From 260faf6be64d289af3d4f2d057564689c1480014 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 15:33:19 +0100
Subject: [PATCH 01/45] Add a check_list_of_arrays fct in utils/validation

---
 gtda/utils/validation.py | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 4622c0764..115040eae 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -5,6 +5,8 @@
 import types
 import numpy as np
 
+from sklearn.utils.validation import check_array
+
 available_metrics = {
     'bottleneck': [('delta', numbers.Number, (0., 1.))],
     'wasserstein': [('p', int, (1, np.inf)),
@@ -174,3 +176,34 @@ def validate_metric_params(metric, metric_params):
                              " parameter. Available metric_params"
                              " are {}".format(param,
                                               available_metric_params[metric]))
+
+
+def check_list_of_arrays(X, **kwargs):
+    """"Check a list of arrays, by itegrating through the input one by one.
+    Parameters
+    ----------
+    X : list(np.array), such that `X[i].ndim==2` (n_points, n_dimensions),
+        or an array `X.dim==3`
+    Returns
+    -------
+    X : list of input arrays, as modified by check_array
+    """
+    if isinstance(X, np.ndarray):
+        return check_array(X, **kwargs)
+    else:
+        results = []
+        messages = []
+        for id_x, x in enumerate(X):
+            try:
+                X[id_x] = np.squeeze(check_array(np.expand_dims(x, axis=0),
+                                                 **kwargs), axis=0)
+                results.append(True)
+                messages = ['']
+            except ValueError as e:
+                results.append(False)
+                messages.append(str(e))
+            if all(results):
+                return X
+            else:
+                raise ValueError("The following errors were raised" +
+                                 "by the inputs: \n" + "\n".join(messages))

From 2d840d364b3695c83a9d486858fe2f85e7cf724d Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 15:52:30 +0100
Subject: [PATCH 02/45] Change the checks in the homology classes

---
 gtda/homology/consistent.py   |  8 ++++----
 gtda/homology/grids.py        |  6 +++---
 gtda/homology/point_clouds.py | 16 ++++++++--------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/gtda/homology/consistent.py b/gtda/homology/consistent.py
index 1e1499b95..f48fb82e9 100644
--- a/gtda/homology/consistent.py
+++ b/gtda/homology/consistent.py
@@ -7,10 +7,10 @@
 from joblib import Parallel, delayed
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.metrics import pairwise_distances
-from sklearn.utils.validation import check_array, check_is_fitted
+from sklearn.utils.validation import check_is_fitted
 
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params
+from ..utils.validation import validate_params, check_list_of_arrays
 
 
 @adapt_fit_transform_docs
@@ -132,7 +132,7 @@ def fit(self, X, y=None):
 
         """
         validate_params(self.get_params(), self._hyperparameters)
-        check_array(X, allow_nd=True)
+        check_list_of_arrays(X, allow_nd=True)
 
         self._is_fitted = True
         return self
@@ -164,7 +164,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        X = check_array(X, allow_nd=True)
+        X = check_list_of_arrays(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._consistent_homology_distance)(X[i])
diff --git a/gtda/homology/grids.py b/gtda/homology/grids.py
index d222da0de..fc67429ec 100644
--- a/gtda/homology/grids.py
+++ b/gtda/homology/grids.py
@@ -5,9 +5,9 @@
 import numbers
 from sklearn.base import BaseEstimator, TransformerMixin
 from joblib import Parallel, delayed
-from sklearn.utils.validation import check_array, check_is_fitted
+from sklearn.utils.validation import check_is_fitted
 from ._utils import _pad_diagram
-from ..utils.validation import validate_params
+from ..utils.validation import validate_params, check_list_of_arrays
 
 from ..externals.python import CubicalComplex, PeriodicCubicalComplex
 
@@ -157,7 +157,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_array(X, allow_nd=True)
+        check_list_of_arrays(X, allow_nd=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
diff --git a/gtda/homology/point_clouds.py b/gtda/homology/point_clouds.py
index a9d228473..2f7c616ee 100644
--- a/gtda/homology/point_clouds.py
+++ b/gtda/homology/point_clouds.py
@@ -6,13 +6,13 @@
 import numpy as np
 from joblib import Parallel, delayed
 from sklearn.base import BaseEstimator, TransformerMixin
-from sklearn.utils.validation import check_array, check_is_fitted
+from sklearn.utils.validation import check_is_fitted
 from sklearn.metrics.pairwise import pairwise_distances
 
 from ._utils import _postprocess_diagrams
 from ..externals.python import ripser, SparseRipsComplex, CechComplex
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params
+from ..utils.validation import validate_params, check_list_of_arrays
 
 
 @adapt_fit_transform_docs
@@ -165,7 +165,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_array(X, allow_nd=True, force_all_finite=False)
+        check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -207,7 +207,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_array(X, allow_nd=True, force_all_finite=False)
+        X = check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
                                           for i in range(len(X)))
@@ -381,7 +381,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_array(X, allow_nd=True, force_all_finite=False)
+        check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -423,7 +423,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_array(X, allow_nd=True, force_all_finite=False)
+        X = check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
@@ -565,7 +565,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_array(X, allow_nd=True)
+        check_list_of_arrays(X, allow_nd=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -602,7 +602,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_array(X, allow_nd=True)
+        X = check_list_of_arrays(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(

From 5c3f24af4be68410a8af636133135b410f4a237b Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 16:47:00 +0100
Subject: [PATCH 03/45] Discard check on arrays and treat everything as lists
 in utils/validations:check_list_of_arrays, modify the point-cloud class
 accordingly

---
 gtda/homology/point_clouds.py | 12 +++++------
 gtda/utils/validation.py      | 39 ++++++++++++++++-------------------
 2 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/gtda/homology/point_clouds.py b/gtda/homology/point_clouds.py
index 2f7c616ee..5a40374cc 100644
--- a/gtda/homology/point_clouds.py
+++ b/gtda/homology/point_clouds.py
@@ -165,7 +165,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
+        check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -207,7 +207,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
+        X = check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
                                           for i in range(len(X)))
@@ -381,7 +381,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
+        check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -423,7 +423,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, allow_nd=True, force_all_finite=False)
+        X = check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
@@ -565,7 +565,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, allow_nd=True)
+        check_list_of_arrays(X, ensure_2d=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -602,7 +602,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, allow_nd=True)
+        X = check_list_of_arrays(X, ensure_2d=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 115040eae..2de9b0eb1 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -179,31 +179,28 @@ def validate_metric_params(metric, metric_params):
 
 
 def check_list_of_arrays(X, **kwargs):
-    """"Check a list of arrays, by itegrating through the input one by one.
+    """"Check a list of arrays, by integrating through the input one by one.
     Parameters
     ----------
-    X : list(np.array), such that `X[i].ndim==2` (n_points, n_dimensions),
+    X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
     Returns
     -------
     X : list of input arrays, as modified by check_array
     """
-    if isinstance(X, np.ndarray):
-        return check_array(X, **kwargs)
-    else:
-        results = []
-        messages = []
-        for id_x, x in enumerate(X):
-            try:
-                X[id_x] = np.squeeze(check_array(np.expand_dims(x, axis=0),
-                                                 **kwargs), axis=0)
-                results.append(True)
-                messages = ['']
-            except ValueError as e:
-                results.append(False)
-                messages.append(str(e))
-            if all(results):
-                return X
-            else:
-                raise ValueError("The following errors were raised" +
-                                 "by the inputs: \n" + "\n".join(messages))
+
+    results = []
+    messages = []
+    for id_x, x in enumerate(X):
+        try:
+            X[id_x] = check_array(x, **kwargs)
+            results.append(True)
+            messages = ['']
+        except ValueError as e:
+            results.append(False)
+            messages.append(str(e))
+        if all(results):
+            return X
+        else:
+            raise ValueError("The following errors were raised" +
+                             "by the inputs: \n" + "\n".join(messages))

