Feature/smartphone example

VERSION

@@ -1 +1 @@
-1.1.0
+1.2.0

docs/source/api_reference/api_reference.md

@@ -57,5 +57,8 @@ raw specifications might not be sufficient to provide comprehensive instructions
     xaiographs.datasets.load_education_performance
     xaiographs.datasets.load_education_performance_discretized
     xaiographs.datasets.load_education_performance_why
+    xaiographs.datasets.load_phone_brand_preferences
+    xaiographs.datasets.load_phone_brand_preferences_discretized
+    xaiographs.datasets.load_phone_brand_preferences_why
 ```
 

docs/source/api_reference/datasets.md

@@ -22,6 +22,9 @@
     xaiographs.datasets.load_education_performance
     xaiographs.datasets.load_education_performance_discretized
     xaiographs.datasets.load_education_performance_why
+    xaiographs.datasets.load_phone_brand_preferences
+    xaiographs.datasets.load_phone_brand_preferences_discretized
+    xaiographs.datasets.load_phone_brand_preferences_why
 ```
 
 ```{eval-rst}
@@ -39,6 +42,9 @@
 .. autofunction:: xaiographs.datasets.load_education_performance
 .. autofunction:: xaiographs.datasets.load_education_performance_discretized
 .. autofunction:: xaiographs.datasets.load_education_performance_why
+.. autofunction:: xaiographs.datasets.load_phone_brand_preferences
+.. autofunction:: xaiographs.datasets.load_phone_brand_preferences_discretized
+.. autofunction:: xaiographs.datasets.load_phone_brand_preferences_why
 ```
 
 

docs/source/contributors/contributors.md

@@ -7,9 +7,11 @@ XAIoGraphs has been developed by ***Applied AI & Privacy*** team (Telefónica In
 * [Enrique Fernandez](https://github.com/QuiqueFdez)
 * [Alejandro Manuel Arranz](https://github.com/cx02747)
 * [Manuel Martín](https://github.com/mmarmar)
+* [Morganne De Witte](https://www.linkedin.com/in/morgannedw/)
 * [Mario Villaizan](https://github.com/mvvmvv)
 * [Cesar García](https://github.com/cesarggtid)
 * [David Cadenas](https://github.com/davidcadi)
 * [Alejandra Maria Alonso](https://www.linkedin.com/in/alejandraalonsodiaz/)
 * [Miguel Angel Martín](https://github.com/mamj-telefonica)
 * [Oriol Arnau](https://github.com/oarnau)
+* [Morganne De Witte](https://github.com/MorganneDeWitte)

docs/source/examples/examples.md

@@ -5,13 +5,14 @@ XAIoGraphs contains a set of examples that can be executed as `entry points`:
 
 
 
-| Example                                           | Entry Point                   | Rows  | Num. Feats |       Task       |
-|:--------------------------------------------------|:------------------------------|:-----:|:----------:|:----------------:|
-| [Titanic](titanic.md)                             | titanic_example               | 1309  |     8      |      Binary      |
-| [COMPAS](compas.md)                               | compas_example                | 4230  |     7      | Multi-Class (3)  |
-| [COMPAS Reality](compas_reality.md)               | compas_reality_example        | 4230  |     7      |      Binary      |
-| [Body Performace](body_performance.md)            | body_performance_example      | 13393 |     11     | Multi-Class (3)  | 
-| [Education Performance](education_performance.md) | education_performance_example |  145  |     29     | Multi-Class (5)  |
+| Example                                                         | Entry Point                   | Rows  | Num. Feats |       Task       |
+|:----------------------------------------------------------------|:------------------------------|:-----:|:----------:|:----------------:|
+| [Titanic](titanic.md)                                           | titanic_example               | 1309  |     8      |      Binary      |
+| [COMPAS](compas.md)                                             | compas_example                | 4230  |     7      | Multi-Class (3)  |
+| [COMPAS Reality](compas_reality.md)                             | compas_reality_example        | 4230  |     7      |      Binary      |
+| [Body Performace](body_performance.md)                          | body_performance_example      | 13393 |     11     | Multi-Class (3)  | 
+| [Education Performance](education_performance.md)               | education_performance_example |  145  |     29     | Multi-Class (5)  |
+| [Smartphone Brand Preferences](smartphone_brand_preferences.md) | smartphone_example            |  259  |     11     | Multi-Class (5)  |
 
