "dict": 1, "feature_range_input": 1, "assum": 1, "alreadi": 1, "numer": [1, 9, 10, 11, 13, 14, 15, 16], "remain": 1, "same": [1, 2, 7, 11, 12, 13, 16, 18], "todo": [1, 2], "need": [1, 6, 7, 10, 11, 12, 16, 18], "work": [1, 7, 9, 10, 12, 13, 15, 17, 18], "adher": 1, "support": [1, 2, 9, 11, 12, 13, 16], "permitted_rang": [1, 2, 7, 10, 11, 13, 15, 18], "both": [1, 7, 9, 10, 12, 13, 14, 15, 18], "discret": [1, 11, 12], "when": [1, 2, 7, 11, 15, 16, 18], "provid": [1, 2, 7, 10, 11, 12, 13, 14, 15, 16, 18], "_generate_counterfactu": [1, 15], "display_warn": 1, "return_mad": 1, "If": [1, 2, 7, 11, 13, 16, 18], "thei": [1, 7, 11, 13, 18], "practic": [1, 7, 11, 18], "instead": [1, 6, 16], "make": [1, 7, 13, 18], "them": [1, 6, 11, 15, 16], "fall": [1, 15], "One": 1, "creat": [1, 7, 9, 10, 11, 13, 14, 15, 18], "do": [1, 7, 11, 13, 15, 16, 18], "oh": [1, 11, 16], "singl": [1, 2, 7, 10, 11, 12, 14, 15, 16, 18], "prepar": [1, 5, 9, 12, 13], "defin": [1, 2, 5, 6, 7, 9, 11, 12, 13, 15, 17], "test": [1, 2, 3, 7, 9, 10, 11, 13, 14, 16, 18], "": [1, 2, 7, 10, 12, 13, 14, 15, 16, 17, 18], "between": [1, 2, 7, 11, 16, 17, 18], "explain": [1, 2, 7, 17, 18], "thi": [1, 2, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "vice": [1, 12], "versa": [1, 12], "col": 1, "infer": [1, 2, 12], "quantil": 1, "05": [1, 2], "gener": [2, 5, 10, 17], "kd": [2, 7, 9, 11, 17, 18], "tree": [2, 7, 9, 11, 17, 18], "code": [2, 7, 9, 11, 12, 13, 14, 15, 16, 18], "similar": [2, 7, 12, 18], "interpret": [2, 7, 10, 18], "guid": 2, "prototyp": 2, "http": [2, 5, 7, 9, 11, 12, 13, 14, 15, 16, 18], "arxiv": [2, 12], "org": [2, 5, 12, 14, 16], "pdf": 2, "1907": 2, "02584": 2, "cf": [2, 7, 11, 12, 13, 14, 18], "sparsity_weight": [2, 15], "final_indic": 2, "data_df_copi": 2, "query_instance_orig": 2, "total_cf": [2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "stopping_threshold": [2, 15], "posthoc_sparsity_algorithm": [2, 15], "verbos": [2, 7, 9, 13, 15, 18], "limit_steps_l": 2, "find": [2, 7, 11, 13, 16, 18], "queri": [2, 7, 9, 10, 11, 12, 14, 15, 16, 17], "d": [2, 6, 7, 9, 10, 11, 12, 13, 15, 16, 18], "nearest": 2, "desir": [2, 7, 11, 13, 14, 18], "dataset": [2, 5, 7, 10, 14, 16, 17, 18], "input_inst": [2, 3], "predict": [2, 3, 5, 7, 9, 10, 11, 12, 13, 14, 18], "kd_query_inst": 2, "ensur": [2, 7, 13, 18], "we": [2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "vari": [2, 7, 11, 15, 18], "divers": [2, 9, 10, 11, 14, 17], "algorithm": [2, 7, 9, 11, 14, 16, 17, 18], "geco": 2, "qualiti": 2, "real": 2, "time": [2, 9, 10, 11, 12, 15, 16], "2101": 2, "01292": 2, "overal": 2, "loss": [2, 7, 9, 11, 12, 13, 18], "x_hat_unnorm": 2, "query_instance_norm": 2, "weight": [2, 7, 12, 16, 17, 18], "distanc": [2, 7, 11, 15, 16, 18], "two": [2, 7, 11, 12, 16, 18], "vector": 2, "first": [2, 10, 11, 12, 16], "part": 2, "y": [2, 7, 11, 18], "initi": [2, 11, 12, 13, 14, 15, 16], "query_instance_df_dummi": 2, "intial": 2, "other": [2, 7, 10, 11, 12, 13, 15, 16, 18], "variabl": [2, 11, 12, 15, 16], "yloss_typ": [2, 9], "diversity_loss_typ": 2, "feature_weight": [2, 7, 15, 16, 18], "main": 2, "proximity_weight": [2, 7, 15, 18], "diversity_weight": [2, 7, 15, 18], "categorical_penalti": [2, 15], "num_init": 2, "maxiter": 2, "thresh": 2, "through": [2, 7, 11, 15, 16, 18], "labelled_input": 2, "cfs_arr": 2, "k1": 2, "k2": 2, "perform": [2, 6, 11, 15, 16], "produc": [2, 11, 12, 13, 16], "offspr": 2, "actual": [2, 7, 18], "updat": 2, "hyperparamet": 2, "x_hat": 2, "x1": [2, 11, 15, 16], "third": [2, 12], "second": [2, 12], "linear": [2, 7, 12, 18], "equal": [2, 15, 16], "constraint": [2, 7, 11, 17, 18], "sum": 2, "optim": [2, 7, 11, 12, 15, 16, 18], "learning_r": [2, 5], "submethod": 2, "dpp": 2, "matrix": 2, "min_it": 2, "max_it": 2, "project_it": 2, "loss_diff_thr": 2, "loss_converge_maxit": [2, 11], "init_near_query_inst": 2, "tie_random": 2, "descent": 2, "transform_data": [2, 3], "out_tensor": [2, 3], "probabl": [2, 3], "model": [2, 3, 5, 7, 8, 17, 18], "sparsiti": [2, 11, 13, 16], "correct": [2, 16], "assign": [2, 7, 15, 18], "intermedi": 2, "project": [2, 7, 18], "itr": 2, "loss_diff": 2, "determin": [2, 3, 7, 12, 18], "stop": 2, "condit": [2, 11], "sampl": [2, 7, 9, 10, 11, 12, 16, 17, 18], "simpl": [2, 7, 11, 12, 18], "low": [2, 7, 11, 12, 18], "high": [2, 7, 11, 12, 16, 18], "1000": 2, "seed": [2, 13, 15], "fixed_features_valu": 2, "feature_rang": 2, "sampling_random_se": 2, "sampling_s": 2, "x": [2, 5, 6, 7, 11, 16, 18], "tf": [2, 7, 15, 16, 18], "hinge_loss": [2, 9], "inverse_dist": 2, "inverse_mad": 2, "500": [2, 12], "5000": [2, 10], "1e": [2, 12], "5": [2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "diversecf": 2, "adam": [2, 7, 18], "10000": 2, "interest": [2, 7, 11, 18], "dictionari": [2, 12, 15, 16], "row": [2, 11], "total": [2, 9, 10, 11, 12, 14, 15, 16], "take": [2, 6, 15], "default": [2, 7, 11, 12, 13, 15, 16, 18], "outcom": [2, 5, 7, 10, 11, 12, 14, 16, 18], "binari": [2, 7, 11, 12, 15, 16, 18], "classif": [2, 7, 11, 17], "posit": 2, "float": [2, 11, 15, 16], "larger": [2, 11], "close": [2, 9, 11, 12, 13], "either": [2, 11], "randominitcf": 2, "kei": [2, 12, 15, 16], "permit": [2, 11, 13], "metric": [2, 7, 11, 18], "l2_loss": 2, "log_loss": 2, "avg_dist": 2, "correspond": 2, "option": [2, 7, 11, 17, 18], "where": [2, 11, 12, 15, 16], "invers": [2, 15, 16], "devid": 2, "mad": [2, 7, 15, 16, 18], "current": [2, 9, 11, 13], "learn": [2, 5, 7, 9, 12, 13, 14, 15, 17, 18], "rate": 2, "iter": 2, "run": [2, 6, 7, 11, 12, 15, 16, 18], "interv": 2, "mani": [2, 11], "minimum": 2, "success": 2, "check": [2, 7, 9, 11, 18], "converg": [2, 11, 13], "maximum": 2, "hold": 2, "declar": [2, 7, 18], "conserv": [2, 11], "2": [2, 5, 7, 9, 10, 11, 12, 14, 16, 17, 18], "paper": [2, 7, 11, 12, 15, 16, 18], "print": [2, 9, 10, 11, 12, 15], "boolean": [2, 3], "indic": [2, 3, 5, 11, 15, 16], "round": [2, 11, 15, 16], "off": [2, 7, 11, 16, 17], "threshold": 2, "target": [2, 9, 10, 11, 13, 14], "post": [2, 7, 12, 18], "hoc": 2, "oper": [2, 11, 15, 16], "enhanc": 2, "search": [2, 7, 11], "prefer": 2, "larg": 2, "incom": [2, 5, 7, 9, 10, 11, 12, 13, 15, 16, 18], "10k": 2, "1000k": 2, "share": [2, 11, 15, 16], "monoton": [2, 12], "relationship": [2, 9, 12, 13], "upper": 2, "limit": [2, 11, 16], "step": [2, 7, 9, 10, 11, 13, 14, 15, 16, 18], "posthoc_sparsity_enhanc": 2, "see": [2, 7, 11, 12, 14, 15, 16, 18], "diverse_counterfactu": [2, 7, 8], "py": [2, 9, 11, 12, 13, 15, 16], "nelder": 2, "mead": 2, "templat": [2, 3], "subclass": [2, 3, 6], "abc": 2, "predicted_outcome_nam": 2, "comment": [2, 7, 9, 12, 13, 18], "necessari": [2, 11], "els": [2, 9, 12, 13], "remov": [2, 16], "feature_ranges_orig": 2, "model_output": 2, "path": [2, 9, 12, 13], "reload": 2, "memori": [2, 14], "read": [2, 12], "file": [2, 9, 11, 12, 13, 15, 16], "diff": 2, "decimal_prec": 2, "cf_ix": 2, "final_cfs_spars": 2, "current_pr": 2, "until": [2, 12], "chang": [2, 7, 10, 11, 12, 17, 18], "current_pred_orig": 2, "greedi": 2, "move": 2, "toward": [2, 7, 11, 12, 18], "greedili": 2, "reach": [2, 15], "encourag": 2, "final": [2, 7, 11, 18], "panda": [2, 7, 14, 16, 18], "done": [2, 7, 16, 18], "avoid": [2, 12], "infinit": 2, "10": [2, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "global_import": 2, "given": [2, 7, 10, 11, 12, 14, 18], "which": [2, 7, 11, 12, 16, 18], "These": [2, 10, 11], "precomput": 2, "everi": [2, 6, 11], "follow": [2, 7, 11, 15, 16, 18], "ignor": [2, 6, 9, 10, 11, 13, 14, 15, 16], "per": [2, 7, 9, 10, 11, 12, 13, 15, 18], "other_paramet": 2, "includ": [2, 11, 12], "summar": [2, 11], "over": [2, 7, 15, 17], "For": [2, 7, 9, 10, 11, 12, 14, 15, 16, 18], "regress": [2, 7, 10, 11, 17], "problem": [2, 7, 18], "ascend": 2, "order": [2, 11, 15, 16], "gradientdesc": 2, "less": [2, 11, 13, 15], "whether": [2, 7, 11, 12, 18], "detail": [2, 7, 11, 12, 15, 18], "messag": [2, 5], "sample_s": 2, "random_se": [2, 13], "reproduc": [2, 15], "accept": 2, "specif": [2, 7, 14, 18], "its": [2, 7, 12, 18], "attribut": [2, 7, 12, 15, 17, 18], "model_scor": [2, 3], "flag": [2, 11, 15, 16], "also": [2, 7, 10, 11, 12, 13, 15, 16, 18], "desired_class_input": 2, "original_pr": 2, "num_output_nod": 2, "call": [2, 5, 6, 9, 11, 12, 13, 15, 16], "multiclass": [2, 7, 17], "downstream": 2, "allow": [2, 7, 11, 12, 15, 18], "desired_range_input": 2, "belong": 2, "test_pr": 2, "z": [2, 6], "vae": [2, 7, 11, 17, 18], "model_out": 2, "target_label": 2, "pre_train": [2, 12], "bool": [2, 6], "pre": [2, 7, 11, 12, 18], "exist": [2, 11, 12, 15, 16], "again": [2, 12, 13], "constraint_typ": 2, "constraint_vari": 2, "constraint_direct": 2, "constraint_reg": 2, "unari": [2, 12], "effect": [2, 12], "cause1": 2, "cause2": 2, "neg": 2, "By": [2, 7, 15, 18], "ha": [2, 7, 11, 12, 15, 16, 18], "tunabl": [2, 7, 15, 18], "hyperparamt": 2, "OR": 3, "inp_siz": 3, "singleton": 3, "kera": [3, 7, 18], "input_tensor": 3, "mode": [3, 7, 9, 12, 13, 18], "autoencod": [5, 6, 7, 18], "decod": [5, 6, 12], "normal_likelihood": [5, 6], "sample_latent_cod": [5, 6], "cf_vae": [5, 6], "compute_elbo": [5, 6], "some": [5, 7, 10, 11, 12, 15, 16, 18], "system": [5, 7, 18], "happen": 5, "dure": [5, 13], "execut": [5, 11, 16], "exception_messag": 5, "str": [5, 9, 12, 13, 15], "describ": [5, 7, 9, 11, 12, 13, 18], "error": [5, 11, 12, 15, 16], "configur": [5, 11], "valid": [5, 7, 11, 12, 18], "containt": 5, "load": [5, 7, 16, 17], "deta": 5, "functiontransform": 5, "scikit": [5, 7, 9, 13, 14, 16, 18], "intern": [5, 7, 14, 15, 18], "stabl": [5, 7, 14, 16, 18], "preprocess": [5, 9, 10, 11, 12, 13, 14], "html": [5, 14, 16], "encoded_s": [5, 6, 12], "cont_minx": 5, "cont_maxx": 5, "margin": [5, 12], "validity_reg": [5, 12], "epoch": [5, 7, 12, 18], "wm1": [5, 12], "wm2": [5, 12], "wm3": [5, 12], "only_train": [5, 9, 12, 13], "adult": [5, 9, 12, 13, 15, 16], "archiv": [5, 9, 11, 12, 13, 15, 16], "ic": [5, 9, 11, 12, 13, 15, 16], "uci": [5, 9, 11, 12, 13, 15, 16], "edu": [5, 9, 11, 12, 13, 15, 16], "analysi": [5, 9, 12, 13], "rpub": [5, 9, 12, 13], "com": [5, 7, 9, 12, 13, 18], "h_zhu": [5, 9, 12, 13], "235617": [5, 9, 12, 13], "adult_data": [5, 9, 12, 13], "modelpath": 5, "test_fract": 5, "random_st": [5, 9, 10, 11, 13, 14], "arg": [5, 12], "ani": [5, 7, 10, 11, 14, 17, 18], "outcome_nam": [5, 7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "data_df": [5, 10], "overridden": 6, "although": 6, "recip": 6, "pass": [6, 13], "within": [6, 7, 11, 13, 18], "afterward": 6, "sinc": [6, 11, 12, 13, 15, 16], "former": 6, "care": 6, "regist": 6, "hook": 6, "while": [6, 11, 12], "latter": 6, "silent": 6, "mean": [6, 7, 11, 12, 15, 18], "logvar": 6, "raxi": 6, "c": [6, 7, 9, 12, 13, 15, 16, 18], "pred_model": 6, "how": [7, 10, 11, 12, 13, 14, 15, 18], "machin": [7, 9, 11, 12, 13, 15, 16, 18], "truth": [7, 18], "yet": [7, 18], "peopl": [7, 18], "ramaravind": [7, 18], "mothil": [7, 18], "amit": [7, 18], "sharma": [7, 18], "chenhao": [7, 18], "tan": [7, 18], "fat": [7, 18], "20": [7, 9, 10, 11, 12, 13, 15, 18], "doc": [7, 18], "live": [7, 18], "jupyt": [7, 18], "blog": [7, 18], "studi": [7, 18], "scienc": [7, 18], "hotel": [7, 18], "book": [7, 18], "analyt": [7, 18], "vidhya": [7, 18], "titan": [7, 18], "critic": [7, 11, 15, 16, 18], "especi": [7, 18], "being": [7, 11, 18], "decis": [7, 11, 18], "societ": [7, 18], "domain": [7, 18], "financ": [7, 18], "healthcar": [7, 18], "educ": [7, 9, 10, 11, 12, 13, 15, 16, 18], "crimin": [7, 18], "justic": [7, 18], "howev": [7, 11, 12, 15, 16, 18], "most": [7, 9, 12, 13, 15, 18], "depend": [7, 18], "approxim": [7, 15, 18], "consid": [7, 18], "person": [7, 11, 15, 18], "who": [7, 18], "appli": [7, 11, 18], "loan": [7, 18], "wa": [7, 11, 16, 18], "reject": [7, 18], "distribut": [7, 18], "financi": [7, 18], "compani": [7, 18], "typic": [7, 18], "mai": [7, 11, 15, 16, 18], "why": [7, 15, 18], "due": [7, 11, 15, 16, 18], "poor": [7, 18], "credit": [7, 18], "histori": [7, 18], "doe": [7, 11, 15, 16, 18], "help": [7, 11, 15, 18], "what": [7, 15, 17, 18], "next": [7, 16, 17, 18], "improv": [7, 18], "chanc": [7, 18], "approv": [7, 18], "futur": [7, 11, 16, 18], "enough": [7, 18], "flip": [7, 18], "even": [7, 11, 12, 18], "changeabl": [7, 18], "gender": [7, 9, 10, 11, 12, 13, 15, 16, 18], "race": [7, 9, 10, 11, 12, 13, 15, 16, 18], "show": [7, 9, 10, 11, 12, 13, 15, 16, 18], "perturb": [7, 11, 12, 15, 18], "would": [7, 11, 12, 15, 18], "have": [7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "receiv": [7, 11, 18], "e": [7, 11, 15, 