From 57f98a228b375d5a2727e6d67eed54467f738196 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 16:48:23 +0100
Subject: [PATCH 04/45] Adapt the tests for pcs

---
 gtda/homology/tests/test_point_clouds.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/gtda/homology/tests/test_point_clouds.py b/gtda/homology/tests/test_point_clouds.py
index 42631d1e7..f18c91d44 100644
--- a/gtda/homology/tests/test_point_clouds.py
+++ b/gtda/homology/tests/test_point_clouds.py
@@ -97,3 +97,17 @@ def test_cp_transform():
     cp = EuclideanCechPersistence()
 
     assert_almost_equal(cp.fit_transform(pc), pc_cp_res)
+
+
+def test_vrp_list_of_arrays():
+    pc_2 = np.array([[0, 1, 2], [1, 2, 4]])
+    pc_list = [pc[0].copy(), pc_2]
+    vrp = VietorisRipsPersistence()
+    vrp.fit(pc_list)
+
+
+def test_vrp_list_invalid_arrays():
+    pc_invalid = np.array([0, 1])
+    vrp = VietorisRipsPersistence()
+    with pytest.raises(ValueError):
+        vrp.fit([pc_invalid])

From d4113057f88cc5865ee818e3a13ef2d510c3d25c Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 17:03:25 +0100
Subject: [PATCH 05/45] Correct the indentation on the for loop

---
 gtda/utils/validation.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 2de9b0eb1..323ecdd5b 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -199,8 +199,8 @@ def check_list_of_arrays(X, **kwargs):
         except ValueError as e:
             results.append(False)
             messages.append(str(e))
-        if all(results):
-            return X
-        else:
-            raise ValueError("The following errors were raised" +
-                             "by the inputs: \n" + "\n".join(messages))
+    if all(results):
+        return X
+    else:
+        raise ValueError("The following errors were raised" +
+                         "by the inputs: \n" + "\n".join(messages))

From cf80832b652227b57ca62e25f4f58a7616944eda Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 17:04:31 +0100
Subject: [PATCH 06/45] Ensure that all points clouds are 2d tensors

---
 gtda/homology/consistent.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gtda/homology/consistent.py b/gtda/homology/consistent.py
index f48fb82e9..c725e66ce 100644
--- a/gtda/homology/consistent.py
+++ b/gtda/homology/consistent.py
@@ -132,7 +132,7 @@ def fit(self, X, y=None):
 
         """
         validate_params(self.get_params(), self._hyperparameters)
-        check_list_of_arrays(X, allow_nd=True)
+        check_list_of_arrays(X, ensure_2d=True)
 
         self._is_fitted = True
         return self
@@ -164,7 +164,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        X = check_list_of_arrays(X, allow_nd=True)
+        X = check_list_of_arrays(X, ensure_2d=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._consistent_homology_distance)(X[i])

From c3310543e96bbb73e3ac40ea74d155650f52da07 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 20 Feb 2020 18:06:42 +0100
Subject: [PATCH 07/45] Introduce the check_list_of_images function

---
 gtda/images/filtrations.py | 20 ++++++++--------
 gtda/utils/validation.py   | 49 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 10 deletions(-)

diff --git a/gtda/images/filtrations.py b/gtda/images/filtrations.py
index 250530251..56586f0c3 100644
--- a/gtda/images/filtrations.py
+++ b/gtda/images/filtrations.py
@@ -7,9 +7,9 @@
 from joblib import Parallel, delayed, effective_n_jobs
 from sklearn.metrics import pairwise_distances
 from sklearn.utils import gen_even_slices
-from sklearn.utils.validation import check_is_fitted, check_array
+from sklearn.utils.validation import check_is_fitted
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params
+from ..utils.validation import validate_params, check_list_of_images
 from ._utils import _dilate
 
 
@@ -96,7 +96,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self.n_dimensions_ = len(X.shape) - 1
 
@@ -152,7 +152,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X,  ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_height)(X[s])
@@ -279,7 +279,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self.n_dimensions_ = len(X.shape) - 1
 
@@ -341,7 +341,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X,  ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_radial)(X[s])
@@ -435,7 +435,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self.max_value_ = np.sum(X.shape[1:])
 
@@ -475,7 +475,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X,  ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_dilation)(X[s])
@@ -569,7 +569,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self.max_value_ = np.sum(X.shape[1:])
 
@@ -609,7 +609,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X,  ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_erosion)(X[s])
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 323ecdd5b..3c6df7a14 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -178,6 +178,40 @@ def validate_metric_params(metric, metric_params):
                                               available_metric_params[metric]))
 
 
+def check_list_of_images(X, **kwargs):
+    """"Check a list of arrays representing images, by integrating
+    through the input one by one.
+    Parameters
+    ----------
+    X : list(ndarray), ???
+    Returns
+    -------
+    X : list of input arrays, as modified by check_array
+    """
+    kwargs_default = {'allow_n_axis_incons':  False,
+                      'allow_dims_incons': False,
+                      'force_all_finite': True,
+                      'ensure_2d': False}
+    kwargs_default.update(kwargs)
+    return check_list_of_arrays(X, **kwargs_default)
+
+
+def check_list_of_point_clouds(X, **kwargs):
+    """"Check a list of arrays representing point clouds, by integrating
+    through the input one by one.
+    Parameters
+    ----------
+    X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
+        or an array `X.dim==3`
+    Returns
+    -------
+    X : list of input arrays, as modified by check_array
+    """
+    kwargs_default = {'ensure_2d': True, 'force_all_finite': False}
+    kwargs_default.update(kwargs)
+    return check_list_of_arrays(X, **kwargs_default)
+
+
 def check_list_of_arrays(X, **kwargs):
     """"Check a list of arrays, by integrating through the input one by one.
     Parameters
@@ -188,6 +222,21 @@ def check_list_of_arrays(X, **kwargs):
     -------
     X : list of input arrays, as modified by check_array
     """
+    allow_n_axis_incons = kwargs.pop('allow_n_axis_incons', True)
+    allow_dim_incons = kwargs.pop('allow_dims_incons', True)
+
+    # if restrictions on the dimensions of the input are imposed
+    if not allow_dim_incons:
+        shapes = [X.shape for x in X]
+        if not(all([shapes[0] == s for s in shapes])):
+            raise ValueError("The arrays in X do not have the same dimensions"
+                             "({}), while they should.".format(shapes))
+        # if the number of dimensions can very
+    if not allow_n_axis_incons:
+        n_axis = [len(X.shape) for x in X]
+        if not(all([n_axis[0] == n for n in n_axis])):
+            raise ValueError("The arrays in X do not have the same number"
+                             "of axes ({}), while they should.".format(n_axis))
 
     results = []
     messages = []