 
 Use the entry points to see an example run with the XAIoGraphs library installed in a Python virtual environment 
@@ -36,3 +37,4 @@ You can see more information about each of these examples at the links below:
 * [Compas Reality Example](compas_reality.md)
 * [Body Performace Example](body_performance.md)
 * [Education Performance Example](education_performance.md)
+* [Smartphone Brand Preferences](smartphone_brand_preferences.md)

docs/source/examples/smartphone_brand_preferences.md

@@ -0,0 +1,134 @@
+[< ✏️ Examples](examples/examples)
+
+# Smartphone Brand Preferences Example
+
+
+This example highlights the most important features smartphones from certain brands have, to predict the most likely smartphone-brand purchase. The [`Smartphone Brand Preferences Dataset`](../user_guide/datasets.md#smartphone-brand-preferences) is used to capture the characteristics a smartphone has and
+why people choose to buy a determined brand
+
+This dataset can be obtained using the [`load_phone_brand_preferences()`](../api_reference/datasets.md#xaiographs.datasets.load_phone_brand_preferences) 
+function:
+
+```python
+>>> from xaiographs.datasets import load_phone_brand_preferences
+>>> df_dataset = load_phone_brand_preferences()
+>>> df_dataset.head(5)
+      brand  internal_memory  performance  main_camera  selfie_camera  battery_size  screen size  weight  price  age   gender    occupation   
+0  Samsung              128         8.81           50             10          3700          6.1     167    528   38   Female  Data analyst
+1    Apple              256         7.94           12             12          3065          6.1     204    999   38   Female  Data analyst
+2   Google              128         6.76           50              8          4614          6.4     207    499   31   Female         sales
+3  Samsung              128         7.22           50             10          4500          6.6     195    899   31   Female         sales
+4   Google              128         6.88           12              8          4410          6.1     178    449   27   Female   Team leader
+
+```
+
+To determine the explainability of this dataset, XAIoGraphs provides a dataset that has already been discretized and 
+columns with targets probabilities using 
+[`load_phone_brand_preferences_discretized()`](../api_reference/datasets.md#xaiographs.datasets.load_education_performance_discretized) function:
+
+
+```python
+>>> from xaiographs.datasets import load_phone_brand_preferences_discretized
+>>> df_dataset, features_cols, target_cols, y_true, y_predict = load_phone_brand_preferences_discretized()
+>>> df_dataset.head(5)
+   id internal_memory performance main_camera selfie_camera   battery_size     screen_size     weight            price          age  gender      occupation   y_true  y_predict  Apple  Google  Motorola  Samsung  Xiaomi
+0  0          128_GB   Ultra top    15_50_MP        <10_MP      <4000_mAh     <6.4_inches     <190_g  450_700_dollars  35_45_years  Female      Technology  Samsung      Apple      1       0         0        0       0     
+1  1        >=256_GB         Top      <15_MP      10_30_MP      <4000_mAh     <6.4_inches  190_205_g     >700_dollars  35_45_years  Female      Technology    Apple      Apple      1       0         0        0       0     