18], "g": [7, 11, 15, 18], "you": [7, 9, 11, 12, 13, 14, 15, 16, 18], "your": [7, 11, 15, 16, 18], "higher": [7, 11, 15, 18], "000": [7, 18], "In": [7, 9, 11, 12, 13, 15, 18], "word": [7, 18], "complement": [7, 18], "end": [7, 11, 12, 18], "develop": [7, 18], "bar": [7, 18], "difficult": [7, 15, 18], "recent": [7, 9, 12, 13, 15, 18], "research": [7, 18], "core": [7, 11, 14, 15, 16, 18], "idea": [7, 13, 18], "adversari": [7, 18], "therefor": [7, 11, 18], "proxim": [7, 10, 11, 17, 18], "It": [7, 11, 12, 13, 15, 18], "python": [7, 9, 12, 13, 16, 18], "3": [7, 9, 10, 11, 12, 14, 16, 17, 18], "pypi": [7, 18], "pip": [7, 18], "conda": [7, 18], "forg": [7, 18], "latest": [7, 12, 18], "dev": [7, 18], "clone": [7, 18], "repo": [7, 18], "top": [7, 18], "folder": [7, 18], "face": [7, 18], "try": [7, 11, 12, 15, 16, 18], "manual": [7, 16, 18], "r": [7, 12, 18], "txt": [7, 18], "addit": [7, 11, 12, 18], "dependendi": [7, 18], "deep": [7, 15, 17, 18], "deeplearn": [7, 18], "unit": [7, 15, 18], "jsonschema": [7, 18], "numpi": [7, 9, 12, 13, 15, 18], "h5py": [7, 18], "tqdm": [7, 15, 18], "13": [7, 9, 11, 13, 14, 15, 18], "With": [7, 18], "three": [7, 9, 11, 13, 15, 18], "process": [7, 12, 18], "invok": [7, 18], "dice_ml": [7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "continuous_featur": [7, 9, 10, 11, 12, 13, 14, 15, 18], "ag": [7, 9, 10, 11, 12, 13, 15, 16, 18], "hours_per_week": [7, 9, 10, 11, 12, 13, 15, 16, 18], "m": [7, 9, 10, 11, 12, 13, 15, 16, 18], "exp": [7, 10, 11, 12, 15, 16, 18], "now": [7, 9, 10, 11, 12, 13, 14, 15, 18], "lead": [7, 11, 16, 18], "22": [7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "workclass": [7, 9, 10, 11, 12, 13, 15, 16, 18], "h": [7, 10, 11, 12, 15, 16, 18], "grad": [7, 10, 11, 12, 15, 16, 18], "marital_statu": [7, 10, 11, 12, 15, 16, 18], "occup": [7, 9, 10, 11, 12, 13, 15, 16, 18], "servic": [7, 10, 11, 12, 15, 16, 18], "white": [7, 10, 11, 12, 15, 16, 18], "femal": [7, 10, 11, 12, 15, 16, 18], "45": [7, 10, 12, 14, 15, 16, 18], "been": [7, 15, 16, 18], "dice_exp": [7, 9, 11, 12, 15, 16, 18], "4": [7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "save": [7, 18], "wai": [7, 11, 12, 15, 18], "disk": [7, 18], "to_csv": [7, 18], "path_or_buf": [7, 18], "csv": [7, 18], "out": [7, 11, 18], "here": [7, 12, 13, 15, 18], "multi": [7, 11, 17, 18], "permiss": [7, 18], "agnost": [7, 9, 11, 18], "explicit": [7, 11, 18], "et": [7, 18], "al": [7, 18], "2020": [7, 18], "variat": [7, 12, 18], "mahajan": [7, 18], "2019": [7, 18], "baseva": [7, 12, 18], "last": [7, 9, 11, 12, 13, 15, 18], "differenti": [7, 11, 18], "neural": [7, 11, 15, 16, 18], "network": [7, 11, 15, 16, 18], "rais": [7, 9, 12, 13, 18], "issu": [7, 13, 18], "full": [7, 9, 10, 11, 12, 13, 14, 18], "thu": [7, 15, 18], "sensit": [7, 11, 18], "17": [7, 10, 11, 13, 14, 15, 16, 18], "90": [7, 10, 15, 16, 18], "govern": [7, 10, 11, 12, 16, 18], "unknown": [7, 10, 11, 12, 15, 16, 18], "self": [7, 9, 10, 11, 12, 13, 15, 16, 18], "emploi": [7, 10, 11, 12, 15, 16, 18], "assoc": [7, 10, 11, 12, 15, 16, 18], "bachelor": [7, 10, 11, 12, 15, 16, 18], "doctor": [7, 10, 11, 12, 16, 18], "master": [7, 10, 11, 12, 16, 18], "prof": [7, 10, 11, 12, 16, 18], "school": [7, 10, 11, 12, 16, 18], "colleg": [7, 10, 11, 12, 15, 16, 18], "divorc": [7, 10, 11, 12, 16, 18], "marri": [7, 10, 11, 12, 15, 16, 18], "separ": [7, 10, 11, 12, 16, 18], "widow": [7, 10, 11, 12, 16, 18], "blue": [7, 10, 11, 12, 16, 18], "collar": [7, 10, 11, 12, 15, 16, 18], "profession": [7, 10, 11, 12, 15, 16, 18], "sale": [7, 10, 11, 12, 16, 18], "male": [7, 10, 11, 12, 15, 16, 18], "99": [7, 15, 16, 18], "well": [7, 18], "sess": [7, 18], "interactivesess": [7, 18], "split_data": [7, 18], "x_train": [7, 9, 10, 11, 13, 14, 18], "loc": [7, 9, 18], "y_train": [7, 9, 10, 11, 13, 14, 18], "fit": [7, 9, 10, 11, 12, 13, 14, 18], "dens": [7, 18], "ann_model": [7, 18], "sequenti": [7, 12, 18], "layer": [7, 18], "input_shap": [7, 18], "shape": [7, 18], "kernel_regular": [7, 18], "regular": [7, 18], "l1": [7, 18], "001": [7, 18], "activ": [7, 12, 18], "nn": [7, 12, 18], "relu": [7, 12, 18], "compil": [7, 11, 15, 16, 18], "binary_crossentropi": [7, 18], "01": [7, 14, 18], "accuraci": [7, 11, 12, 16, 18], "validation_split": [7, 18], "100": [7, 10, 11, 12, 14, 16, 18], "class_weight": [7, 18], "highlight": [7, 11, 18], "plan": [7, 18], "english": [7, 18], "languag": [7, 18], "too": [7, 12, 18], "acknowledg": [7, 15, 18], "closer": [7, 15, 18], "individu": [7, 11, 15, 18], "profil": [7, 15, 18], "choos": [7, 15, 18], "multipl": [7, 11, 14, 15, 18], "possibl": [7, 11, 15, 18], "kind": [7, 11, 12, 18], "addition": [7, 11, 18], "harder": [7, 15, 18], "than": [7, 11, 13, 15, 16, 18], "hour": [7, 9, 10, 11, 12, 13, 15, 18], "week": [7, 9, 10, 11, 12, 13, 15, 18], "rel": [7, 11, 15, 16, 18], "difficulti": [7, 15, 18], "measur": [7, 10, 15, 18], "divid": [7, 15, 18], "imposs": [7, 11, 18], "reflect": [7, 15, 18], "50": [7, 10, 11, 13, 15, 18], "Being": [7, 18], "stakehold": [7, 18], "made": [7, 11, 18], "subject": [7, 18], "explor": [7, 11, 18], "action": [7, 18], "recours": [7, 18], "altern": [7, 18], "understand": [7, 11, 18], "could": [7, 11, 15, 16, 18], "debug": [7, 18], "potenti": [7, 18], "select": [7, 15, 18], "uncov": [7, 18], "problemat": [7, 18], "95": [7, 18], "aim": [7, 18], "aggreg": [7, 11, 18], "maker": [7, 18], "judg": [7, 18], "particular": [7, 10, 11, 15, 16, 18], "probe": [7, 18], "enabl": [7, 11, 15, 16, 18], "assess": [7, 18], "trust": [7, 18], "evalu": [7, 18], "fair": [7, 18], "ideal": [7, 11, 18], "balanc": [7, 18], "wide": [7, 18], "suggest": [7, 18], "eas": [7, 15, 18], "adopt": [7, 18], "those": [7, 10, 11, 16, 18], "causal": [7, 18], "law": [7, 18], "world": [7, 18], "hardli": [7, 18], "lower": [7, 18], "degre": [7, 18], "ad": [7, 17, 18], "construct": [7, 11, 12, 18], "phrase": [7, 18], "like": [7, 9, 10, 11, 12, 13, 18], "lime": [7, 11, 18], "shap": [7, 11, 18], "necess": [7, 10, 11, 18], "suffici": [7, 11, 18], "bayesian": [7, 18], "better": [7, 11, 18], "pleas": [7, 13, 16, 18], "proceed": [7, 18], "confer": [7, 18], "account": [7, 18], "transpar": [7, 18], "bibtex": [7, 18], "inproceed": [7, 18], "mothilal2020dic": [7, 18], "titl": [7, 18], "author": [7, 18], "booktitl": [7, 18], "page": [7, 18], "607": [7, 18], "617": [7, 18], "year": [7, 11, 18], "welcom": [7, 18], "agre": [7, 18], "contributor": [7, 18], "licens": [7, 18], "agreement": [7, 18], "cla": [7, 18], "right": [7, 18], "grant": [7, 18], "u": [7, 15, 18], "visit": [7, 18], "microsoft": [7, 18], "submit": [7, 18], "pull": [7, 18], "request": [7, 12, 18], "bot": [7, 18], "automat": [7, 18], "decor": [7, 18], "pr": [7, 18], "simpli": [7, 11, 18], "instruct": [7, 11, 15, 16, 18], "onc": [7, 14, 18], "across": [7, 13, 18], "our": [7, 11, 12, 13, 15, 16, 18], "open": [7, 9, 11, 12, 13, 15, 16, 18], "conduct": [7, 18], "faq": [7, 18], "contact": [7, 18], "opencod": [7, 18], "question": [7, 11, 18], "quick": [7, 17], "introduct": [7, 17], "preliminari": [7, 17], "resourc": [7, 17], "independ": [7, 9, 17], "without": [7, 11, 12, 17], "advanc": [7, 12, 16, 17], "custom": [7, 11, 16, 17], "trade": [7, 17], "goal": [7, 13, 17], "modelapprox": [7, 17], "initil": [7, 17], "subpackag": [7, 8], "submodul": [7, 8], "constant": [7, 8, 11, 16], "modul": [7, 8, 9, 11, 12, 13, 14, 15, 16], "counterfactual_explan": [7, 8], "content": [7, 8], "packag": [8, 9, 11, 12, 13, 16, 18], "notebook": [9, 11, 12, 13, 14, 16, 18], "runtim": 9, "np": [9, 12, 13], "timeit": 9, "compos": [9, 10, 11, 13, 14], "columntransform": [9, 10, 11, 13, 14, 16], "model_select": [9, 10, 11, 13, 14], "train_test_split": [9, 10, 11, 13, 14], "pipelin": [9, 10, 11, 13, 14, 16], "standardscal": [9, 10, 13, 14], "onehotencod": [9, 10, 11, 13, 14, 16], "ensembl": [9, 10, 11, 13, 14], "randomforestclassifi": [9, 10, 11, 13, 14, 16], "load_ext": [9, 10, 11, 12, 13, 14, 15, 16], "autoreload": [9, 10, 11, 12, 13, 14, 15, 16], "repositori": [9, 11, 12, 13, 15, 16], "demonstr": [9, 11, 12, 13, 14, 15], "purpos": [9, 11, 12, 15], "filenotfounderror": [9, 13], "traceback": [9, 12, 13, 15], "lt": [9, 10, 11, 12, 13, 14, 15, 16], "cell": [9, 12, 13, 15], "line": [9, 12, 13, 15], "gt": [9, 10, 11, 12, 13, 14, 15], "mnt": [9, 12, 13, 15, 16], "amshar": [9, 11, 12, 13, 15, 16], "25": [9, 10, 12, 13, 14], "19": [9, 10, 11, 12, 13, 14, 15, 16], "def": [9, 12, 13, 15], "34": [9, 10, 11, 12, 13, 14, 15], "21": [9, 10, 11, 12, 13, 14], "23": [9, 10, 11, 12, 13, 14], "24": [9, 12, 13, 14, 15, 16], "raw_data": [9, 12, 13], "genfromtxt": [9, 12, 13], "39": [9, 10, 11, 12, 13, 14, 15, 16], "databas": [9, 12, 13], "26": [9, 11, 12, 13, 16], "delimit": [9, 12, 13], "dtype": [9, 12, 13, 14], "invalid_rais": [9, 12, 13], "28": [9, 10, 11, 12, 13, 14, 15, 16], "29": [9, 10, 11, 12, 13, 14, 15, 16], "column_nam": [9, 12, 13], "fnlwgt": [9, 12, 13], "num": [9, 10, 12, 13, 14], "marit": [9, 10, 11, 12, 13], "statu": [9, 10, 11, 12, 13], "30": [9, 10, 11, 12, 13, 15], "capit": [9, 12, 13], "gain": [9, 12, 13], "nativ": [9, 12, 13], "countri": [9, 12, 13], "31": [9, 10, 12, 13, 15], "env": [9, 12, 13, 16], "v3": [9, 12, 13, 16], "8dowhi": [9, 12, 13, 16], "lib": [9, 12, 13, 16], "python3": [9, 12, 13, 16], "8": [9, 10, 11, 12, 13, 14, 15, 16], "site": [9, 12, 13, 16], "npyio": [9, 12, 13], "1934": [9, 12, 13], "fname": [9, 12, 13], "skip_head": [9, 12, 13], "skip_foot": [9, 12, 13], "missing_valu": [9, 12, 13], "filling_valu": [9, 12, 13], "usecol": [9, 12, 13], "excludelist": [9, 12, 13], "deletechar": [9, 12, 13], "replace_spac": [9, 12, 13], "autostrip": [9, 12, 13], "case_sensit": [9, 12, 13], "defaultfmt": [9, 12, 13], "unpack": [9, 12, 13], "usemask": [9, 12, 13], "loos": [9, 12, 13], "max_row": [9, 12, 13], "ndmin": [9, 12, 13], "1932": [9, 12, 13], "os_fspath": [9, 12, 13], "1933": [9, 12, 13], "isinst": [9, 12, 13], "fid": [9, 12, 13], "_datasourc": [9, 12, 13], "rt": [9, 12, 13], "1935": [9, 12, 13], "fid_ctx": [9, 12, 13], "contextlib": [9, 12, 13], "1936": [9, 12, 13], "193": [9, 11, 12, 13, 15, 16], "destpath": [9, 12, 13], "newlin": [9, 12, 13], "156": [9, 11, 12, 13, 15, 16], "157": [9, 12, 13], "158": [9, 12, 13, 15], "189": [9, 12, 13], "190": [9, 12, 13], "192": [9, 12, 13], "datasourc": [9, 12, 13], "533": [9, 13], "530": [9, 13], "_file_open": [9, 13], "ext": [9, 12, 13], "found": [9, 11, 12, 13, 16], "531": [9, 13], "532": [9, 13], "f": [9, 13], "head": [9, 11, 12, 13, 14, 15], "nameerror": [9, 12, 13, 15], "soon": [9, 12, 13], "6": [9, 10, 11, 12, 13, 14, 15, 16], "split": [9, 10, 11, 12, 13, 14], "datasetx": [9, 10, 13, 14], "drop": [9, 10, 11, 13, 14], "axi": [9, 10, 11, 13, 14], "x_test": [9, 10, 11, 13, 14], "y_test": [9, 10, 11, 13, 14], "test_siz": [9, 10, 11, 12, 13, 14], "stratifi": [9, 10, 11, 13, 14], "numeric_transform": [9, 10, 13, 14], "scaler": [9, 10, 13, 14], "categorical_transform": [9, 10, 11, 13, 14], "onehot": [9, 10, 11, 13, 14], "handle_unknown": [9, 10, 11, 13, 14], "cat": [9, 10, 11, 13, 14], "append": [9, 10, 11, 13, 14, 15, 16], "clf": [9, 10, 11, 13], "preprocessor": [9, 10, 11, 13, 14], "7": [9, 10, 11, 12, 13, 14, 15, 16], "exp_random": [9, 13], "9": [9, 10, 11, 12, 13, 14, 15, 16], "exp_genet": [9, 13], "exp_kd": [9, 13], "11": [9, 10, 11, 12, 13, 14, 15, 16], "12": [9, 10, 11, 12, 13, 14, 15], "modifi": 9, "num_loop": 9, "14": [9, 10, 11, 13, 14, 15, 16], "elapsed_random": 9, "elapsed_kd": 9, "elapsed_genet": 9, "q": 9, "categorical_feature_nam": 9, "uniqu": 9, "choic": 9, "uniform": 9, "start_tim": 9, "default_tim": 9, "dice_exp_random": [9, 13], "m_random": 9, "s_random": 9, "divmod": 9, "60": [9, 11, 13, 15, 16], "taken": [9, 11, 16], "02d": 9, "sec": [9, 11, 16], "m_kd": 9, "s_kd": 9, "m_genet": 9, "s_genet": 9, "summari": [10, 11], "intuit": [10, 11], "often": [10, 11], "build": [10, 13], "caus": [10, 11, 12], "That": [10, 11, 12], "significantli": [10, 11, 16], "case": [10, 11, 12, 15, 16], "combin": [10, 15], "yield": 10, "downsampl": 10, "reduc": 10, "industri": [10, 11, 12], "50k": [10, 11, 12], "v": [10, 11, 12], "e1": [10, 11], "00": [10, 11, 14, 15, 16], "12it": [10, 11], "43": [10, 14, 16], "94": 10, "63": [10, 11], "33": [10, 14], "15": [10, 11, 13, 14, 15], "77": 10, "64": [10, 11, 15, 16], "calcul": 10, "imp": [10, 11], "directli": [10, 16], "leav": 10, "argument": [10, 11, 12, 14], "blank": 10, "18it": 10, "repres": 10, "cobj": 10, "57it": 10, "46": [10, 11], "test_data": 10, "37": [10, 11, 14], "40": [10, 