From 9cfd604821b3f6b57db8fb9051656a0359bc3f30 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 09:18:25 +0100
Subject: [PATCH 08/45] Use check_point_clouds in the point-cloud filtrations.
 Add the allow_nd param to check_array for images

---
 gtda/homology/point_clouds.py | 14 +++++++-------
 gtda/utils/validation.py      | 28 ++++++++++++++--------------
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/gtda/homology/point_clouds.py b/gtda/homology/point_clouds.py
index 5a40374cc..aed190cb4 100644
--- a/gtda/homology/point_clouds.py
+++ b/gtda/homology/point_clouds.py
@@ -12,7 +12,7 @@
 from ._utils import _postprocess_diagrams
 from ..externals.python import ripser, SparseRipsComplex, CechComplex
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params, check_list_of_arrays
+from ..utils.validation import validate_params, check_list_of_point_clouds
 
 
 @adapt_fit_transform_docs
@@ -165,7 +165,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
+        check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -207,7 +207,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
+        X = check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
                                           for i in range(len(X)))
@@ -381,7 +381,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
+        check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -423,7 +423,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, ensure_2d=True, force_all_finite=False)
+        X = check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
@@ -565,7 +565,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, ensure_2d=True)
+        check_list_of_point_clouds(X, ensure_2d=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -602,7 +602,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_arrays(X, ensure_2d=True)
+        X = check_list_of_point_clouds(X, ensure_2d=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 3c6df7a14..8c8eeef48 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -183,15 +183,14 @@ def check_list_of_images(X, **kwargs):
     through the input one by one.
     Parameters
     ----------
-    X : list(ndarray), ???
+    X : list of ndarray, 
     Returns
     -------
-    X : list of input arrays, as modified by check_array
+    X : list of ndarray, as modified by check_array
     """
-    kwargs_default = {'allow_n_axis_incons':  False,
-                      'allow_dims_incons': False,
-                      'force_all_finite': True,
-                      'ensure_2d': False}
+    kwargs_default = {'force_same_n_axis':  False,
+                      'force_same_dim': True, 'force_all_finite': True,
+                      'ensure_2d': False, 'allow_nd': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
@@ -207,7 +206,8 @@ def check_list_of_point_clouds(X, **kwargs):
     -------
     X : list of input arrays, as modified by check_array
     """
-    kwargs_default = {'ensure_2d': True, 'force_all_finite': False}
+    kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
+                      'force_same_dim': False, 'force_same_n_axis': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
@@ -222,18 +222,18 @@ def check_list_of_arrays(X, **kwargs):
     -------
     X : list of input arrays, as modified by check_array
     """
-    allow_n_axis_incons = kwargs.pop('allow_n_axis_incons', True)
-    allow_dim_incons = kwargs.pop('allow_dims_incons', True)
+    force_same_dim = kwargs.pop('force_same_dim', True)
+    force_same_n_axis = kwargs.pop('force_same_n_axis', True)
 
     # if restrictions on the dimensions of the input are imposed
-    if not allow_dim_incons:
-        shapes = [X.shape for x in X]
+    if force_same_dim:
+        shapes = [x.shape for x in X]
         if not(all([shapes[0] == s for s in shapes])):
             raise ValueError("The arrays in X do not have the same dimensions"
                              "({}), while they should.".format(shapes))
-        # if the number of dimensions can very
-    if not allow_n_axis_incons:
-        n_axis = [len(X.shape) for x in X]
+    # if the number of dimensions can vary
+    if force_same_n_axis:
+        n_axis = [len(x.shape) for x in X]
         if not(all([n_axis[0] == n for n in n_axis])):
             raise ValueError("The arrays in X do not have the same number"
                              "of axes ({}), while they should.".format(n_axis))

From 993cff1782413a0525cba07ea1f97f2049a74fc6 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 09:25:55 +0100
Subject: [PATCH 09/45] Fix lkinting

---
 gtda/homology/point_clouds.py | 6 ++++--
 gtda/utils/validation.py      | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/gtda/homology/point_clouds.py b/gtda/homology/point_clouds.py
index aed190cb4..5e1c0981f 100644
--- a/gtda/homology/point_clouds.py
+++ b/gtda/homology/point_clouds.py
@@ -207,7 +207,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
+        X = check_list_of_point_clouds(X, ensure_2d=True,
+                                       force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
                                           for i in range(len(X)))
@@ -423,7 +424,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
+        X = check_list_of_point_clouds(X, ensure_2d=True,
+                                       force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 8c8eeef48..24863eff5 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -183,7 +183,7 @@ def check_list_of_images(X, **kwargs):
     through the input one by one.
     Parameters
     ----------
-    X : list of ndarray, 
+    X : list of ndarray,
     Returns
     -------
     X : list of ndarray, as modified by check_array

From 028bd00a5d11b92ec6302523c7cf1c10a5e08fb0 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 09:59:13 +0100
Subject: [PATCH 10/45] Change the size of inputs in preprocessing

---
 gtda/images/preprocessing.py | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index 1b2fb93c0..e189aec8c 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -6,9 +6,9 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from joblib import Parallel, delayed, effective_n_jobs
 from sklearn.utils import gen_even_slices
-from sklearn.utils.validation import check_is_fitted, check_array
+from sklearn.utils.validation import check_is_fitted
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params
+from ..utils.validation import validate_params,check_list_of_images
 
 
 @adapt_fit_transform_docs
@@ -83,7 +83,7 @@ def fit(self, X, y=None):
 
         """
         validate_params(self.get_params(), self._hyperparameters)
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self.n_dimensions_ = len(X.shape) - 1
         self.max_value_ = np.max(X)
@@ -114,7 +114,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X,  ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._binarize)(X[s])
@@ -166,7 +166,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X, ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         self._is_fitted = True
         return self
@@ -194,7 +194,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, ['_is_fitted'])
-        Xt = check_array(X, ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.logical_not)(X[s])
@@ -275,7 +275,7 @@ def fit(self, X, y=None):
                         {**self._hyperparameters,
                          'paddings_dim': [int, [n_dimensions]]})
 
-        check_array(X, ensure_2d=False, allow_nd=True)
+        check_list_of_images(X)
 
         self._pad_width = ((0, 0),
                            *[(self.paddings_[axis], self.paddings_[axis])
@@ -306,7 +306,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X, ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.pad)(X[s], pad_width=self._pad_width,
@@ -378,7 +378,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_array(X,  ensure_2d=False, allow_nd=True)
+        X = check_list_of_images(X)
 
         n_dimensions = len(X.shape) - 1
         axis_order = [2, 1, 3]
@@ -415,7 +415,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X, ensure_2d=False, allow_nd=True, copy=True)
+        Xt = check_list_of_images(X, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._embed)(X[s])

From c1e7b163b3482330703dbcac1bfd391620c9ed49 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 10:52:48 +0100
Subject: [PATCH 11/45] Make the outpu of the image2pctransformer variable in
 size,  and adjust the tests (modify the expected values)

---
 gtda/images/preprocessing.py            | 12 +++++++---
 gtda/images/tests/test_preprocessing.py | 32 +++++++++++++++++++++++--
 2 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index e189aec8c..ba8707e4d 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -2,6 +2,7 @@
 # License: GNU AGPLv3
 
 import numbers
+from functools import reduce
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin
 from joblib import Parallel, delayed, effective_n_jobs
@@ -353,11 +354,15 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin):
     def __init__(self, n_jobs=None):
         self.n_jobs = n_jobs
 