+2  2          128_GB         Mid    15_50_MP        <10_MP  4000_4700_mAh     <6.4_inches     >205_g  450_700_dollars  25_35_years  Female        Business   Google     Google      0       1         0        0       0     
+3  3          128_GB         Mid    15_50_MP        <10_MP  4000_4700_mAh  6.4_6.6_inches  190_205_g     >700_dollars  25_35_years  Female        Business  Samsung    Samsung      0       0         0        1       0     
+4  4          128_GB         Mid      <15_MP        <10_MP  4000_4700_mAh     <6.4_inches     <190_g  200_450_dollars  25_35_years  Female  Administration   Google     Google      0       1         0        0       0     
+
+```
+
+
+&nbsp;
+## Code Example
+
+The following entry point (with Python virtual environment enabled) is used to demonstrate this example.
+
+```python
+>> smartphone_brand_preferences
+```
+
+Alternatively, you may run the code below to view a full implementation of all XAIoGraphs functionalities with this Dataset:
+
+```python
+from xaiographs import Explainer
+from xaiographs import Why
+from xaiographs import Fairness
+from xaiographs.datasets import load_phone_brand_preferences_discretized, load_phone_brand_preferences_why
+
+LANG = 'en'
+
+# LOAD DATASETS & SEMANTICS
+df_phone_brand_pref, feature_cols, target_cols, y_true, y_predict = load_phone_brand_preferences_discretized()
+df_values_semantics, df_target_values_semantics = load_phone_brand_preferences_why(language=LANG)
+
+# EXPLAINER
+explainer = Explainer(importance_engine='LIDE', verbose=1)
+explainer.fit(df=df_phone_brand_pref, feature_cols=feature_cols, target_cols=target_cols)
+
+# WHY
+why = Why(language=LANG,
+            explainer=explainer,
+            why_values_semantics=df_values_semantics,
+            why_target_values_semantics=df_target_values_semantics,
+            verbose=1)
+why.fit()
+
+# FAIRNESS
+f = Fairness(verbose=1)
+f.fit(df=df_phone_brand_pref[feature_cols + [y_true] + [y_predict]],
+        sensitive_cols=['gender', 'age'],
+        target_col=y_true,
+        predict_col=y_predict)
+```
+
+&nbsp;
+## XAIoWeb Smartphone Brand Preferences
+
+After running the `.fit()` methods of each of the classes (one, two, or all three), a sequence of JSON files are 
+generated in the `xaioweb_files` folder to visualized in XAIoWeb interface.
+
+
+To launch the web (with the virtual environment enabled), run the following entry point:
+
+```python
+>> xaioweb -d xaioweb_files -o -f
+```
+
+And the results seen in XAIoWeb are the following:
+
+&nbsp;
+#### Global Explainability
+&nbsp;
+```{image} ../../imgs/smartphone_brand_preferences_example/XaioWeb_Global_Explainability.png
+:alt: Global Explainability
+:class: bg-primary
+:width: 600px
+:align: center
+```
+
+&nbsp;
+#### Local Explainability
+&nbsp;
+```{image} ../../imgs/smartphone_brand_preferences_example/XaioWeb_Local_Explainability.png
+:alt: Local Explainability
+:class: bg-primary
+:width: 600px
+:align: center
+```
+
+&nbsp;
+#### Fairness
+&nbsp;
+```{image} ../../imgs/smartphone_brand_preferences_example/XaioWeb_Fairness.png
+:alt: Fairness
+:class: bg-primary
+:width: 600px
+:align: center
+```
+&nbsp;
+
+
+[< ✏️ Examples](examples/examples)

docs/source/user_guide/datasets.md

@@ -8,13 +8,14 @@ To test the capabilities of XAIoGraphs, it provides a series of datasets via
 
 The following datasets are included:
 