11, 13], "44": [10, 16], "41": [10, 11, 12, 14, 15], "53": 10, "38": [10, 11, 14, 16], "cfs_list": 10, "73": [10, 16], "88": [10, 14], "42": [10, 12], "83": 10, "59": 10, "55": [10, 15, 16], "27": [10, 13], "80": 10, "81": [10, 14], "36": 10, "47": [10, 14], "67": 10, "52": [10, 14], "84": 10, "93": 10, "57": 10, "78": 10, "82": 10, "51": [10, 11], "98": 10, "72": 10, "91": 10, "56": [10, 15, 16], "66": 10, "69": [10, 11], "75": 10, "97": [10, 14], "70": [10, 11, 16], "65": [10, 11, 15], "68": [10, 11], "54": 10, "48": 10, "79": 10, "74": [10, 16], "89": [10, 16], "71": 10, "62": [10, 11], "dummy_data": 10, "feature_nam": [10, 14], "feature_names_including_target": 10, "null": [10, 14], "imp_r": 10, "o": 10, "scenario": 11, "inspect": 11, "librari": [11, 12, 14, 15, 16], "formal": 11, "known": 11, "answer": 11, "abov": [11, 12, 15, 16], "obtain": 11, "revers": 11, "know": [11, 16], "bring": 11, "logic": 11, "spars": [11, 13], "achiev": 11, "easi": 11, "minim": 11, "anoth": [11, 12], "feasibl": [11, 13, 15, 17], "outsid": 11, "simplest": 11, "complex": [11, 12], "concept": 11, "just": [11, 14], "certain": 11, "releas": 11, "x_i": 11, "keep": 11, "similarli": 11, "absenc": 11, "neither": 11, "nor": 11, "definit": 11, "translat": 11, "easili": 11, "deriv": 11, "rank": 11, "frequenc": 11, "among": 11, "parameter": 11, "refin": 11, "space": 11, "consequ": 11, "compar": [11, 12, 15, 16], "tend": 11, "give": [11, 13], "black": 11, "box": 11, "nearbi": 11, "privaci": 11, "reason": [11, 12, 15], "binar": [11, 12], "32": [11, 15], "35": [11, 15], "descript": [11, 12], "adult_info": [11, 12], "train_dataset": 11, "test_dataset": 11, "want": [11, 13, 16], "four": 11, "snippet": 11, "38it": 11, "restrict": 11, "e2": 11, "58it": 11, "e3": 11, "72it": 11, "operation": 11, "criterion": 11, "refer": [11, 12, 16], "unifi": 11, "around": 11, "denot": 11, "04": 11, "83it": [11, 14], "275": 11, "235": 11, "175": 11, "155": 11, "09": 11, "rather": 11, "slower": 11, "compon": 11, "formul": 11, "baselin": [11, 12, 16], "conveni": [11, 12], "16": [11, 13, 14, 15, 16], "instal": 11, "ml_modelpath": [11, 12, 15, 16], "2022": [11, 15, 16], "694158": 11, "cc": [11, 15, 16], "169": [11, 15, 16], "onednn": [11, 15, 16], "slightli": [11, 15, 16], "turn": [11, 15, 16], "environ": [11, 15, 16], "tf_enable_onednn_opt": [11, 15, 16], "698027": 11, "w": [11, 15, 16], "stream_executor": [11, 15, 16], "platform": [11, 15, 16], "dso_load": [11, 15, 16], "dynam": [11, 15, 16], "libcudart": [11, 15, 16], "so": [11, 15, 16], "dlerror": [11, 15, 16], "cannot": [11, 15, 16], "No": [11, 15, 16], "directori": [11, 15, 16], "698044": 11, "cuda": [11, 15, 16], "cudart_stub": [11, 15, 16], "cudart": [11, 15, 16], "gpu": [11, 15, 16], "up": [11, 15, 16], "note": [11, 12, 13, 15, 16], "eager": [11, 16], "style": [11, 16], "greater": [11, 16], "graph": [11, 16], "instanti": [11, 12], "49": 11, "357741": 11, "libcuda": [11, 15, 16], "357797": 11, "cuda_driv": [11, 15, 16], "269": [11, 15, 16], "fail": [11, 12, 15, 16], "cuinit": [11, 15, 16], "303": [11, 15, 16], "357820": 11, "cuda_diagnost": [11, 15, 16], "kernel": [11, 15, 16], "driver": [11, 15, 16], "appear": [11, 15, 16], "host": [11, 15, 16], "proc": [11, 15, 16], "nvidia": [11, 15, 16], "358100": 11, "cpu_feature_guard": [11, 15, 16], "oneapi": [11, 15, 16], "cpu": [11, 15, 16], "avx2": [11, 15, 16], "avx512f": [11, 15, 16], "avx512_vnni": [11, 15, 16], "fma": [11, 15, 16], "rebuild": [11, 15, 16], "18": [11, 13], "671": 11, "rigor": 11, "experiment": 11, "replic": 11, "info": [11, 14, 16], "dice_interfac": 11, "dice_tensorflow": 11, "03": 11, "07": 11, "618": 11, "968": 11, "35it": 11, "constrain": [11, 12, 13], "weigh": [11, 16], "consider": 11, "likelihood": 11, "term": 11, "present": 12, "approach": 12, "ab": 12, "1912": 12, "03277": 12, "remotedisconnect": 12, "525": [12, 16], "522": 12, "valueerror": 12, "url": 12, "writeabl": 12, "524": 12, "_findfil": 12, "write": 12, "526": [12, 14], "527": 12, "_fname": 12, "_splitzipext": 12, "369": 12, "366": 12, "filelist": 12, "_possible_nam": 12, "368": 12, "370": 12, "_isurl": 12, "371": 12, "_cach": 12, "479": 12, "477": 12, "478": 12, "netfil": 12, "urlopen": 12, "480": 12, "481": 12, "del": 12, "usr": 12, "urllib": 12, "222": 12, "timeout": 12, "cafil": 12, "capath": 12, "cadefault": 12, "context": 12, "220": 12, "221": 12, "_open": 12, "openerdirector": 12, "fullurl": 12, "req": 12, "meth": 12, "sy": 12, "audit": 12, "full_url": 12, "header": 12, "get_method": 12, "respons": 12, "528": 12, "meth_nam": 12, "protocol": 12, "_respons": 12, "542": 12, "539": 12, "541": 12, "_call_chain": 12, "handle_open": 12, "543": 12, "544": 12, "545": 12, "502": 12, "chain": 12, "handler": 12, "501": 12, "getattr": 12, "503": 12, "504": 12, "1397": 12, "httpshandler": 12, "https_open": 12, "1396": 12, "do_open": 12, "client": 12, "httpsconnect": 12, "1398": 12, "_context": 12, "check_hostnam": 12, "_check_hostnam": 12, "1358": 12, "abstracthttphandl": 12, "http_class": 12, "http_conn_arg": 12, "1356": 12, "oserror": 12, "err": 12, "1357": 12, "urlerror": 12, "getrespons": 12, "1359": 12, "1360": 12, "1348": 12, "httpconnect": 12, "1346": 12, "1347": 12, "begin": 12, "1349": 12, "connectionerror": 12, "1350": 12, "316": 12, "httprespons": 12, "314": 12, "non": [12, 14, 15], "315": 12, "_read_statu": 12, "317": 12, "318": 12, "break": [12, 16], "285": 12, "281": 12, "repli": 12, "repr": 12, "282": 12, "283": 12, "presum": 12, "server": 12, "connect": 12, "befor": [12, 15], "284": 12, "send": 12, "remot": 12, "286": 12, "287": 12, "288": 12, "data_nam": 12, "becaus": 12, "_2node": 12, "pth": 12, "userwarn": [12, 16], "warn": [12, 15, 16], "in_featur": 12, "out_featur": 12, "bia": 12, "softmax": 12, "dim": 12, "home": [12, 16], "torch": 12, "786": 12, "sourcechangewarn": 12, "retriev": 12, "dump_patch": 12, "patch": 12, "tool": 12, "revert": 12, "msg": 12, "arug": 12, "re": [12, 15], "repeat": 12, "lr": 12, "batch_siz": 12, "2048": 12, "165": 12, "super": 12, "fast": 12, "might": [12, 16], "notic": 12, "still": [12, 16], "infeas": 12, "adpat": 12, "prodcu": 12, "adapt": 12, "under": 12, "assumpt": 12, "section": 12, "preserv": 12, "ed": 12, "never": 12, "decreas": 12, "increas": [12, 13, 15], "impli": [12, 15], "cause_1": 12, "cause_n": 12, "intend": 12, "direct": 12, "fourth": 12, "penalti": 12, "76": 12, "344": 12, "87": 12, "unlik": 12, "experi": 12, "scmgencf": 12, "oraclegencf": 12, "method_nam": 13, "observ": [13, 15, 16], "contrast": 13, "worsen": 13, "further": 13, "sens": 13, "randomli": 13, "freeli": 13, "control": 13, "best": 13, "quickli": 13, "promot": 13, "previous": 13, "dice_exp_genet": 13, "wish": 13, "closest": 13, "effici": 13, "behind": 13, "itself": 13, "displai": 13, "dice_exp_kd": 13, "rest": 14, "complet": 14, "ident": 14, "load_iri": 14, "fetch_california_h": 14, "randomforestregressor": 14, "pd": [14, 16], "iri": 14, "consist": 14, "iris": 14, "setosa": 14, "versicolour": 14, "virginica": 14, "petal": 14, "sepal": 14, "length": 14, "toy_dataset": 14, "plant": 14, "df_iri": 14, "as_fram": 14, "frame": [14, 16], "cm": 14, "width": 14, "rangeindex": 14, "150": 14, "entri": 14, "149": 14, "count": 14, "float64": 14, "int64": 14, "usag": 14, "kb": 14, "continuous_features_iri": 14, "tolist": 14, "categorical_featur": 14, "clf_iri": 14, "model_iri": 14, "d_iri": 14, "m_iri": 14, "exp_genetic_iri": 14, "As": [14, 15, 16], "lie": 14, "query_instances_iri": 14, "genetic_iri": 14, "39it": 14, "california": 14, "hous": 14, "price": 14, "housing_data": 14, "df_hous": 14, "seri": 14, "medinc": 14, "houseag": 14, "averoom": 14, "avebedrm": 14, "popul": 14, "aveoccup": 14, "latitud": 14, "longitud": 14, "3252": 14, "984127": 14, "023810": 14, "322": 14, "555556": 14, "122": 14, "3014": 14, "238137": 14, "971880": 14, "2401": 14, "109842": 14, "86": 14, "585": 14, "2574": 14, "288136": 14, "073446": 14, "496": 14, "802260": 14, "85": 14, "521": 14, "6431": 14, "817352": 14, "073059": 14, "558": 14, "547945": 14, "413": 14, "8462": 14, "281853": 14, "081081": 14, "565": 14, "181467": 14, "422": 14, "20640": 14, "20639": 14, "mb": 14, "continuous_features_h": 14, "regr_hous": 14, "model_h": 14, "d_hous": 14, "m_hous": 14, "exp_genetic_h": 14, "query_instances_h": 14, "genetic_h": 14, "49it": 14, "3487": 14, "930712": 14, "026217": 14, "1554": 14, "910112": 14, "650002": 14, "121": 14, "839996": 14, "49846": 14, "5173": 14, "119": 14, "4537603999999984": 14, "6184": 14, "1543": 14, "118": 14, "126689999999999": 14, "4511": 14, "992958": 14, "316901": 14, "390": 14, "746479": 14, "200001": 14, "115": 14, "599998": 14, "91159": 14, "3682": 14, "394": 14, "61": 14, "117": 14, "92": 14, "98180959999999": 14, "9167": 14, "393": 14, "890800399999997": 14, "discuss": [15, 16], "behavior": 15, "supress": 15, "deprec": [15, 16], "compat": 15, "v1": 15, "log": 15, "set_verbos": 15, "631881": 15, "635417": 15, "635428": 15, "artifici": 15, "set_random_se": 15, "set_se": 15, "__version__": [15, 16], "394561": 15, "394614": 15, "394632": 15, "394838": 15, "attributeerror": 15, "160": 15, "query_instances_list": 15, "159": 15, "set_continuous_feature_index": 15, "161": 15, "162": 15, "163": 15, "170": 15, "171": 15, "172": 15, "cf_examples_arr": 15, "remap": 15, "continuous_feature_index": 15, "get_loc": 15, "continuous_feature_nam": 15, "listcomp": 15, "resutl": 15, "convei": 15, "robust": 15, "standard": 15, "affect": 15, "outlier": 15, "let": 15, "seven": 15, "Of": 15, "cours": 15, "sound": 15, "odd": 15, "ride": 15, "handl": 15, "scale": [15, 16], "veri": 15, "categori": [15, 16], "tabl": [15, 18], "extrem": 15, "factor": 15, "captur": [15, 16], "preval": [15, 16], "respect": [15, 16], "basic": 16, "simul": 16, "ordereddict": 16, "randomforest": 16, "sk_modelpath": 16, "pretrain": 16, "329": 16, "unpickl": 16, "invalid": 16, "own": 16, "risk": 16, "model_persist": 16, "secur": 16, "maintain": 16, "decisiontreeclassifi": 16, "02": 16, "popular": 16, "come": 16, "built": 16, "noqa": 16, "988801": 16, "992079": 16, "992092": 16, "820933": 16, "820983": 16, "821002": 16, "821194": 16, "382": 16, "futurewarn": 16, "concat": 16, "temp": 16, "ohe_base_df": 16, "ignore_index": 16, "sort": 16, "019": 16, "911": 16, "755": 16, "dice_getting_start": 16, "nonetheless": 16}, "objects": {"": [[0, 0, 0, "-", "dice_ml"]], "dice_ml": [[0, 1, 1, "", "Data"], [0, 1, 1, "", "Dice"], [0, 1, 1, "", "Model"], [0, 0, 0, "-", "constants"], [0, 0, 0, "-", "counterfactual_explanations"], [0, 0, 0, "-", "data"], [1, 0, 0, "-", "data_interfaces"], [0, 0, 0, "-", "dice"], [0, 0, 0, "-", "diverse_counterfactuals"], [2, 0, 0, "-", "explainer_interfaces"], [0, 0, 0, "-", "model"], [3, 0, 0, "-", "model_interfaces"], [4, 0, 0, "-", "schema"], [5, 0, 0, "-", "utils"]], "dice_ml.Data": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.Dice": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.Model": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.constants": [[0, 1, 1, "", "BackEndTypes"], [0, 1, 1, "", "ModelTypes"], [0, 1, 1, "", "SamplingStrategy"]], "dice_ml.constants.BackEndTypes": [[0, 3, 1, "", "ALL"], [0, 3, 1, "", "Pytorch"], [0, 3, 1, "", "Sklearn"], [0, 3, 1, "", "Tensorflow1"], [0, 3, 1, "", "Tensorflow2"]], "dice_ml.constants.ModelTypes": [[0, 3, 1, "", "ALL"], [0, 3, 1, "", "Classifier"], [0, 3, 1, "", "Regressor"]], "dice_ml.constants.SamplingStrategy": [[0, 3, 1, "", "Genetic"], [0, 3, 1, "", "Gradient"], [0, 3, 1, "", "KdTree"], [0, 3, 1, "", "Random"]], "dice_ml.counterfactual_explanations": [[0, 1, 1, "", "CounterfactualExplanations"]], "dice_ml.counterfactual_explanations.CounterfactualExplanations": [[0, 4, 1, "", "cf_examples_list"], [0, 2, 1, "", "from_json"], [0, 4, 1, "", "local_importance"], [0, 4, 1, "", "metadata"], [0, 4, 1, "", "summary_importance"], [0, 2, 1, "", "to_json"], [0, 2, 1, "", "visualize_as_dataframe"], [0, 2, 1, "", "visualize_as_list"]], "dice_ml.data": [[0, 1, 1, "", "Data"], [0, 5, 1, "", "decide"]], "dice_ml.data.Data": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.data_interfaces": [[1, 0, 0, "-", "base_data_interface"], [1, 0, 0, "-", "private_data_interface"], [1, 0, 0, "-", "public_data_interface"]], "dice_ml.data_interfaces.private_data_interface": [[1, 1, 1, "", "PrivateData"]], "dice_ml.data_interfaces.private_data_interface.PrivateData": [[1, 2, 1, "", "create_ohe_params"], [1, 2, 1, "", "de_normalize_data"], [1, 2, 