-    def _embed(self, X):
+    def _embed_(self, X):
         Xpts = np.stack([self.mesh_ for _ in range(X.shape[0])]) * 1.0
         Xpts[np.logical_not(X.reshape((X.shape[0], -1))), :] += np.inf
         return Xpts
 
+    def _embed(self, X):
+        Xpts = [np.stack(np.nonzero(x), axis=1) for x in X]
+        return Xpts
+
     def fit(self, X, y=None):
         """Do nothing and return the estimator unchanged.
         This method is here to implement the usual scikit-learn API and hence
@@ -380,7 +385,7 @@ def fit(self, X, y=None):
         """
         X = check_list_of_images(X)
 
-        n_dimensions = len(X.shape) - 1
+        n_dimensions = len(X[0].shape)
         axis_order = [2, 1, 3]
         mesh_range_list = [np.arange(0, X.shape[i])
                            for i in axis_order[:n_dimensions]]
@@ -421,5 +426,6 @@ def transform(self, X, y=None):
             self._embed)(X[s])
             for s in gen_even_slices(X.shape[0],
                                      effective_n_jobs(self.n_jobs)))
-        Xt = np.concatenate(Xt)
+        #Xt = np.concatenate(Xt)
+        Xt = reduce(sum, Xt, [])
         return Xt
diff --git a/gtda/images/tests/test_preprocessing.py b/gtda/images/tests/test_preprocessing.py
index 77dd4855c..d55180c28 100644
--- a/gtda/images/tests/test_preprocessing.py
+++ b/gtda/images/tests/test_preprocessing.py
@@ -136,6 +136,24 @@ def test_img2pc_not_fitted():
       [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
       [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf]]])
 
+images_2D_img2pc = list(
+    [np.array([[0., 2.], [1., 2.], [0., 1.], [1., 1.], [0., 0.], [1., 0.]]),
+     np.array([[0., 2.], [0., 1.], [0., 0.]]),
+     np.array([[]])
+     ])
+
+images_3D_img2pc = list(
+    [np.array([[0., 2., 0.], [0., 2., 1.],
+              [1., 2., 0.], [1., 2., 1.],
+              [0., 1., 0.], [0., 1., 1.],
+              [1., 1., 0.], [1., 1., 1.],
+              [0., 0., 0.], [0., 0., 1.],
+              [1., 0., 0.], [1., 0., 1.]]),
+     np.array([[0., 2., 0.], [0., 2., 1.],
+               [0., 1., 0.], [0., 1., 1.],
+               [0., 0., 0.], [0., 0., 1.]]),
+     np.array([[]])])
+
 
 @pytest.mark.parametrize("images, expected",
                          [(images_2D_small, images_2D_img2pc),
@@ -143,5 +161,15 @@ def test_img2pc_not_fitted():
 def test_img2pc_transform(images, expected):
     img2pc = ImageToPointCloud()
 
-    assert_almost_equal(img2pc.fit_transform(images),
-                        expected)
+    all(compare_arrays_as_sets(res, expected)
+        for res, expected in zip(img2pc.fit_transform(images),
+                                 expected))
+
+
+def compare_arrays_as_sets(a1, a2):
+    """ A helper function to compare two point_clouds. They should have the same points,
+    but not necessarily in the same order"""
+    def to_set_of_elements(a):
+        return set([tuple(p) for p in a])
+    as1, as2 = [to_set_of_elements(a) for a in [a1, a2]]
+    return (as1 <= as2) and (as1 >= as2)

From 4572d74cc269a6723d30887b16d0e72568d90ad6 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 10:55:35 +0100
Subject: [PATCH 12/45] Fix linting in gttda.images and the docstring from
 imageToPointCloud

---
 gtda/images/preprocessing.py            | 23 ++++-------------------
 gtda/images/tests/test_preprocessing.py |  5 +++--
 2 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index ba8707e4d..29c34e3d8 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -9,7 +9,7 @@
 from sklearn.utils import gen_even_slices
 from sklearn.utils.validation import check_is_fitted
 from ..utils._docs import adapt_fit_transform_docs
-from ..utils.validation import validate_params,check_list_of_images
+from ..utils.validation import validate_params, check_list_of_images
 
 
 @adapt_fit_transform_docs
@@ -324,8 +324,7 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin):
     """Represent active pixels in 2D/3D binary images as points in 2D/3D space.
 
     The coordinates of each point is calculated as follows. For each activated
-    pixel, assign coordinates that are the pixel position on this image. All
-    deactivated pixels are given infinite coordinates in that space.
+    pixel, assign coordinates that are the pixel position on this image.
     This transformer is meant to transform a collection of images to a point
     cloud so that collection of point clouds-based persistent homology module
     can be applied.
@@ -354,11 +353,6 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin):
     def __init__(self, n_jobs=None):
         self.n_jobs = n_jobs
 
-    def _embed_(self, X):
-        Xpts = np.stack([self.mesh_ for _ in range(X.shape[0])]) * 1.0
-        Xpts[np.logical_not(X.reshape((X.shape[0], -1))), :] += np.inf
-        return Xpts
-
     def _embed(self, X):
         Xpts = [np.stack(np.nonzero(x), axis=1) for x in X]
         return Xpts
@@ -383,16 +377,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X)
-
-        n_dimensions = len(X[0].shape)
-        axis_order = [2, 1, 3]
-        mesh_range_list = [np.arange(0, X.shape[i])
-                           for i in axis_order[:n_dimensions]]
-
-        self.mesh_ = np.flip(np.stack(np.meshgrid(*mesh_range_list),
-                                      axis=n_dimensions),
-                             axis=0).reshape((-1, n_dimensions))
+        _ = check_list_of_images(X)
 
         return self
 
@@ -426,6 +411,6 @@ def transform(self, X, y=None):
             self._embed)(X[s])
             for s in gen_even_slices(X.shape[0],
                                      effective_n_jobs(self.n_jobs)))
-        #Xt = np.concatenate(Xt)
+
         Xt = reduce(sum, Xt, [])
         return Xt
diff --git a/gtda/images/tests/test_preprocessing.py b/gtda/images/tests/test_preprocessing.py
index d55180c28..8ee30ad45 100644
--- a/gtda/images/tests/test_preprocessing.py
+++ b/gtda/images/tests/test_preprocessing.py
@@ -167,8 +167,9 @@ def test_img2pc_transform(images, expected):
 
 
 def compare_arrays_as_sets(a1, a2):
-    """ A helper function to compare two point_clouds. They should have the same points,
-    but not necessarily in the same order"""
+    """ A helper function to compare two point_clouds.
+    They should have the same points, but not necessarily in the same order.
+    """
     def to_set_of_elements(a):
         return set([tuple(p) for p in a])
     as1, as2 = [to_set_of_elements(a) for a in [a1, a2]]

From 5556e4c284cc98efaf82e46b5109886fcc2d38c0 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 11:30:52 +0100
Subject: [PATCH 13/45] Document the validation functions, lint test
 preprocessing and make ImageToPointCloud pass the check_is:_fitted test