-| Datset                                          | Rows  | Num. Feats |      Task       |
-|:------------------------------------------------|:-----:|:----------:|:---------------:|
-| [Titanic](#titanic)                             | 1309  |     8      |     Binary      |
-| [Compas](#compas)                               | 4230  |     7      | Multi-Class (3) |
-| [Compas Reality](#compas)                       | 4230  |     7      |     Binary      |
-| [Body Performace](#body-performance)            | 13393 |     11     | Multi-Class (3) | 
-| [Education Performance](#education-performance) |  145  |     29     | Multi-Class (5) |
+| Dataset                                                         | Rows  | Num. Feats |       Task       |
+|:----------------------------------------------------------------|:-----:|:----------:|:----------------:|
+| [Titanic](titanic.md)                                           | 1309  |     8      |      Binary      |
+| [COMPAS](compas.md)                                             | 4230  |     7      | Multi-Class (3)  |
+| [COMPAS Reality](compas_reality.md)                             | 4230  |     7      |      Binary      |
+| [Body Performace](body_performance.md)                          | 13393 |     11     | Multi-Class (3)  | 
+| [Education Performance](education_performance.md)               |  145  |     29     | Multi-Class (5)  |
+| [Smartphone Brand Preferences](smartphone_brand_preferences.md) |  981  |     17     | Multi-Class (5)  |
 
 These datasets are accessible in both raw and discretized form, ready for usage by the 
 [`Explainability`](../api_reference/explainability.md)  and [`Fairness`](../api_reference/fairness.md) classes.
@@ -99,5 +100,19 @@ purpose is to predict students' end-of-term performances using ML techniques.
 | **function to obtain dataset**               | [`xaiographs.datasets.load_education_performance()`](../api_reference/datasets.md#xaiographs.datasets.load_education_performance)                                                                | 
 | **function to obtain discretized dataset**   | [`xaiographs.datasets.load_education_performance_discretized()`](../api_reference/datasets.md#xaiographs.datasets.load_education_performance_discretized)                                        |
 
+ 
+## Smartphone Brand Preferences
+
+The data was collected through a combination of three datasets containing the most noteworthy features on the preferred smartphones in the US in 2022, user's data and smartphone ratings. This information was obtained via a Mechanical Turk survey where participants assessed 10 randomly presented phones by likelihood of purchase and provided personal information. This example highlights the most important features smartphones from certain brands have, to predict the most likely smartphone-brand purchase.
+
+|                                              |                                                                                                                                                                                                  |
+|----------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| **Source**                                   | [https://www.kaggle.com/datasets/meirnizri/cellphones-recommendations/data?select=cellphones+ratings.csv](https://www.kaggle.com/datasets/meirnizri/cellphones-recommendations/data?select=cellphones+ratings.csv) |
+| **Num Rows:**                                | 259                                                                                                                                                                                              |
+| **Num Features**                             | 11                                                                                                                                                                                               |
+| **Num Targets:**                             | 5                                                                                                                                                                                                |
+| **function to obtain dataset**               | [`xaiographs.datasets.load_phone_brand_preferences()`](../api_reference/datasets.md#xaiographs.datasets.load_education_performance)                                                                | 
+| **function to obtain discretized dataset**   | [`xaiographs.datasets.load_phone_brand_preferences_discretized()`](../api_reference/datasets.md#xaiographs.datasets.load_education_performance_discretized)                                        |
+
 
 [< 📚 User Guide](user_guide/user_guide)

docs/source/user_guide/user_guide.md

@@ -30,5 +30,6 @@
 * [COMPAS](datasets.md#compas)
 * [Body Performace](datasets.md#body-performace)
 * [Education Performance](datasets.md#education-performance)
+* [Smartphone Brand Preferences](datasets.md#smartphone-brand-preferences)
 