1, "", "fit_label_encoders"], [1, 2, 1, "", "from_dummies"], [1, 2, 1, "", "from_label"], [1, 2, 1, "", "get_all_dummy_colnames"], [1, 2, 1, "", "get_data_params_for_gradient_dice"], [1, 2, 1, "", "get_decimal_precisions"], [1, 2, 1, "", "get_decoded_data"], [1, 2, 1, "", "get_encoded_categorical_feature_indexes"], [1, 2, 1, "", "get_features_range"], [1, 2, 1, "", "get_indexes_of_features_to_vary"], [1, 2, 1, "", "get_inverse_ohe_min_max_normalized_data"], [1, 2, 1, "", "get_mads"], [1, 2, 1, "", "get_minx_maxx"], [1, 2, 1, "", "get_ohe_min_max_normalized_data"], [1, 2, 1, "", "get_valid_feature_range"], [1, 2, 1, "", "get_valid_mads"], [1, 2, 1, "", "normalize_data"], [1, 2, 1, "", "one_hot_encode_data"], [1, 2, 1, "", "prepare_df_for_ohe_encoding"], [1, 2, 1, "", "prepare_query_instance"]], "dice_ml.data_interfaces.public_data_interface": [[1, 1, 1, "", "PublicData"]], "dice_ml.data_interfaces.public_data_interface.PublicData": [[1, 2, 1, "", "create_ohe_params"], [1, 2, 1, "", "de_normalize_data"], [1, 2, 1, "", "fit_label_encoders"], [1, 2, 1, "", "from_dummies"], [1, 2, 1, "", "from_label"], [1, 2, 1, "", "get_all_dummy_colnames"], [1, 2, 1, "", "get_data_params_for_gradient_dice"], [1, 2, 1, "", "get_data_type"], [1, 2, 1, "", "get_decimal_precisions"], [1, 2, 1, "", "get_decoded_data"], [1, 2, 1, "", "get_encoded_categorical_feature_indexes"], [1, 2, 1, "", "get_features_range"], [1, 2, 1, "", "get_indexes_of_features_to_vary"], [1, 2, 1, "", "get_inverse_ohe_min_max_normalized_data"], [1, 2, 1, "", "get_mads"], [1, 2, 1, "", "get_minx_maxx"], [1, 2, 1, "", "get_ohe_min_max_normalized_data"], [1, 2, 1, "", "get_quantiles_from_training_data"], [1, 2, 1, "", "get_valid_feature_range"], [1, 2, 1, "", "get_valid_mads"], [1, 2, 1, "", "normalize_data"], [1, 2, 1, "", "one_hot_encode_data"], [1, 2, 1, "", "prepare_df_for_ohe_encoding"], [1, 2, 1, "", "prepare_query_instance"]], "dice_ml.dice": [[0, 1, 1, "", "Dice"], [0, 5, 1, "", "decide"]], "dice_ml.dice.Dice": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.diverse_counterfactuals": [[0, 1, 1, "", "CounterfactualExamples"], [0, 5, 1, "", "json_converter"]], "dice_ml.diverse_counterfactuals.CounterfactualExamples": [[0, 2, 1, "", "display_df"], [0, 2, 1, "", "from_json"], [0, 2, 1, "", "print_list"], [0, 2, 1, "", "to_json"], [0, 2, 1, "", "visualize_as_dataframe"], [0, 2, 1, "", "visualize_as_list"]], "dice_ml.explainer_interfaces": [[2, 0, 0, "-", "dice_KD"], [2, 0, 0, "-", "dice_genetic"], [2, 0, 0, "-", "dice_pytorch"], [2, 0, 0, "-", "dice_random"], [2, 0, 0, "-", "dice_tensorflow1"], [2, 0, 0, "-", "dice_tensorflow2"], [2, 0, 0, "-", "explainer_base"], [2, 0, 0, "-", "feasible_base_vae"], [2, 0, 0, "-", "feasible_model_approx"]], "dice_ml.explainer_interfaces.dice_KD": [[2, 1, 1, "", "DiceKD"]], "dice_ml.explainer_interfaces.dice_KD.DiceKD": [[2, 2, 1, "", "do_sparsity_check"], [2, 2, 1, "", "duplicates"], [2, 2, 1, "", "find_counterfactuals"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "vary_valid"]], "dice_ml.explainer_interfaces.dice_genetic": [[2, 1, 1, "", "DiceGenetic"]], "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic": [[2, 2, 1, "", "compute_loss"], [2, 2, 1, "", "compute_proximity_loss"], [2, 2, 1, "", "compute_sparsity_loss"], [2, 2, 1, "", "compute_yloss"], [2, 2, 1, "", "do_KD_init"], [2, 2, 1, "", "do_cf_initializations"], [2, 2, 1, "", "do_loss_initializations"], [2, 2, 1, "", "do_param_initializations"], [2, 2, 1, "", "do_random_init"], [2, 2, 1, "", "find_counterfactuals"], [2, 2, 1, "", "get_valid_feature_range"], [2, 2, 1, "", "label_decode"], [2, 2, 1, "", "label_decode_cfs"], [2, 2, 1, "", "label_encode"], [2, 2, 1, "", "mate"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "predict_fn_scores"], [2, 2, 1, "", "update_hyperparameters"]], "dice_ml.explainer_interfaces.dice_pytorch": [[2, 1, 1, "", "DicePyTorch"]], "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch": [[2, 2, 1, "", "compute_dist"], [2, 2, 1, "", "compute_diversity_loss"], [2, 2, 1, "", "compute_loss"], [2, 2, 1, "", "compute_proximity_loss"], [2, 2, 1, "", "compute_regularization_loss"], [2, 2, 1, "", "compute_yloss"], [2, 2, 1, "", "do_cf_initializations"], [2, 2, 1, "", "do_loss_initializations"], [2, 2, 1, "", "do_optimizer_initializations"], [2, 2, 1, "", "dpp_style"], [2, 2, 1, "", "find_counterfactuals"], [2, 2, 1, "", "get_model_output"], [2, 2, 1, "", "initialize_CFs"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "predict_fn_for_sparsity"], [2, 2, 1, "", "round_off_cfs"], [2, 2, 1, "", "stop_loop"], [2, 2, 1, "", "update_hyperparameters"]], "dice_ml.explainer_interfaces.dice_random": [[2, 1, 1, "", "DiceRandom"]], "dice_ml.explainer_interfaces.dice_random.DiceRandom": [[2, 2, 1, "", "get_continuous_samples"], [2, 2, 1, "", "get_samples"]], "dice_ml.explainer_interfaces.dice_tensorflow1": [[2, 1, 1, "", "DiceTensorFlow1"]], "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1": [[2, 2, 1, "", "compute_dist"], [2, 2, 1, "", "compute_diversity_loss"], [2, 2, 1, "", "compute_proximity_loss"], [2, 2, 1, "", "compute_regularization_loss"], [2, 2, 1, "", "compute_yloss"], [2, 2, 1, "", "do_cf_initializations"], [2, 2, 1, "", "do_loss_initializations"], [2, 2, 1, "", "do_optimizer_initializations"], [2, 2, 1, "", "dpp_style"], [2, 2, 1, "", "find_counterfactuals"], [2, 2, 1, "", "generate_counterfactuals"], [2, 2, 1, "", "initialize_CFs"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "predict_fn_for_sparsity"], [2, 2, 1, "", "round_off_cfs"], [2, 2, 1, "", "scipy_optimizers"], [2, 2, 1, "", "stop_loop"], [2, 2, 1, "", "tensorflow_optimizers"], [2, 2, 1, "", "update_hyperparameters"]], "dice_ml.explainer_interfaces.dice_tensorflow2": [[2, 1, 1, "", "DiceTensorFlow2"]], "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2": [[2, 2, 1, "", "compute_dist"], [2, 2, 1, "", "compute_diversity_loss"], [2, 2, 1, "", "compute_loss"], [2, 2, 1, "", "compute_proximity_loss"], [2, 2, 1, "", "compute_regularization_loss"], [2, 2, 1, "", "compute_yloss"], [2, 2, 1, "", "do_cf_initializations"], [2, 2, 1, "", "do_loss_initializations"], [2, 2, 1, "", "do_optimizer_initializations"], [2, 2, 1, "", "dpp_style"], [2, 2, 1, "", "find_counterfactuals"], [2, 2, 1, "", "generate_counterfactuals"], [2, 2, 1, "", "initialize_CFs"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "predict_fn_for_sparsity"], [2, 2, 1, "", "round_off_cfs"], [2, 2, 1, "", "stop_loop"], [2, 2, 1, "", "update_hyperparameters"]], "dice_ml.explainer_interfaces.explainer_base": [[2, 1, 1, "", "ExplainerBase"]], "dice_ml.explainer_interfaces.explainer_base.ExplainerBase": [[2, 2, 1, "", "build_KD_tree"], [2, 2, 1, "", "check_permitted_range"], [2, 2, 1, "", "check_query_instance_validity"], [2, 2, 1, "", "decide_cf_validity"], [2, 2, 1, "", "deserialize_explainer"], [2, 2, 1, "", "do_binary_search"], [2, 2, 1, "", "do_linear_search"], [2, 2, 1, "", "do_posthoc_sparsity_enhancement"], [2, 2, 1, "", "feature_importance"], [2, 2, 1, "", "generate_counterfactuals"], [2, 2, 1, "", "get_model_output_from_scores"], [2, 2, 1, "", "global_feature_importance"], [2, 2, 1, "", "infer_target_cfs_class"], [2, 2, 1, "", "infer_target_cfs_range"], [2, 2, 1, "", "is_cf_valid"], [2, 2, 1, "", "local_feature_importance"], [2, 2, 1, "", "misc_init"], [2, 2, 1, "", "predict_fn"], [2, 2, 1, "", "predict_fn_for_sparsity"], [2, 2, 1, "", "round_to_precision"], [2, 2, 1, "", "serialize_explainer"], [2, 2, 1, "", "setup"], [2, 2, 1, "", "sigmoid"]], "dice_ml.explainer_interfaces.feasible_base_vae": [[2, 1, 1, "", "FeasibleBaseVAE"]], "dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE": [[2, 2, 1, "", "compute_loss"], [2, 2, 1, "", "generate_counterfactuals"], [2, 2, 1, "", "train"]], "dice_ml.explainer_interfaces.feasible_model_approx": [[2, 1, 1, "", "FeasibleModelApprox"]], "dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox": [[2, 2, 1, "", "train"]], "dice_ml.model": [[0, 1, 1, "", "Model"], [0, 5, 1, "", "decide"]], "dice_ml.model.Model": [[0, 2, 1, "", "decide_implementation_type"]], "dice_ml.model_interfaces": [[3, 0, 0, "-", "base_model"], [3, 0, 0, "-", "keras_tensorflow_model"], [3, 0, 0, "-", "pytorch_model"]], "dice_ml.model_interfaces.base_model": [[3, 1, 1, "", "BaseModel"]], "dice_ml.model_interfaces.base_model.BaseModel": [[3, 2, 1, "", "get_gradient"], [3, 2, 1, "", "get_num_output_nodes"], [3, 2, 1, "", "get_num_output_nodes2"], [3, 2, 1, "", "get_output"], [3, 2, 1, "", "load_model"]], "dice_ml.model_interfaces.keras_tensorflow_model": [[3, 1, 1, "", "KerasTensorFlowModel"]], "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel": [[3, 2, 1, "", "get_gradient"], [3, 2, 1, "", "get_num_output_nodes"], [3, 2, 1, "", "get_output"], [3, 2, 1, "", "load_model"]], "dice_ml.model_interfaces.pytorch_model": [[3, 1, 1, "", "PyTorchModel"]], "dice_ml.model_interfaces.pytorch_model.PyTorchModel": [[3, 2, 1, "", "get_gradient"], [3, 2, 1, "", "get_num_output_nodes"], [3, 2, 1, "", "get_output"], [3, 2, 1, "", "load_model"], [3, 2, 1, "", "set_eval_mode"]], "dice_ml.utils": [[5, 0, 0, "-", "exception"], [5, 0, 0, "-", "helpers"], [5, 0, 0, "-", "neuralnetworks"], [6, 0, 0, "-", "sample_architecture"], [5, 0, 0, "-", "serialize"]], "dice_ml.utils.exception": [[5, 6, 1, "", "SystemException"], [5, 6, 1, "", "UserConfigValidationException"]], "dice_ml.utils.helpers": [[5, 1, 1, "", "DataTransfomer"], [5, 5, 1, "", "get_adult_data_info"], [5, 5, 1, "", "get_adult_income_modelpath"], [5, 5, 1, "", "get_base_gen_cf_initialization"], [5, 5, 1, "", "get_custom_dataset_modelpath_pipeline"], [5, 5, 1, "", "get_custom_dataset_modelpath_pipeline_binary"], [5, 5, 1, "", "get_custom_dataset_modelpath_pipeline_multiclass"], [5, 5, 1, "", "get_custom_dataset_modelpath_pipeline_regression"], [5, 5, 1, "", "get_custom_vars_dataset_modelpath_pipeline"], [5, 5, 1, "", "inverse_ohe_min_max_transformation"], [5, 5, 1, "", "load_adult_income_dataset"], [5, 5, 1, "", "load_custom_testing_dataset"], [5, 5, 1, "", "load_custom_testing_dataset_binary"], [5, 5, 1, "", "load_custom_testing_dataset_multiclass"], [5, 5, 1, "", "load_custom_testing_dataset_regression"], [5, 5, 1, "", "load_min_max_equal_dataset"], [5, 5, 1, "", "load_outcome_not_last_column_dataset"], [5, 5, 1, "", "ohe_min_max_transformation"], [5, 5, 1, "", "save_adult_income_model"]], "dice_ml.utils.helpers.DataTransfomer": [[5, 2, 1, "", "feed_data_params"], [5, 2, 1, "", "initialize_transform_func"], [5, 2, 1, "", "inverse_transform"], [5, 2, 1, "", "transform"]], "dice_ml.utils.neuralnetworks": [[5, 1, 1, "", "FFNetwork"]], "dice_ml.utils.neuralnetworks.FFNetwork": [[5, 2, 1, "", "forward"]], "dice_ml.utils.sample_architecture": [[6, 0, 0, "-", "vae_model"]], "dice_ml.utils.sample_architecture.vae_model": [[6, 1, 1, "", "AutoEncoder"], [6, 1, 1, "", "CF_VAE"]], "dice_ml.utils.sample_architecture.vae_model.AutoEncoder": [[6, 2, 1, "", "decoder"], [6, 2, 1, "", "encoder"], [6, 2, 1, "", "forward"], [6, 2, 1, "", "normal_likelihood"], [6, 2, 1, "", "sample_latent_code"], [6, 3, 1, "", "training"]], "dice_ml.utils.sample_architecture.vae_model.CF_VAE": [[6, 2, 1, "", "compute_elbo"], [6, 2, 1, "", "decoder"], [6, 2, 1, "", "encoder"], [6, 2, 1, "", "forward"], [6, 2, 1, "", "normal_likelihood"], [6, 2, 1, "", "sample_latent_code"], [6, 3, 1, "", "training"]], "dice_ml.utils.serialize": [[5, 1, 1, "", "DummyDataInterface"]], "dice_ml.utils.serialize.DummyDataInterface": [[5, 2, 1, "", "to_json"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:method", "3": "py:attribute", "4": "py:property", "5": "py:function", "6": "py:exception"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "method", "Python method"], "3": ["py", "attribute", "Python attribute"], "4": ["py", "property", "Python property"], "5": ["py", "function", "Python function"], "6": ["py", "exception", "Python exception"]}, "titleterms": {"dice_ml": [0, 1, 2, 3, 4, 5, 6, 8], "packag": [0, 1, 2, 3, 4, 5, 6, 7], "subpackag": [0, 5], "submodul": [0, 1, 2, 3, 5, 6], "constant": 0, "modul": [0, 1, 2, 3, 4, 5, 6], "counterfactual_explan": 0, "data": [0, 10, 16], "dice": [0, 7, 10, 11, 18], "diverse_counterfactu": 0, "model": [0, 9, 10, 11, 12, 13, 14, 15, 16], "content": [0, 1, 2, 3, 4, 5, 6], "data_interfac": 1, "base_data_interfac": 1, "private_data_interfac": 1, "public_data_interfac": 1, "explainer_interfac": 2, "dice_kd": 2, "dice_genet": 2, "dice_pytorch": 2, "dice_random": 