---
 gtda/images/preprocessing.py            |  3 ++-
 gtda/images/tests/test_preprocessing.py |  3 ++-
 gtda/utils/validation.py                | 30 +++++++++++++++++++++----
 3 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index 29c34e3d8..a119452f6 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -124,7 +124,7 @@ def transform(self, X, y=None):
         Xt = np.concatenate(Xt)
 
         if self.n_dimensions_ == 2:
-            Xt = Xt.reshape((*X.shape))
+            Xt = Xt.reshape(X.shape)
 
         return Xt
 
@@ -378,6 +378,7 @@ def fit(self, X, y=None):
 
         """
         _ = check_list_of_images(X)
+        self.is_fitted_ = True
 
         return self
 
diff --git a/gtda/images/tests/test_preprocessing.py b/gtda/images/tests/test_preprocessing.py
index 8ee30ad45..3b877960e 100644
--- a/gtda/images/tests/test_preprocessing.py
+++ b/gtda/images/tests/test_preprocessing.py
@@ -160,9 +160,10 @@ def test_img2pc_not_fitted():
                           (images_3D_small, images_3D_img2pc)])
 def test_img2pc_transform(images, expected):
     img2pc = ImageToPointCloud()
+    results = img2pc.fit_transform(images)
 
     all(compare_arrays_as_sets(res, expected)
-        for res, expected in zip(img2pc.fit_transform(images),
+        for res, expected in zip(results,
                                  expected))
 
 
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 24863eff5..637568b61 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -180,13 +180,17 @@ def validate_metric_params(metric, metric_params):
 
 def check_list_of_images(X, **kwargs):
     """"Check a list of arrays representing images, by integrating
-    through the input one by one.
+    through the input one by one. To pass a test with
+    :param:`kwargs`=None
+
     Parameters
     ----------
     X : list of ndarray,
+        Each entry of X corresponds to an image.
     Returns
     -------
     X : list of ndarray, as modified by check_array
+
     """
     kwargs_default = {'force_same_n_axis':  False,
                       'force_same_dim': True, 'force_all_finite': True,
@@ -202,9 +206,11 @@ def check_list_of_point_clouds(X, **kwargs):
     ----------
     X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
+
     Returns
     -------
     X : list of input arrays, as modified by check_array
+
     """
     kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
                       'force_same_dim': False, 'force_same_n_axis': True}
@@ -212,18 +218,34 @@ def check_list_of_point_clouds(X, **kwargs):
     return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_list_of_arrays(X, **kwargs):
+def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
+                         **kwargs):
     """"Check a list of arrays, by integrating through the input one by one.
+    The constraints are to be specified in :param:`kwargs`. On top of
+    parameters from :func:`~sklearn.utils.validation.check_array`,
+    the optional parameters are listed below.
+
     Parameters
     ----------
     X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
+
+    force_same_dim : bool, optional, default: ``True``
+        Indicates whether the shapes of the elements of X should all
+        be the same.
+
+    force_same_n_axis : bool, optional, default: ``True``
+        Indicates whether the number of axes in the elements of X should all
+        be the same.
+
+    kwargs: dict or None, optional, default: ``None``
+        Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
+
     Returns
     -------
     X : list of input arrays, as modified by check_array
+
     """
-    force_same_dim = kwargs.pop('force_same_dim', True)
-    force_same_n_axis = kwargs.pop('force_same_n_axis', True)
 
     # if restrictions on the dimensions of the input are imposed
     if force_same_dim:

From 6faf94aabaa6be9f94b5c8b0af964ab17369f809 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 11:38:31 +0100
Subject: [PATCH 14/45] Work on docstring for check images  and point cloud
 functions

---
 gtda/utils/validation.py | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 637568b61..8f1441988 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -181,19 +181,26 @@ def validate_metric_params(metric, metric_params):
 def check_list_of_images(X, **kwargs):
     """"Check a list of arrays representing images, by integrating
     through the input one by one. To pass a test with
-    :param:`kwargs`=None
+    :param:`kwargs`=``None``, all images x in X must satisfy:
+        - x.ndim >= 2,
+        - all(np.isfinite(x))
 
     Parameters
     ----------
     X : list of ndarray,
         Each entry of X corresponds to an image.
+
+    kwargs: dict or None, optional, default: ``None``
+        Parameters accepted by
+        :func:`~gtda.utils.validation.check_list_of_arrays`.
+
     Returns
     -------
     X : list of ndarray, as modified by check_array
 
     """
     kwargs_default = {'force_same_n_axis':  False,
-                      'force_same_dim': True, 'force_all_finite': True,
+                      'force_same_dim': False, 'force_all_finite': True,
                       'ensure_2d': False, 'allow_nd': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
@@ -201,12 +208,20 @@ def check_list_of_images(X, **kwargs):
 
 def check_list_of_point_clouds(X, **kwargs):
     """"Check a list of arrays representing point clouds, by integrating
-    through the input one by one.
+    through the input one by one. To pass a test with
+    :param:`kwargs`=``None``, all point clouds x, y in X must satisfy:
+        - x.ndim == 2,
+        - len(y.shape) == len(y.shape).
+
     Parameters
     ----------
     X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
 
+    kwargs: dict or None, optional, default: ``None``
+        Parameters accepted by
+        :func:`~gtda.utils.validation.check_list_of_arrays`.
+
     Returns
     -------
     X : list of input arrays, as modified by check_array

From 2c445d7eca2e2a21fc41f1a108f7e6e7800da0e4 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 15:26:14 +0100
Subject: [PATCH 15/45] Fix docstring issues

---
 gtda/utils/validation.py | 49 +++++++++++++++++++++-------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 8f1441988..d21278cf1 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -179,24 +179,25 @@ def validate_metric_params(metric, metric_params):
 
 
 def check_list_of_images(X, **kwargs):
-    """"Check a list of arrays representing images, by integrating
-    through the input one by one. To pass a test with
-    :param:`kwargs`=``None``, all images x in X must satisfy:
-        - x.ndim >= 2,
-        - all(np.isfinite(x))
+    """Check a list of arrays representing images, by integrating
+    through the input one by one. To pass a test when `kwargs` is ``None``,
+    all images ``x`` in `X` must satisfy:
+        - ``x.ndim`` >= 2,
+        - ``all(np.isfinite(x))``
 
     Parameters
     ----------
-    X : list of ndarray,
-        Each entry of X corresponds to an image.
+    X : list of ndarray
+        Each entry of `X` corresponds to an image.
 
-    kwargs: dict or None, optional, default: ``None``
+    kwargs : dict or None, optional, default: ``None``
         Parameters accepted by
         :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Returns
     -------
-    X : list of ndarray, as modified by check_array
+    X : list of ndarray
+        as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
     kwargs_default = {'force_same_n_axis':  False,
@@ -207,24 +208,25 @@ def check_list_of_images(X, **kwargs):
 
 
 def check_list_of_point_clouds(X, **kwargs):
-    """"Check a list of arrays representing point clouds, by integrating
-    through the input one by one. To pass a test with
-    :param:`kwargs`=``None``, all point clouds x, y in X must satisfy:
-        - x.ndim == 2,
-        - len(y.shape) == len(y.shape).
+    """Check a list of arrays representing point clouds, by integrating
+    through the input one by one. To pass a test when `kwargs` is ``None``,
+    all point clouds ``x``, ``y`` in X must satisfy:
+        - ``x.ndim == 2``,
+        - ``len(y.shape) == len(y.shape)``.
 