 [//]: # (* [Compas](datasets.md#compas))

examples/smartphone_brand_preferences_example.py

@@ -0,0 +1,46 @@
+# -*- coding: utf-8 -*-
+
+u"""
+© 2023 Telefónica Digital España S.L.
+This file is part of XAIoGraphs.
+
+XAIoGraphs is free software: you can redistribute it and/or modify it under the terms of the Affero GNU General Public
+License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any
+later version.
+
+XAIoGraphs is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied
+warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the Affero GNU General Public License
+for more details.
+
+You should have received a copy of the Affero GNU General Public License along with XAIoGraphs. If not,
+see https://www.gnu.org/licenses/."""
+
+from xaiographs import Explainer
+from xaiographs import Why
+from xaiographs import Fairness
+from xaiographs.datasets import load_phone_brand_preferences_discretized, load_phone_brand_preferences_why
+
+LANG = 'en'
+
+# LOAD DATASETS & SEMANTICS
+df_phone_brand_pref, feature_cols, target_cols, y_true, y_predict = load_phone_brand_preferences_discretized()
+df_values_semantics, df_target_values_semantics = load_phone_brand_preferences_why(language=LANG)
+
+# EXPLAINER
+explainer = Explainer(importance_engine='LIDE', verbose=1)
+explainer.fit(df=df_phone_brand_pref, feature_cols=feature_cols, target_cols=target_cols)
+
+# WHY
+why = Why(language=LANG,
+            explainer=explainer,
+            why_values_semantics=df_values_semantics,
+            why_target_values_semantics=df_target_values_semantics,
+            verbose=1)
+why.fit()
+
+# FAIRNESS
+f = Fairness(verbose=1)
+f.fit(df=df_phone_brand_pref[feature_cols + [y_true] + [y_predict]],
+        sensitive_cols=['gender', 'age'],
+        target_col=y_true,
+        predict_col=y_predict)

requirements.txt

@@ -1,5 +1,5 @@
-numpy==1.21.6
-pandas==1.3.5
-scikit-learn==0.24.2
-scipy==1.7.3
+numpy>=1.19.5,<=1.23.1
+pandas>=1.3.5,<2.0.0
+scikit-learn<=0.24.2,<=1.3.2
+scipy>=1.7.3
 tqdm==4.64.1

setup.py

@@ -36,7 +36,7 @@
     author='Telefonica I+D',
     author_email='ricardo.moyagarcia@telefonica.com',
     license='AGPL-3.0 license',
-    python_requires='>=3.7',
+    python_requires='>=3.7,<3.10',
     packages=['xaiographs'],
     include_package_data=True,
     install_requires=required,
@@ -50,6 +50,7 @@
             "education_performance_example = xaiographs.examples.education_performance_example:main",
             "compas_example = xaiographs.examples.compas_example:main",
             "compas_reality_example = xaiographs.examples.compas_reality_example:main",
+            "smartphone_example = xaiographs.examples.smartphone_brand_preferences_example:main",
         ]
     }
 )

xaiographs/__init__.py

@@ -15,7 +15,27 @@
 You should have received a copy of the Affero GNU General Public License along with XAIoGraphs. If not,
 see https://www.gnu.org/licenses/."""
 
+import sys
+import numpy as np
 
 from .exgraph.explainer import Explainer
 from .fairness import Fairness
 from .why.why import Why
+
+# Check the Python version
+if sys.version_info < (3, 7) or sys.version_info >= (3, 10):
+    raise RuntimeError("Your Python {}.{}.{} version is incompatible with XAIoGraphs.\n"
+                       "XAIoGraphs requires Python 3.7 or higher, but less than 3.10."
+                       .format(sys.version_info.major, sys.version_info.minor, sys.version_info.micro))
+
+# Check the numpy version
+numpy_version = np.__version__
+
+# Split the version into a tuple of integers (e.g., '1.20.3' -> (1, 20, 3))
+numpy_version_tuple = tuple(map(int, numpy_version.split('.')))
+
+# Check if the version is within the allowed range (>=1.19.5, <1.23.5)
+if not ((1, 19, 5) <= numpy_version_tuple <= (1, 23, 1)):
+    raise ImportError("Your numpy version {} is incompatible with XAIoGraphs.\n"
+                      "XAIoGraphs requires numpy version 1.19.5 or higher, but less than 1.23.1"
+                      .format(numpy_version))