2, "dice_tensorflow1": 2, "dice_tensorflow2": 2, "explainer_bas": 2, "feasible_base_va": 2, "feasible_model_approx": 2, "model_interfac": 3, "base_model": 3, "keras_tensorflow_model": 3, "pytorch_model": 3, "schema": 4, "util": [5, 6], "except": 5, "helper": 5, "neuralnetwork": 5, "serial": 5, "sample_architectur": 6, "vae_model": 6, "divers": [7, 13, 15, 16, 18], "counterfactu": [7, 9, 10, 11, 12, 13, 14, 15, 16, 18], "explan": [7, 9, 11, 12, 13, 15, 16, 18], "ml": [7, 9, 10, 11, 12, 13, 15, 18], "instal": [7, 18], "get": [7, 18], "start": [7, 18], "support": [7, 18], "method": [7, 9, 18], "gener": [7, 9, 11, 12, 13, 14, 15, 16, 18], "us": [7, 10, 11, 12, 18], "case": [7, 18], "feasibl": [7, 12, 18], "The": [7, 18], "promis": [7, 18], "roadmap": [7, 18], "cite": [7, 18], "contribut": [7, 18], "notebook": [7, 17], "indic": 7, "tabl": 7, "benchmark": 9, "differ": 9, "cf": 9, "load": [9, 10, 11, 12, 13, 15], "dataset": [9, 11, 12, 13, 15], "train": [9, 11, 13, 16], "initi": 9, "estim": 10, "local": [10, 11], "global": [10, 11], "featur": [10, 11, 13, 15], "import": [10, 11], "score": [10, 11], "preliminari": [10, 11], "convert": 10, "output": 10, "json": 10, "object": 10, "quick": 11, "introduct": 11, "over": 11, "adult": 11, "exampl": 11, "attribut": 11, "work": 11, "deep": [11, 16], "learn": [11, 16], "tensorflow": 11, "pytorch": 11, "explain": [11, 12, 16], "more": 11, "resourc": 11, "what": 11, "": 11, "next": 11, "vae": 12, "ad": 12, "constraint": 12, "modelapprox": 12, "initil": 12, "feasiblemodelapprox": 12, "ani": 13, "1": [13, 15], "independ": 13, "random": 13, "sampl": 13, "custom": [13, 15], "select": 13, "vari": 13, "choos": 13, "rang": 13, "2": [13, 15], "genet": 13, "algorithm": 13, "3": [13, 15], "queri": 13, "kd": 13, "tree": 13, "multi": 14, "class": 14, "classif": 14, "regress": 14, "multiclass": 14, "advanc": 15, "option": 15, "chang": 15, "weight": 15, "trade": 15, "off": 15, "between": 15, "proxim": 15, "goal": 15, "without": 16, "access": 16, "defin": 16, "meta": 16, "pre": 16, "sklearn": 16}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx.ext.todo": 2, "nbsphinx": 4, "sphinx": 57}, "alltitles": {"dice_ml package": [[0, "dice-ml-package"]], "Subpackages": [[0, "subpackages"], [5, "subpackages"]], "Submodules": [[0, "submodules"], [1, "submodules"], [2, "submodules"], [3, "submodules"], [5, "submodules"], [6, "submodules"]], "dice_ml.constants module": [[0, "module-dice_ml.constants"]], "dice_ml.counterfactual_explanations module": [[0, "module-dice_ml.counterfactual_explanations"]], "dice_ml.data module": [[0, "module-dice_ml.data"]], "dice_ml.dice module": [[0, "module-dice_ml.dice"]], "dice_ml.diverse_counterfactuals module": [[0, "module-dice_ml.diverse_counterfactuals"]], "dice_ml.model module": [[0, "module-dice_ml.model"]], "Module contents": [[0, "module-dice_ml"], [1, "module-dice_ml.data_interfaces"], [2, "module-dice_ml.explainer_interfaces"], [3, "module-dice_ml.model_interfaces"], [4, "module-dice_ml.schema"], [5, "module-dice_ml.utils"], [6, "module-dice_ml.utils.sample_architecture"]], "dice_ml.data_interfaces package": [[1, "dice-ml-data-interfaces-package"]], "dice_ml.data_interfaces.base_data_interface module": [[1, "module-dice_ml.data_interfaces.base_data_interface"]], "dice_ml.data_interfaces.private_data_interface module": [[1, "module-dice_ml.data_interfaces.private_data_interface"]], "dice_ml.data_interfaces.public_data_interface module": [[1, "module-dice_ml.data_interfaces.public_data_interface"]], "dice_ml.explainer_interfaces package": [[2, "dice-ml-explainer-interfaces-package"]], "dice_ml.explainer_interfaces.dice_KD module": [[2, "module-dice_ml.explainer_interfaces.dice_KD"]], "dice_ml.explainer_interfaces.dice_genetic module": [[2, "module-dice_ml.explainer_interfaces.dice_genetic"]], "dice_ml.explainer_interfaces.dice_pytorch module": [[2, "module-dice_ml.explainer_interfaces.dice_pytorch"]], "dice_ml.explainer_interfaces.dice_random module": [[2, "module-dice_ml.explainer_interfaces.dice_random"]], "dice_ml.explainer_interfaces.dice_tensorflow1 module": [[2, "module-dice_ml.explainer_interfaces.dice_tensorflow1"]], "dice_ml.explainer_interfaces.dice_tensorflow2 module": [[2, "module-dice_ml.explainer_interfaces.dice_tensorflow2"]], "dice_ml.explainer_interfaces.explainer_base module": [[2, "module-dice_ml.explainer_interfaces.explainer_base"]], "dice_ml.explainer_interfaces.feasible_base_vae module": [[2, "module-dice_ml.explainer_interfaces.feasible_base_vae"]], "dice_ml.explainer_interfaces.feasible_model_approx module": [[2, "module-dice_ml.explainer_interfaces.feasible_model_approx"]], "dice_ml.model_interfaces package": [[3, "dice-ml-model-interfaces-package"]], "dice_ml.model_interfaces.base_model module": [[3, "module-dice_ml.model_interfaces.base_model"]], "dice_ml.model_interfaces.keras_tensorflow_model module": [[3, "module-dice_ml.model_interfaces.keras_tensorflow_model"]], "dice_ml.model_interfaces.pytorch_model module": [[3, "module-dice_ml.model_interfaces.pytorch_model"]], "dice_ml.schema package": [[4, "dice-ml-schema-package"]], "dice_ml.utils package": [[5, "dice-ml-utils-package"]], "dice_ml.utils.exception module": [[5, "module-dice_ml.utils.exception"]], "dice_ml.utils.helpers module": [[5, "module-dice_ml.utils.helpers"]], "dice_ml.utils.neuralnetworks module": [[5, "module-dice_ml.utils.neuralnetworks"]], "dice_ml.utils.serialize module": [[5, "module-dice_ml.utils.serialize"]], "dice_ml.utils.sample_architecture package": [[6, "dice-ml-utils-sample-architecture-package"]], "dice_ml.utils.sample_architecture.vae_model module": [[6, "module-dice_ml.utils.sample_architecture.vae_model"]], "Diverse Counterfactual Explanations (DiCE) for ML": [[7, "diverse-counterfactual-explanations-dice-for-ml"], [18, "diverse-counterfactual-explanations-dice-for-ml"]], "Installing DICE": [[7, "installing-dice"], [18, "installing-dice"]], "Getting started with DiCE": [[7, "getting-started-with-dice"], [18, "getting-started-with-dice"]], "Supported methods for generating counterfactuals": [[7, "supported-methods-for-generating-counterfactuals"], [18, "supported-methods-for-generating-counterfactuals"]], "Supported use-cases": [[7, "supported-use-cases"], [18, "supported-use-cases"]], "Feasibility of counterfactual explanations": [[7, "feasibility-of-counterfactual-explanations"], [18, "feasibility-of-counterfactual-explanations"]], "The promise of counterfactual explanations": [[7, "the-promise-of-counterfactual-explanations"], [18, "the-promise-of-counterfactual-explanations"]], "Roadmap": [[7, "roadmap"], [18, "roadmap"]], "Citing": [[7, "citing"], [18, "citing"]], "Contributing": [[7, "contributing"], [18, "contributing"]], "Getting Started:": [[7, null]], "Notebooks:": [[7, null], [17, null]], "Package:": [[7, null]], "Indices and tables": [[7, "indices-and-tables"]], "dice_ml": [[8, "dice-ml"]], "Benchmarking different CF explanation methods": [[9, "Benchmarking-different-CF-explanation-methods"]], "Loading dataset": [[9, "Loading-dataset"], [12, "Loading-dataset"], [13, "Loading-dataset"], [15, "Loading-dataset"]], "Training the ML model": [[9, "Training-the-ML-model"]], "Initialize counterfactual generation methods": [[9, "Initialize-counterfactual-generation-methods"]], "Generate Counterfactuals": [[9, "Generate-Counterfactuals"]], "Estimating local and global feature importance scores using DiCE": [[10, "Estimating-local-and-global-feature-importance-scores-using-DiCE"]], "Preliminaries: Loading the data and ML model": [[10, "Preliminaries:-Loading-the-data-and-ML-model"]], "Local feature importance": [[10, "Local-feature-importance"]], "Global importance": [[10, "Global-importance"]], "Convert the counterfactual output to json": [[10, "Convert-the-counterfactual-output-to-json"]], "Convert the json output to a counterfactual object": [[10, "Convert-the-json-output-to-a-counterfactual-object"]], "Quick introduction to generating counterfactual explanations using DiCE": [[11, "Quick-introduction-to-generating-counterfactual-explanations-using-DiCE"]], "Preliminaries: Loading a dataset and a ML model trained over it": [[11, "Preliminaries:-Loading-a-dataset-and-a-ML-model-trained-over-it"]], "Loading the Adult dataset": [[11, "Loading-the-Adult-dataset"]], "Loading the ML model": [[11, "Loading-the-ML-model"], [12, "Loading-the-ML-model"]], "Generating counterfactual examples using DiCE": [[11, "Generating-counterfactual-examples-using-DiCE"]], "Generating feature attributions (local and global) using DiCE": [[11, "Generating-feature-attributions-(local-and-global)-using-DiCE"]], "Local feature importance scores": [[11, "Local-feature-importance-scores"]], "Global feature importance scores": [[11, "Global-feature-importance-scores"]], "Working with deep learning models (TensorFlow and PyTorch)": [[11, "Working-with-deep-learning-models-(TensorFlow-and-PyTorch)"]], "Explaining a Tensorflow model": [[11, "Explaining-a-Tensorflow-model"]], "Explaining a Pytorch model": [[11, "Explaining-a-Pytorch-model"]], "More resources: What\u2019s next?": [[11, "More-resources:-What\u2019s-next?"]], "Generate feasible counterfactual explanations using a VAE": [[12, "Generate-feasible-counterfactual-explanations-using-a-VAE"]], "Generate counterfactuals using a VAE model": [[12, "Generate-counterfactuals-using-a-VAE-model"]], "Adding feasibility constraints": [[12, "Adding-feasibility-constraints"]], "ModelApprox": [[12, "ModelApprox"]], "Initilize the Model and Explainer for FeasibleModelApprox": [[12, "Initilize-the-Model-and-Explainer-for-FeasibleModelApprox"]], "Generating counterfactual explanations with any ML model": [[13, "Generating-counterfactual-explanations-with-any-ML-model"]], "1. Independent random sampling of features": [[13, "1.-Independent-random-sampling-of-features"]], "Training a custom ML model": [[13, "Training-a-custom-ML-model"], [13, "id1"], [13, "id3"]], "Generate diverse counterfactuals": [[13, "Generate-diverse-counterfactuals"], [13, "id2"], [13, "id4"], [15, "Generate-diverse-counterfactuals"], [16, "Generate-diverse-counterfactuals"], [16, "id1"]], "Selecting the features to vary": [[13, "Selecting-the-features-to-vary"], [13, "id5"]], "Choosing feature ranges": [[13, "Choosing-feature-ranges"]], "2. Genetic Algorithm": [[13, "2.-Genetic-Algorithm"]], "3. Querying a KD Tree": [[13, "3.-Querying-a-KD-Tree"]], "Selecting the feature ranges": [[13, "Selecting-the-feature-ranges"]], "Generating counterfactuals for multi-class classification and regression models": [[14, "Generating-counterfactuals-for-multi-class-classification-and-regression-models"]], "Multiclass Classification": [[14, "Multiclass-Classification"]], "Regression": [[14, "Regression"]], "Advanced options to customize Counterfactual Explanations": [[15, "Advanced-options-to-customize-Counterfactual-Explanations"]], "1. Loading a custom ML model": [[15, "1.-Loading-a-custom-ML-model"]], "2. Changing feature weights": [[15, "2.-Changing-feature-weights"]], "3. Trading off between proximity and diversity goals": [[15, "3.