     Parameters
     ----------
-    X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
+    X : list of ndarray, such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    kwargs: dict or None, optional, default: ``None``
+    kwargs : dict or None, optional, default: ``None``
         Parameters accepted by
         :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Returns
     -------
-    X : list of input arrays, as modified by check_array
+    X : list of input arrays
+        as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
     kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
@@ -235,7 +237,7 @@ def check_list_of_point_clouds(X, **kwargs):
 
 def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
                          **kwargs):
-    """"Check a list of arrays, by integrating through the input one by one.
+    """Check a list of arrays, by integrating through the input one by one.
     The constraints are to be specified in :param:`kwargs`. On top of
     parameters from :func:`~sklearn.utils.validation.check_array`,
     the optional parameters are listed below.
@@ -258,7 +260,8 @@ def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
 
     Returns
     -------
-    X : list of input arrays, as modified by check_array
+    X : list of input arrays
+        as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
 
@@ -266,14 +269,14 @@ def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
     if force_same_dim:
         shapes = [x.shape for x in X]
         if not(all([shapes[0] == s for s in shapes])):
-            raise ValueError("The arrays in X do not have the same dimensions"
-                             "({}), while they should.".format(shapes))
+            raise ValueError(f"The arrays in X do not have the same dimensions"
+                             "({shapes}), while they should.")
     # if the number of dimensions can vary
     if force_same_n_axis:
         n_axis = [len(x.shape) for x in X]
         if not(all([n_axis[0] == n for n in n_axis])):
-            raise ValueError("The arrays in X do not have the same number"
-                             "of axes ({}), while they should.".format(n_axis))
+            raise ValueError(f"The arrays in X do not have the same number"
+                             "of axes ({n_axis}), while they should.")
 
     results = []
     messages = []

From 4219e82d20e97271b63c8904288f33091c1695ab Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 15:28:16 +0100
Subject: [PATCH 16/45] Rename force_same_dim to force_same_shape

---
 gtda/utils/validation.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index d21278cf1..89384f8c5 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -201,7 +201,7 @@ def check_list_of_images(X, **kwargs):
 
     """
     kwargs_default = {'force_same_n_axis':  False,
-                      'force_same_dim': False, 'force_all_finite': True,
+                      'force_same_shape': False, 'force_all_finite': True,
                       'ensure_2d': False, 'allow_nd': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
@@ -230,12 +230,12 @@ def check_list_of_point_clouds(X, **kwargs):
 
     """
     kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
-                      'force_same_dim': False, 'force_same_n_axis': True}
+                      'force_same_shape': False, 'force_same_n_axis': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
+def check_list_of_arrays(X, force_same_shape=True, force_same_n_axis=True,
                          **kwargs):
     """Check a list of arrays, by integrating through the input one by one.
     The constraints are to be specified in :param:`kwargs`. On top of
@@ -247,7 +247,7 @@ def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
     X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    force_same_dim : bool, optional, default: ``True``
+    force_same_shape : bool, optional, default: ``True``
         Indicates whether the shapes of the elements of X should all
         be the same.
 
@@ -266,7 +266,7 @@ def check_list_of_arrays(X, force_same_dim=True, force_same_n_axis=True,
     """
 
     # if restrictions on the dimensions of the input are imposed
-    if force_same_dim:
+    if force_same_shape:
         shapes = [x.shape for x in X]
         if not(all([shapes[0] == s for s in shapes])):
             raise ValueError(f"The arrays in X do not have the same dimensions"

From cb03ee450c71be94f1a3615700e136b19a79773e Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 15:56:37 +0100
Subject: [PATCH 17/45] Remove list of results, andreplaceitwith aflag
 parameter, put ToDo

---
 gtda/utils/validation.py | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 89384f8c5..bece4fb25 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -86,7 +86,7 @@ def validate_params(parameters, references):
         if len(references[key]) == 1:
             continue
         if references[key][0] == list or \
-           references[key][0] == np.ndarray:
+                references[key][0] == np.ndarray:
             for parameter in parameters[key]:
                 if references[key][1][0] == int:
                     if not isinstance(parameter, numbers.Number):
@@ -164,7 +164,7 @@ def validate_metric_params(metric, metric_params):
                                           param_type))
             if param_values is not None:
                 if input_param < param_values[0] or \
-                   input_param > param_values[1]:
+                        input_param > param_values[1]:
                     raise ValueError("{} in param_metric should be between {} "
                                      "and {} but has been set to {}."
                                      "".format(param, param_values[0],
@@ -200,7 +200,7 @@ def check_list_of_images(X, **kwargs):
         as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
-    kwargs_default = {'force_same_n_axis':  False,
+    kwargs_default = {'force_same_n_axis': False,
                       'force_same_shape': False, 'force_all_finite': True,
                       'ensure_2d': False, 'allow_nd': True}
     kwargs_default.update(kwargs)
@@ -268,28 +268,28 @@ def check_list_of_arrays(X, force_same_shape=True, force_same_n_axis=True,
     # if restrictions on the dimensions of the input are imposed
     if force_same_shape:
         shapes = [x.shape for x in X]
-        if not(all([shapes[0] == s for s in shapes])):
+        if not (all([shapes[0] == s for s in shapes])):
             raise ValueError(f"The arrays in X do not have the same dimensions"
                              "({shapes}), while they should.")
     # if the number of dimensions can vary
-    if force_same_n_axis:
-        n_axis = [len(x.shape) for x in X]
-        if not(all([n_axis[0] == n for n in n_axis])):
+    elif force_same_n_axis:
+        n_axis = [x.ndim for x in X]
+        if not (all([n_axis[0] == n for n in n_axis])):
             raise ValueError(f"The arrays in X do not have the same number"
                              "of axes ({n_axis}), while they should.")
 
-    results = []
+    is_check_failed = False
     messages = []
-    for id_x, x in enumerate(X):
+    for i, x in enumerate(X):
         try:
-            X[id_x] = check_array(x, **kwargs)
-            results.append(True)
+            # TODO: verifythe behavior depending on copy.
+            X[i] = check_array(x, **kwargs)
             messages = ['']
         except ValueError as e:
-            results.append(False)
+            is_check_failed = True
             messages.append(str(e))
-    if all(results):
-        return X
-    else:
+    if is_check_failed:
         raise ValueError("The following errors were raised" +
                          "by the inputs: \n" + "\n".join(messages))
+    else:
+        return X

From 2af6d380c25f9ebc77cc99a24d130cfc1ad8ec5a Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Fri, 21 Feb 2020 15:59:26 +0100
Subject: [PATCH 18/45] Change force_same_n_axis to force_same_ndim and fix a
 docstring

---
 gtda/utils/validation.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index bece4fb25..50cdc4ba7 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -182,7 +182,7 @@ def check_list_of_images(X, **kwargs):
     """Check a list of arrays representing images, by integrating
     through the input one by one. To pass a test when `kwargs` is ``None``,
     all images ``x`` in `X` must satisfy:
-        - ``x.ndim`` >= 2,
+        - ``x.ndim >= 2``,
         - ``all(np.isfinite(x))``
 
     Parameters
@@ -200,7 +200,7 @@ def check_list_of_images(X, **kwargs):
         as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
-    kwargs_default = {'force_same_n_axis': False,
+    kwargs_default = {'force_same_ndim': False,
                       'force_same_shape': False, 'force_all_finite': True,
                       'ensure_2d': False, 'allow_nd': True}
     kwargs_default.update(kwargs)
@@ -230,12 +230,12 @@ def check_list_of_point_clouds(X, **kwargs):
 
     """
     kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
-                      'force_same_shape': False, 'force_same_n_axis': True}
+                      'force_same_shape': False, 'force_same_ndim': True}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_list_of_arrays(X, force_same_shape=True, force_same_n_axis=True,
+def check_list_of_arrays(X, force_same_shape=True, force_same_ndim=True,
                          **kwargs):
     """Check a list of arrays, by integrating through the input one by one.
     The constraints are to be specified in :param:`kwargs`. On top of
@@ -251,7 +251,7 @@ def check_list_of_arrays(X, force_same_shape=True, force_same_n_axis=True,
         Indicates whether the shapes of the elements of X should all
         be the same.
 