-Trading-off-between-proximity-and-diversity-goals"]], "Generating counterfactual explanations without access to training data": [[16, "Generating-counterfactual-explanations-without-access-to-training-data"]], "Defining meta data": [[16, "Defining-meta-data"]], "Explaining pre-trained sklearn models": [[16, "Explaining-pre-trained-sklearn-models"]], "Explaining pre-trained deep learning models": [[16, "Explaining-pre-trained-deep-learning-models"]]}, "indexentries": {"all (dice_ml.constants.backendtypes attribute)": [[0, "dice_ml.constants.BackEndTypes.ALL"]], "all (dice_ml.constants.modeltypes attribute)": [[0, "dice_ml.constants.ModelTypes.ALL"]], "backendtypes (class in dice_ml.constants)": [[0, "dice_ml.constants.BackEndTypes"]], "classifier (dice_ml.constants.modeltypes attribute)": [[0, "dice_ml.constants.ModelTypes.Classifier"]], "counterfactualexamples (class in dice_ml.diverse_counterfactuals)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples"]], "counterfactualexplanations (class in dice_ml.counterfactual_explanations)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations"]], "data (class in dice_ml)": [[0, "dice_ml.Data"]], "data (class in dice_ml.data)": [[0, "dice_ml.data.Data"]], "dice (class in dice_ml)": [[0, "dice_ml.Dice"]], "dice (class in dice_ml.dice)": [[0, "dice_ml.dice.Dice"]], "genetic (dice_ml.constants.samplingstrategy attribute)": [[0, "dice_ml.constants.SamplingStrategy.Genetic"]], "gradient (dice_ml.constants.samplingstrategy attribute)": [[0, "dice_ml.constants.SamplingStrategy.Gradient"]], "kdtree (dice_ml.constants.samplingstrategy attribute)": [[0, "dice_ml.constants.SamplingStrategy.KdTree"]], "model (class in dice_ml)": [[0, "dice_ml.Model"]], "model (class in dice_ml.model)": [[0, "dice_ml.model.Model"]], "modeltypes (class in dice_ml.constants)": [[0, "dice_ml.constants.ModelTypes"]], "pytorch (dice_ml.constants.backendtypes attribute)": [[0, "dice_ml.constants.BackEndTypes.Pytorch"]], "random (dice_ml.constants.samplingstrategy attribute)": [[0, "dice_ml.constants.SamplingStrategy.Random"]], "regressor (dice_ml.constants.modeltypes attribute)": [[0, "dice_ml.constants.ModelTypes.Regressor"]], "samplingstrategy (class in dice_ml.constants)": [[0, "dice_ml.constants.SamplingStrategy"]], "sklearn (dice_ml.constants.backendtypes attribute)": [[0, "dice_ml.constants.BackEndTypes.Sklearn"]], "tensorflow1 (dice_ml.constants.backendtypes attribute)": [[0, "dice_ml.constants.BackEndTypes.Tensorflow1"]], "tensorflow2 (dice_ml.constants.backendtypes attribute)": [[0, "dice_ml.constants.BackEndTypes.Tensorflow2"]], "cf_examples_list (dice_ml.counterfactual_explanations.counterfactualexplanations property)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.cf_examples_list"]], "decide() (in module dice_ml.data)": [[0, "dice_ml.data.decide"]], "decide() (in module dice_ml.dice)": [[0, "dice_ml.dice.decide"]], "decide() (in module dice_ml.model)": [[0, "dice_ml.model.decide"]], "decide_implementation_type() (dice_ml.data method)": [[0, "dice_ml.Data.decide_implementation_type"]], "decide_implementation_type() (dice_ml.dice method)": [[0, "dice_ml.Dice.decide_implementation_type"]], "decide_implementation_type() (dice_ml.model method)": [[0, "dice_ml.Model.decide_implementation_type"]], "decide_implementation_type() (dice_ml.data.data method)": [[0, "dice_ml.data.Data.decide_implementation_type"]], "decide_implementation_type() (dice_ml.dice.dice method)": [[0, "dice_ml.dice.Dice.decide_implementation_type"]], "decide_implementation_type() (dice_ml.model.model method)": [[0, "dice_ml.model.Model.decide_implementation_type"]], "dice_ml": [[0, "module-dice_ml"]], "dice_ml.constants": [[0, "module-dice_ml.constants"]], "dice_ml.counterfactual_explanations": [[0, "module-dice_ml.counterfactual_explanations"]], "dice_ml.data": [[0, "module-dice_ml.data"]], "dice_ml.dice": [[0, "module-dice_ml.dice"]], "dice_ml.diverse_counterfactuals": [[0, "module-dice_ml.diverse_counterfactuals"]], "dice_ml.model": [[0, "module-dice_ml.model"]], "display_df() (dice_ml.diverse_counterfactuals.counterfactualexamples method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.display_df"]], "from_json() (dice_ml.counterfactual_explanations.counterfactualexplanations static method)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.from_json"]], "from_json() (dice_ml.diverse_counterfactuals.counterfactualexamples static method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.from_json"]], "json_converter() (in module dice_ml.diverse_counterfactuals)": [[0, "dice_ml.diverse_counterfactuals.json_converter"]], "local_importance (dice_ml.counterfactual_explanations.counterfactualexplanations property)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.local_importance"]], "metadata (dice_ml.counterfactual_explanations.counterfactualexplanations property)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.metadata"]], "module": [[0, "module-dice_ml"], [0, "module-dice_ml.constants"], [0, "module-dice_ml.counterfactual_explanations"], [0, "module-dice_ml.data"], [0, "module-dice_ml.dice"], [0, "module-dice_ml.diverse_counterfactuals"], [0, "module-dice_ml.model"], [1, "module-dice_ml.data_interfaces"], [1, "module-dice_ml.data_interfaces.base_data_interface"], [1, "module-dice_ml.data_interfaces.private_data_interface"], [1, "module-dice_ml.data_interfaces.public_data_interface"], [2, "module-dice_ml.explainer_interfaces"], [2, "module-dice_ml.explainer_interfaces.dice_KD"], [2, "module-dice_ml.explainer_interfaces.dice_genetic"], [2, "module-dice_ml.explainer_interfaces.dice_pytorch"], [2, "module-dice_ml.explainer_interfaces.dice_random"], [2, "module-dice_ml.explainer_interfaces.dice_tensorflow1"], [2, "module-dice_ml.explainer_interfaces.dice_tensorflow2"], [2, "module-dice_ml.explainer_interfaces.explainer_base"], [2, "module-dice_ml.explainer_interfaces.feasible_base_vae"], [2, "module-dice_ml.explainer_interfaces.feasible_model_approx"], [3, "module-dice_ml.model_interfaces"], [3, "module-dice_ml.model_interfaces.base_model"], [3, "module-dice_ml.model_interfaces.keras_tensorflow_model"], [3, "module-dice_ml.model_interfaces.pytorch_model"], [4, "module-dice_ml.schema"], [5, "module-dice_ml.utils"], [5, "module-dice_ml.utils.exception"], [5, "module-dice_ml.utils.helpers"], [5, "module-dice_ml.utils.neuralnetworks"], [5, "module-dice_ml.utils.serialize"], [6, "module-dice_ml.utils.sample_architecture"], [6, "module-dice_ml.utils.sample_architecture.vae_model"]], "print_list() (dice_ml.diverse_counterfactuals.counterfactualexamples method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.print_list"]], "summary_importance (dice_ml.counterfactual_explanations.counterfactualexplanations property)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.summary_importance"]], "to_json() (dice_ml.counterfactual_explanations.counterfactualexplanations method)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.to_json"]], "to_json() (dice_ml.diverse_counterfactuals.counterfactualexamples method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.to_json"]], "visualize_as_dataframe() (dice_ml.counterfactual_explanations.counterfactualexplanations method)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_dataframe"]], "visualize_as_dataframe() (dice_ml.diverse_counterfactuals.counterfactualexamples method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_dataframe"]], "visualize_as_list() (dice_ml.counterfactual_explanations.counterfactualexplanations method)": [[0, "dice_ml.counterfactual_explanations.CounterfactualExplanations.visualize_as_list"]], "visualize_as_list() (dice_ml.diverse_counterfactuals.counterfactualexamples method)": [[0, "dice_ml.diverse_counterfactuals.CounterfactualExamples.visualize_as_list"]], "privatedata (class in dice_ml.data_interfaces.private_data_interface)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData"]], "publicdata (class in dice_ml.data_interfaces.public_data_interface)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData"]], "create_ohe_params() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.create_ohe_params"]], "create_ohe_params() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.create_ohe_params"]], "de_normalize_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.de_normalize_data"]], "de_normalize_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.de_normalize_data"]], "dice_ml.data_interfaces": [[1, "module-dice_ml.data_interfaces"]], "dice_ml.data_interfaces.base_data_interface": [[1, "module-dice_ml.data_interfaces.base_data_interface"]], "dice_ml.data_interfaces.private_data_interface": [[1, "module-dice_ml.data_interfaces.private_data_interface"]], "dice_ml.data_interfaces.public_data_interface": [[1, "module-dice_ml.data_interfaces.public_data_interface"]], "fit_label_encoders() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.fit_label_encoders"]], "fit_label_encoders() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.fit_label_encoders"]], "from_dummies() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.from_dummies"]], "from_dummies() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.from_dummies"]], "from_label() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.from_label"]], "from_label() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.from_label"]], "get_all_dummy_colnames() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_all_dummy_colnames"]], "get_all_dummy_colnames() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_all_dummy_colnames"]], "get_data_params_for_gradient_dice() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_data_params_for_gradient_dice"]], "get_data_params_for_gradient_dice() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_data_params_for_gradient_dice"]], "get_data_type() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_data_type"]], "get_decimal_precisions() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_decimal_precisions"]], "get_decimal_precisions() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_decimal_precisions"]], "get_decoded_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_decoded_data"]], "get_decoded_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_decoded_data"]], "get_encoded_categorical_feature_indexes() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_encoded_categorical_feature_indexes"]], "get_encoded_categorical_feature_indexes() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_encoded_categorical_feature_indexes"]], "get_features_range() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_features_range"]], "get_features_range() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_features_range"]], "get_indexes_of_features_to_vary() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_indexes_of_features_to_vary"]], "get_indexes_of_features_to_vary() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_indexes_of_features_to_vary"]], "get_inverse_ohe_min_max_normalized_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_inverse_ohe_min_max_normalized_data"]], "get_inverse_ohe_min_max_normalized_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_inverse_ohe_min_max_normalized_data"]], "get_mads() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_mads"]], "get_mads() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_mads"]], "get_minx_maxx() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_minx_maxx"]], "get_minx_maxx() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_minx_maxx"]], "get_ohe_min_max_normalized_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_ohe_min_max_normalized_data"]], "get_ohe_min_max_normalized_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_ohe_min_max_normalized_data"]], "get_quantiles_from_training_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_quantiles_from_training_data"]], "get_valid_feature_range() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_feature_range"]], "get_valid_feature_range() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_feature_range"]], "get_valid_mads() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.get_valid_mads"]], "get_valid_mads() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.get_valid_mads"]], "normalize_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.normalize_data"]], "normalize_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.normalize_data"]], "one_hot_encode_data() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.one_hot_encode_data"]], "one_hot_encode_data() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.one_hot_encode_data"]], "prepare_df_for_ohe_encoding() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.prepare_df_for_ohe_encoding"]], "prepare_df_for_ohe_encoding() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.prepare_df_for_ohe_encoding"]], "prepare_query_instance() (dice_ml.data_interfaces.private_data_interface.privatedata method)": [[1, "dice_ml.data_interfaces.private_data_interface.PrivateData.prepare_query_instance"]], "prepare_query_instance() (dice_ml.data_interfaces.public_data_interface.publicdata method)": [[1, "dice_ml.data_interfaces.public_data_interface.PublicData.prepare_query_instance"]], "dicegenetic (class in dice_ml.explainer_interfaces.dice_genetic)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic"]], "dicekd (class in dice_ml.explainer_interfaces.dice_kd)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD"]], "dicepytorch (class in dice_ml.explainer_interfaces.dice_pytorch)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch"]], "dicerandom (class in dice_ml.explainer_interfaces.dice_random)": [[2, "dice_ml.explainer_interfaces.dice_random.DiceRandom"]], "dicetensorflow1 (class in dice_ml.explainer_interfaces.dice_tensorflow1)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1"]], "dicetensorflow2 (class in dice_ml.explainer_interfaces.dice_tensorflow2)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2"]], "explainerbase (class in dice_ml.explainer_interfaces.explainer_base)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase"]], "feasiblebasevae (class in dice_ml.explainer_interfaces.feasible_base_vae)": [[2, "dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE"]], "feasiblemodelapprox (class in dice_ml.explainer_interfaces.feasible_model_approx)": [[2, "dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox"]], "build_kd_tree() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.build_KD_tree"]], "check_permitted_range() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_permitted_range"]], "check_query_instance_validity() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.check_query_instance_validity"]], "compute_dist() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_dist"]], "compute_dist() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_dist"]], "compute_dist() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_dist"]], "compute_diversity_loss() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_diversity_loss"]], "compute_diversity_loss() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_diversity_loss"]], "compute_diversity_loss() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_diversity_loss"]], "compute_loss() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_loss"]], "compute_loss() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_loss"]], "compute_loss() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_loss"]], "compute_loss() (dice_ml.explainer_interfaces.feasible_base_vae.feasiblebasevae method)": [[2, "dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.compute_loss"]], "compute_proximity_loss() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_proximity_loss"]], "compute_proximity_loss() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_proximity_loss"]], "compute_proximity_loss() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_proximity_loss"]], "compute_proximity_loss() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_proximity_loss"]], "compute_regularization_loss() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_regularization_loss"]], "compute_regularization_loss() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_regularization_loss"]], "compute_regularization_loss() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_regularization_loss"]], "compute_sparsity_loss() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_sparsity_loss"]], "compute_yloss() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.compute_yloss"]], "compute_yloss() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.compute_yloss"]], "compute_yloss() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.compute_yloss"]], "compute_yloss() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.compute_yloss"]], "decide_cf_validity() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.decide_cf_validity"]], "deserialize_explainer() (dice_ml.explainer_interfaces.explainer_base.explainerbase static method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.deserialize_explainer"]], "dice_ml.explainer_interfaces": [[2, "module-dice_ml.explainer_interfaces"]], "dice_ml.explainer_interfaces.dice_kd": [[2, "module-dice_ml.explainer_interfaces.dice_KD"]], "dice_ml.explainer_interfaces.dice_genetic": [[2, "module-dice_ml.explainer_interfaces.dice_genetic"]], "dice_ml.explainer_interfaces.dice_pytorch": [[2, "module-dice_ml.explainer_interfaces.dice_pytorch"]], "dice_ml.explainer_interfaces.dice_random": [[2, "module-dice_ml.explainer_interfaces.dice_random"]], "dice_ml.explainer_interfaces.dice_tensorflow1": [[2, "module-dice_ml.explainer_interfaces.dice_tensorflow1"]], "dice_ml.explainer_interfaces.dice_tensorflow2": [[2, "module-dice_ml.explainer_interfaces.dice_tensorflow2"]], "dice_ml.explainer_interfaces.explainer_base": [[2, "module-dice_ml.explainer_interfaces.explainer_base"]], "dice_ml.explainer_interfaces.feasible_base_vae": [[2, "module-dice_ml.explainer_interfaces.feasible_base_vae"]], "dice_ml.explainer_interfaces.feasible_model_approx": [[2, "module-dice_ml.explainer_interfaces.feasible_model_approx"]], "do_kd_init() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_KD_init"]], "do_binary_search() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_binary_search"]], "do_cf_initializations() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_cf_initializations"]], "do_cf_initializations() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_cf_initializations"]], "do_cf_initializations() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_cf_initializations"]], "do_cf_initializations() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_cf_initializations"]], "do_linear_search() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_linear_search"]], "do_loss_initializations() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_loss_initializations"]], "do_loss_initializations() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_loss_initializations"]], "do_loss_initializations() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_loss_initializations"]], "do_loss_initializations() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_loss_initializations"]], "do_optimizer_initializations() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.do_optimizer_initializations"]], "do_optimizer_initializations() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.do_optimizer_initializations"]], "do_optimizer_initializations() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.do_optimizer_initializations"]], "do_param_initializations() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_param_initializations"]], "do_posthoc_sparsity_enhancement() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.do_posthoc_sparsity_enhancement"]], "do_random_init() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.do_random_init"]], "do_sparsity_check() (dice_ml.explainer_interfaces.dice_kd.dicekd method)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD.do_sparsity_check"]], "dpp_style() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.dpp_style"]], "dpp_style() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.dpp_style"]], "dpp_style() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.dpp_style"]], "duplicates() (dice_ml.explainer_interfaces.dice_kd.dicekd method)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD.duplicates"]], "feature_importance() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.feature_importance"]], "find_counterfactuals() (dice_ml.explainer_interfaces.dice_kd.dicekd method)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD.find_counterfactuals"]], "find_counterfactuals() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.find_counterfactuals"]], "find_counterfactuals() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.find_counterfactuals"]], "find_counterfactuals() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.find_counterfactuals"]], "find_counterfactuals() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.find_counterfactuals"]], "generate_counterfactuals() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.generate_counterfactuals"]], "generate_counterfactuals() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.generate_counterfactuals"]], "generate_counterfactuals() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.generate_counterfactuals"]], "generate_counterfactuals() (dice_ml.explainer_interfaces.feasible_base_vae.feasiblebasevae method)": [[2, "dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.generate_counterfactuals"]], "get_continuous_samples() (dice_ml.explainer_interfaces.dice_random.dicerandom method)": [[2, "dice_ml.explainer_interfaces.dice_random.DiceRandom.get_continuous_samples"]], "get_model_output() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.get_model_output"]], "get_model_output_from_scores() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.get_model_output_from_scores"]], "get_samples() (dice_ml.explainer_interfaces.dice_random.dicerandom method)": [[2, "dice_ml.explainer_interfaces.dice_random.DiceRandom.get_samples"]], "get_valid_feature_range() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.get_valid_feature_range"]], "global_feature_importance() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.global_feature_importance"]], "infer_target_cfs_class() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.infer_target_cfs_class"]], "infer_target_cfs_range() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.infer_target_cfs_range"]], "initialize_cfs() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.initialize_CFs"]], "initialize_cfs() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.initialize_CFs"]], "initialize_cfs() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.initialize_CFs"]], "is_cf_valid() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.is_cf_valid"]], "label_decode() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_decode"]], "label_decode_cfs() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_decode_cfs"]], "label_encode() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.label_encode"]], "local_feature_importance() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.local_feature_importance"]], "mate() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.mate"]], "misc_init() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.misc_init"]], "predict_fn() (dice_ml.explainer_interfaces.dice_kd.dicekd method)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD.predict_fn"]], "predict_fn() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn"]], "predict_fn() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn"]], "predict_fn() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.predict_fn"]], "predict_fn() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.predict_fn"]], "predict_fn() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn"]], "predict_fn_for_sparsity() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.predict_fn_for_sparsity"]], "predict_fn_for_sparsity() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.predict_fn_for_sparsity"]], "predict_fn_for_sparsity() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.predict_fn_for_sparsity"]], "predict_fn_for_sparsity() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.predict_fn_for_sparsity"]], "predict_fn_scores() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.predict_fn_scores"]], "round_off_cfs() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.round_off_cfs"]], "round_off_cfs() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.round_off_cfs"]], "round_off_cfs() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.round_off_cfs"]], "round_to_precision() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.round_to_precision"]], "scipy_optimizers() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.scipy_optimizers"]], "serialize_explainer() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.serialize_explainer"]], "setup() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.setup"]], "sigmoid() (dice_ml.explainer_interfaces.explainer_base.explainerbase method)": [[2, "dice_ml.explainer_interfaces.explainer_base.ExplainerBase.sigmoid"]], "stop_loop() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.stop_loop"]], "stop_loop() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.stop_loop"]], "stop_loop() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.stop_loop"]], "tensorflow_optimizers() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.tensorflow_optimizers"]], "train() (dice_ml.explainer_interfaces.feasible_base_vae.feasiblebasevae method)": [[2, "dice_ml.explainer_interfaces.feasible_base_vae.FeasibleBaseVAE.train"]], "train() (dice_ml.explainer_interfaces.feasible_model_approx.feasiblemodelapprox method)": [[2, "dice_ml.explainer_interfaces.feasible_model_approx.FeasibleModelApprox.train"]], "update_hyperparameters() (dice_ml.explainer_interfaces.dice_genetic.dicegenetic method)": [[2, "dice_ml.explainer_interfaces.dice_genetic.DiceGenetic.update_hyperparameters"]], "update_hyperparameters() (dice_ml.explainer_interfaces.dice_pytorch.dicepytorch