-    force_same_n_axis : bool, optional, default: ``True``
+    force_same_ndim : bool, optional, default: ``True``
         Indicates whether the number of axes in the elements of X should all
         be the same.
 
@@ -272,7 +272,7 @@ def check_list_of_arrays(X, force_same_shape=True, force_same_n_axis=True,
             raise ValueError(f"The arrays in X do not have the same dimensions"
                              "({shapes}), while they should.")
     # if the number of dimensions can vary
-    elif force_same_n_axis:
+    elif force_same_ndim:
         n_axis = [x.ndim for x in X]
         if not (all([n_axis[0] == n for n in n_axis])):
             raise ValueError(f"The arrays in X do not have the same number"

From 596bab643a8472b327fe5530c10546fef9ded0c4 Mon Sep 17 00:00:00 2001
From: Umberto Lupo <46537483+ulupo@users.noreply.github.com>
Date: Fri, 21 Feb 2020 18:56:31 +0100
Subject: [PATCH 19/45] Docstring fixes

---
 gtda/utils/validation.py | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 50cdc4ba7..78f379cac 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -216,7 +216,7 @@ def check_list_of_point_clouds(X, **kwargs):
 
     Parameters
     ----------
-    X : list of ndarray, such that `X[i].ndim==2` (n_points, n_dimensions),
+    X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
         or an array `X.dim==3`
 
     kwargs : dict or None, optional, default: ``None``
@@ -237,31 +237,33 @@ def check_list_of_point_clouds(X, **kwargs):
 
 def check_list_of_arrays(X, force_same_shape=True, force_same_ndim=True,
                          **kwargs):
-    """Check a list of arrays, by integrating through the input one by one.
-    The constraints are to be specified in :param:`kwargs`. On top of
+    """Input validation on a list of lists, arrays, sparse matrices, or similar.
+
+    The constraints are to be specified in `kwargs`. On top of
     parameters from :func:`~sklearn.utils.validation.check_array`,
     the optional parameters are listed below.
 
     Parameters
     ----------
-    X : list(ndarray), such that `X[i].ndim==2` (n_points, n_dimensions),
-        or an array `X.dim==3`
+    X : list
+        Input list of objects to check / convert.
 
     force_same_shape : bool, optional, default: ``True``
-        Indicates whether the shapes of the elements of X should all
+        Indicates whether the shapes of the elements of `X` should all
         be the same.
 
     force_same_ndim : bool, optional, default: ``True``
-        Indicates whether the number of axes in the elements of X should all
+        Indicates whether the number of axes in the elements of `X` should all
         be the same.
 
-    kwargs: dict or None, optional, default: ``None``
+    kwargs : dict or None, optional, default: ``None``
         Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
 
     Returns
     -------
-    X : list of input arrays
-        as modified by :func:`~sklearn.utils.validation.check_array`
+    X : list
+        Output list of objects, each checked / converted by
+        :func:`~sklearn.utils.validation.check_array`
 
     """
 

From cb96cbd18d2e7007eb0ac09c0b4ce8a894d06404 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 09:19:02 +0100
Subject: [PATCH 20/45] Remove  redundant lines for test results definitions
 for ImageToPointCloud

---
 gtda/images/tests/test_preprocessing.py | 28 -------------------------
 1 file changed, 28 deletions(-)

diff --git a/gtda/images/tests/test_preprocessing.py b/gtda/images/tests/test_preprocessing.py
index 3b877960e..1f4ebe8d8 100644
--- a/gtda/images/tests/test_preprocessing.py
+++ b/gtda/images/tests/test_preprocessing.py
@@ -108,34 +108,6 @@ def test_img2pc_not_fitted():
         img2pc.transform(images_2D)
 
 
-images_2D_img2pc = np.array(
-    [[[0., 2.], [1., 2.], [0., 1.],
-      [1., 1.], [0., 0.], [1., 0.]],
-     [[0., 2.], [np.inf, np.inf], [0., 1.],
-      [np.inf, np.inf], [0., 0.], [np.inf, np.inf]],
-     [[np.inf, np.inf], [np.inf, np.inf], [np.inf, np.inf],
-      [np.inf, np.inf], [np.inf, np.inf], [np.inf, np.inf]]])
-
-images_3D_img2pc = np.array(
-    [[[0., 2., 0.], [0., 2., 1.],
-      [1., 2., 0.], [1., 2., 1.],
-      [0., 1., 0.], [0., 1., 1.],
-      [1., 1., 0.], [1., 1., 1.],
-      [0., 0., 0.], [0., 0., 1.],
-      [1., 0., 0.], [1., 0., 1.]],
-     [[0., 2., 0.], [0., 2., 1.],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [0., 1., 0.], [0., 1., 1.],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [0., 0., 0.], [0., 0., 1.],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf]],
-     [[np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf],
-      [np.inf, np.inf, np.inf], [np.inf, np.inf, np.inf]]])
-
 images_2D_img2pc = list(
     [np.array([[0., 2.], [1., 2.], [0., 1.], [1., 1.], [0., 0.], [1., 0.]]),
      np.array([[0., 2.], [0., 1.], [0., 0.]]),

From 11fcfc8b7e8a671f5a610ed891ef4dbf393467e7 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 10:48:58 +0100
Subject: [PATCH 21/45] Modularizethe checks with lambda functions. Modify the
 tests in test_simplicial (tests for ok and invalid shapes respectively)