method)": [[2, "dice_ml.explainer_interfaces.dice_pytorch.DicePyTorch.update_hyperparameters"]], "update_hyperparameters() (dice_ml.explainer_interfaces.dice_tensorflow1.dicetensorflow1 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow1.DiceTensorFlow1.update_hyperparameters"]], "update_hyperparameters() (dice_ml.explainer_interfaces.dice_tensorflow2.dicetensorflow2 method)": [[2, "dice_ml.explainer_interfaces.dice_tensorflow2.DiceTensorFlow2.update_hyperparameters"]], "vary_valid() (dice_ml.explainer_interfaces.dice_kd.dicekd method)": [[2, "dice_ml.explainer_interfaces.dice_KD.DiceKD.vary_valid"]], "basemodel (class in dice_ml.model_interfaces.base_model)": [[3, "dice_ml.model_interfaces.base_model.BaseModel"]], "kerastensorflowmodel (class in dice_ml.model_interfaces.keras_tensorflow_model)": [[3, "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel"]], "pytorchmodel (class in dice_ml.model_interfaces.pytorch_model)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel"]], "dice_ml.model_interfaces": [[3, "module-dice_ml.model_interfaces"]], "dice_ml.model_interfaces.base_model": [[3, "module-dice_ml.model_interfaces.base_model"]], "dice_ml.model_interfaces.keras_tensorflow_model": [[3, "module-dice_ml.model_interfaces.keras_tensorflow_model"]], "dice_ml.model_interfaces.pytorch_model": [[3, "module-dice_ml.model_interfaces.pytorch_model"]], "get_gradient() (dice_ml.model_interfaces.base_model.basemodel method)": [[3, "dice_ml.model_interfaces.base_model.BaseModel.get_gradient"]], "get_gradient() (dice_ml.model_interfaces.keras_tensorflow_model.kerastensorflowmodel method)": [[3, "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_gradient"]], "get_gradient() (dice_ml.model_interfaces.pytorch_model.pytorchmodel method)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_gradient"]], "get_num_output_nodes() (dice_ml.model_interfaces.base_model.basemodel method)": [[3, "dice_ml.model_interfaces.base_model.BaseModel.get_num_output_nodes"]], "get_num_output_nodes() (dice_ml.model_interfaces.keras_tensorflow_model.kerastensorflowmodel method)": [[3, "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_num_output_nodes"]], "get_num_output_nodes() (dice_ml.model_interfaces.pytorch_model.pytorchmodel method)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_num_output_nodes"]], "get_num_output_nodes2() (dice_ml.model_interfaces.base_model.basemodel method)": [[3, "dice_ml.model_interfaces.base_model.BaseModel.get_num_output_nodes2"]], "get_output() (dice_ml.model_interfaces.base_model.basemodel method)": [[3, "dice_ml.model_interfaces.base_model.BaseModel.get_output"]], "get_output() (dice_ml.model_interfaces.keras_tensorflow_model.kerastensorflowmodel method)": [[3, "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.get_output"]], "get_output() (dice_ml.model_interfaces.pytorch_model.pytorchmodel method)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel.get_output"]], "load_model() (dice_ml.model_interfaces.base_model.basemodel method)": [[3, "dice_ml.model_interfaces.base_model.BaseModel.load_model"]], "load_model() (dice_ml.model_interfaces.keras_tensorflow_model.kerastensorflowmodel method)": [[3, "dice_ml.model_interfaces.keras_tensorflow_model.KerasTensorFlowModel.load_model"]], "load_model() (dice_ml.model_interfaces.pytorch_model.pytorchmodel method)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel.load_model"]], "set_eval_mode() (dice_ml.model_interfaces.pytorch_model.pytorchmodel method)": [[3, "dice_ml.model_interfaces.pytorch_model.PyTorchModel.set_eval_mode"]], "dice_ml.schema": [[4, "module-dice_ml.schema"]], "datatransfomer (class in dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.DataTransfomer"]], "dummydatainterface (class in dice_ml.utils.serialize)": [[5, "dice_ml.utils.serialize.DummyDataInterface"]], "ffnetwork (class in dice_ml.utils.neuralnetworks)": [[5, "dice_ml.utils.neuralnetworks.FFNetwork"]], "systemexception": [[5, "dice_ml.utils.exception.SystemException"]], "userconfigvalidationexception": [[5, "dice_ml.utils.exception.UserConfigValidationException"]], "dice_ml.utils": [[5, "module-dice_ml.utils"]], "dice_ml.utils.exception": [[5, "module-dice_ml.utils.exception"]], "dice_ml.utils.helpers": [[5, "module-dice_ml.utils.helpers"]], "dice_ml.utils.neuralnetworks": [[5, "module-dice_ml.utils.neuralnetworks"]], "dice_ml.utils.serialize": [[5, "module-dice_ml.utils.serialize"]], "feed_data_params() (dice_ml.utils.helpers.datatransfomer method)": [[5, "dice_ml.utils.helpers.DataTransfomer.feed_data_params"]], "forward() (dice_ml.utils.neuralnetworks.ffnetwork method)": [[5, "dice_ml.utils.neuralnetworks.FFNetwork.forward"]], "get_adult_data_info() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_adult_data_info"]], "get_adult_income_modelpath() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_adult_income_modelpath"]], "get_base_gen_cf_initialization() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_base_gen_cf_initialization"]], "get_custom_dataset_modelpath_pipeline() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline"]], "get_custom_dataset_modelpath_pipeline_binary() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_binary"]], "get_custom_dataset_modelpath_pipeline_multiclass() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_multiclass"]], "get_custom_dataset_modelpath_pipeline_regression() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_custom_dataset_modelpath_pipeline_regression"]], "get_custom_vars_dataset_modelpath_pipeline() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.get_custom_vars_dataset_modelpath_pipeline"]], "initialize_transform_func() (dice_ml.utils.helpers.datatransfomer method)": [[5, "dice_ml.utils.helpers.DataTransfomer.initialize_transform_func"]], "inverse_ohe_min_max_transformation() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.inverse_ohe_min_max_transformation"]], "inverse_transform() (dice_ml.utils.helpers.datatransfomer method)": [[5, "dice_ml.utils.helpers.DataTransfomer.inverse_transform"]], "load_adult_income_dataset() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_adult_income_dataset"]], "load_custom_testing_dataset() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_custom_testing_dataset"]], "load_custom_testing_dataset_binary() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_custom_testing_dataset_binary"]], "load_custom_testing_dataset_multiclass() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_custom_testing_dataset_multiclass"]], "load_custom_testing_dataset_regression() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_custom_testing_dataset_regression"]], "load_min_max_equal_dataset() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_min_max_equal_dataset"]], "load_outcome_not_last_column_dataset() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.load_outcome_not_last_column_dataset"]], "ohe_min_max_transformation() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.ohe_min_max_transformation"]], "save_adult_income_model() (in module dice_ml.utils.helpers)": [[5, "dice_ml.utils.helpers.save_adult_income_model"]], "to_json() (dice_ml.utils.serialize.dummydatainterface method)": [[5, "dice_ml.utils.serialize.DummyDataInterface.to_json"]], "transform() (dice_ml.utils.helpers.datatransfomer method)": [[5, "dice_ml.utils.helpers.DataTransfomer.transform"]], "autoencoder (class in dice_ml.utils.sample_architecture.vae_model)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder"]], "cf_vae (class in dice_ml.utils.sample_architecture.vae_model)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE"]], "compute_elbo() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.compute_elbo"]], "decoder() (dice_ml.utils.sample_architecture.vae_model.autoencoder method)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.decoder"]], "decoder() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.decoder"]], "dice_ml.utils.sample_architecture": [[6, "module-dice_ml.utils.sample_architecture"]], "dice_ml.utils.sample_architecture.vae_model": [[6, "module-dice_ml.utils.sample_architecture.vae_model"]], "encoder() (dice_ml.utils.sample_architecture.vae_model.autoencoder method)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.encoder"]], "encoder() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.encoder"]], "forward() (dice_ml.utils.sample_architecture.vae_model.autoencoder method)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.forward"]], "forward() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.forward"]], "normal_likelihood() (dice_ml.utils.sample_architecture.vae_model.autoencoder method)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.normal_likelihood"]], "normal_likelihood() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.normal_likelihood"]], "sample_latent_code() (dice_ml.utils.sample_architecture.vae_model.autoencoder method)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.sample_latent_code"]], "sample_latent_code() (dice_ml.utils.sample_architecture.vae_model.cf_vae method)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.sample_latent_code"]], "training (dice_ml.utils.sample_architecture.vae_model.autoencoder attribute)": [[6, "dice_ml.utils.sample_architecture.vae_model.AutoEncoder.training"]], "training (dice_ml.utils.sample_architecture.vae_model.cf_vae attribute)": [[6, "dice_ml.utils.sample_architecture.vae_model.CF_VAE.training"]]}})
\ No newline at end of file
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 487d84d3..4b790740 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -15,7 +15,6 @@
 
 sys.path.insert(0, os.path.abspath("../../"))
 
-
 # -- Project information -----------------------------------------------------
 
 project = 'DiCE'
@@ -23,7 +22,7 @@
 author = 'Ramaravind, Amit, Chenhao'
 
 # The full version, including alpha/beta/rc tags
-release = '0.8'
+release = '0.9'
 
 
 # -- General configuration ---------------------------------------------------
diff --git a/docs/source/dice_ml.utils.rst b/docs/source/dice_ml.utils.rst
index c37395cd..e1fd2c75 100644
--- a/docs/source/dice_ml.utils.rst
+++ b/docs/source/dice_ml.utils.rst
@@ -28,6 +28,14 @@ dice\_ml.utils.helpers module
    :undoc-members:
    :show-inheritance:
 
+dice\_ml.utils.neuralnetworks module
+------------------------------------
+
+.. automodule:: dice_ml.utils.neuralnetworks
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 dice\_ml.utils.serialize module
 -------------------------------
 
diff --git a/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb b/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb
index f6dcee3c..064c28a4 100644
--- a/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb
+++ b/docs/source/notebooks/DiCE_model_agnostic_CFs.ipynb
@@ -360,7 +360,7 @@
    "outputs": [],
    "source": [
     "# generate counterfactuals\n",
-    "dice_exp_genetic = exp_genetic.generate_counterfactuals(query_instances, total_CFs=4, desired_class=0, verbose=True)"
+    "dice_exp_genetic = exp_genetic.generate_counterfactuals(query_instances, total_CFs=4, desired_class=\"opposite\", verbose=True)"
    ]
   },
   {
@@ -389,7 +389,7 @@
    "source": [
     "# generate counterfactuals\n",
     "dice_exp_genetic = exp_genetic.generate_counterfactuals(\n",
-    "    query_instances, total_CFs=2, desired_class=0,\n",
+    "    query_instances, total_CFs=2, desired_class=\"opposite\",\n",
     "    features_to_vary=['workclass', 'education', 'occupation', 'hours_per_week'])\n",
     "dice_exp_genetic.visualize_as_dataframe(show_only_changes=True)"
    ]
@@ -409,7 +409,7 @@
    "source": [
     "# generate counterfactuals\n",
     "dice_exp_genetic = exp_genetic.generate_counterfactuals(\n",
-    "    query_instances, total_CFs=2, desired_class=0,\n",
+    "    query_instances, total_CFs=2, desired_class=\"opposite\",\n",
     "    permitted_range={'age': [22, 50], 'hours_per_week': [40, 60]})\n",
     "dice_exp_genetic.visualize_as_dataframe(show_only_changes=True)"
    ]
@@ -543,7 +543,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -557,7 +557,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.8.10"
   },
   "toc": {
    "base_numbering": 1,
diff --git a/setup.py b/setup.py
index 03ad7aeb..c1009b06 100644
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,6 @@
 import setuptools
 
-VERSION_STR = "0.8"
+VERSION_STR = "0.9"
 
 with open("README.rst", "r") as fh:
     long_description = fh.read()