---
 gtda/homology/tests/test_simplicial.py |  9 +++--
 gtda/utils/validation.py               | 53 ++++++++++++++------------
 2 files changed, 35 insertions(+), 27 deletions(-)

diff --git a/gtda/homology/tests/test_simplicial.py b/gtda/homology/tests/test_simplicial.py
index f18c91d44..38292053f 100644
--- a/gtda/homology/tests/test_simplicial.py
+++ b/gtda/homology/tests/test_simplicial.py
@@ -100,14 +100,17 @@ def test_cp_transform():
 
 
 def test_vrp_list_of_arrays():
-    pc_2 = np.array([[0, 1, 2], [1, 2, 4]])
+    """Verify that a list of point clouds"""
+    pc_2 = np.array([[0, 1], [1, 2]])
     pc_list = [pc[0].copy(), pc_2]
     vrp = VietorisRipsPersistence()
     vrp.fit(pc_list)
 
 
 def test_vrp_list_invalid_arrays():
-    pc_invalid = np.array([0, 1])
+    pc_2 = np.array([[0, 1, 2]])
+    pc_invalid = [pc[0].copy(), pc_2]
+
     vrp = VietorisRipsPersistence()
     with pytest.raises(ValueError):
-        vrp.fit([pc_invalid])
+        vrp.fit(pc_invalid)
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index f18cf7115..37d7442ca 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -242,9 +242,12 @@ def check_list_of_images(X, **kwargs):
         as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
-    kwargs_default = {'force_same_ndim': False,
-                      'force_same_shape': False, 'force_all_finite': True,
-                      'ensure_2d': False, 'allow_nd': True}
+    kwargs_default = {'force_all_finite': True,
+                      'ensure_2d': False, 'allow_nd': True,
+                      'check_shapes': [('embedding_dimension',
+                                        lambda x: x.shape,
+                                        'The images should have exactly'
+                                        'the same shape')]}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
@@ -272,13 +275,24 @@ def check_list_of_point_clouds(X, **kwargs):
 
     """
     kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
-                      'force_same_shape': False, 'force_same_ndim': True}
+                      'check_shapes': [('embedding_dimension',
+                                        lambda x: x.shape[1:],
+                                        'Not all point clouds have the same'
+                                        'embedding dimension')]}
     kwargs_default.update(kwargs)
     return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_list_of_arrays(X, force_same_shape=True, force_same_ndim=True,
-                         **kwargs):
+def check_dimensions(X, get_property):
+    """ """
+    from functools import reduce
+    from operator import and_
+    reference = get_property(X[0])
+    return reduce(and_, map(lambda x: get_property(x) == reference, X[1:]),
+                  True)
+
+
+def check_list_of_arrays(X, check_shapes=list(), **kwargs):
     """Input validation on a list of lists, arrays, sparse matrices, or similar.
 
     The constraints are to be specified in `kwargs`. On top of
@@ -290,13 +304,10 @@ def check_list_of_arrays(X, force_same_shape=True, force_same_ndim=True,
     X : list
         Input list of objects to check / convert.
 
-    force_same_shape : bool, optional, default: ``True``
-        Indicates whether the shapes of the elements of `X` should all
-        be the same.
-
-    force_same_ndim : bool, optional, default: ``True``
-        Indicates whether the number of axes in the elements of `X` should all
-        be the same.
+    check_shapes: list of tuples t, where t = (str, function to pass to
+        check_dimensions, error message if test fails).
+        The checks are applied in the order they are provided, only until
+        the first failure.
 
     kwargs : dict or None, optional, default: ``None``
         Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
@@ -310,17 +321,11 @@ def check_list_of_arrays(X, force_same_shape=True, force_same_ndim=True,
     """
 
     # if restrictions on the dimensions of the input are imposed
-    if force_same_shape:
-        shapes = [x.shape for x in X]
-        if not (all([shapes[0] == s for s in shapes])):
-            raise ValueError(f"The arrays in X do not have the same dimensions"
-                             "({shapes}), while they should.")
-    # if the number of dimensions can vary
-    elif force_same_ndim:
-        n_axis = [x.ndim for x in X]
-        if not (all([n_axis[0] == n for n in n_axis])):
-            raise ValueError(f"The arrays in X do not have the same number"
-                             "of axes ({n_axis}), while they should.")
+    for (test_name, get_property, err_message) in check_shapes:
+        if check_dimensions(X, get_property):
+            continue
+        else:
+            raise ValueError(err_message)
 
     is_check_failed = False
     messages = []

From d349c89f47e4efafde044735e9eae29b75cdc024 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 11:15:17 +0100
Subject: [PATCH 22/45] Add a docstring in check_dimensions

---
 gtda/utils/validation.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 37d7442ca..f1aa2b6c4 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -266,7 +266,7 @@ def check_list_of_point_clouds(X, **kwargs):
 
     kwargs : dict or None, optional, default: ``None``
         Parameters accepted by
-        :func:`~gtda.utils.validation.check_list_of_arrays`.
+        :func:`~`gtda.utils.validation.check_list_of_arrays``.
 
     Returns
     -------
@@ -284,7 +284,19 @@ def check_list_of_point_clouds(X, **kwargs):
 
 
 def check_dimensions(X, get_property):
-    """ """
+    """Check the dimensions of X are consistent, where the check is defined
+    by get_property 'sample-wise'.
+    Parameters
+    ----------
+    X: list of ndarray,
+        Usually represents point clouds or images- see
+        :func:`~`gtda.utils.validation.check_list_of_arrays``.
+
+    get_property: function: ndarray -> _,
+        Defines a property to be conserved, across all arrays (samples)
+        in X.
+    
+    """
     from functools import reduce
     from operator import and_
     reference = get_property(X[0])

From 54cacbdd979fc831eb73bc966097eace19579905 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 11:19:38 +0100
Subject: [PATCH 23/45] Adapt the docstrings of check_list_of_point_clouds and
 check_list_of_images, to match the logic agreed upon

---
 gtda/utils/validation.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index f1aa2b6c4..e7c6a4ea2 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -223,9 +223,10 @@ def validate_metric_params(metric, metric_params):
 def check_list_of_images(X, **kwargs):
     """Check a list of arrays representing images, by integrating
     through the input one by one. To pass a test when `kwargs` is ``None``,
-    all images ``x`` in `X` must satisfy:
+    all images ``x``, ``y`` in `X` must satisfy:
         - ``x.ndim >= 2``,
-        - ``all(np.isfinite(x))``
+        - ``all(np.isfinite(x))``,
+        - ``x.shape == y.shape``.
 
     Parameters
     ----------
@@ -257,7 +258,7 @@ def check_list_of_point_clouds(X, **kwargs):
     through the input one by one. To pass a test when `kwargs` is ``None``,
     all point clouds ``x``, ``y`` in X must satisfy:
         - ``x.ndim == 2``,
-        - ``len(y.shape) == len(y.shape)``.
+        - ``len(y.shape[1:]) == len(y.shape[1:])``.
 
     Parameters
     ----------
@@ -295,7 +296,7 @@ def check_dimensions(X, get_property):
     get_property: function: ndarray -> _,
         Defines a property to be conserved, across all arrays (samples)
         in X.
-    
+
     """
     from functools import reduce
     from operator import and_

From 3ed0dad93ce4678b70afe437722e62bee2ad28f5 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 16:43:35 +0100
Subject: [PATCH 24/45] Add falling back to check_array if the input is really
 an array

---
 gtda/homology/cubical.py    |  4 ++--
 gtda/homology/simplicial.py | 18 +++++++++++------
 gtda/utils/validation.py    | 39 ++++++++++++++++++++++---------------
 3 files changed, 37 insertions(+), 24 deletions(-)

diff --git a/gtda/homology/cubical.py b/gtda/homology/cubical.py
index bf6875dad..c1cc83d90 100644
--- a/gtda/homology/cubical.py
+++ b/gtda/homology/cubical.py
@@ -7,7 +7,7 @@
 from joblib import Parallel, delayed
 from sklearn.utils.validation import check_is_fitted
 from ._utils import _pad_diagram
-from ..utils.validation import validate_params, check_list_of_arrays
+from ..utils.validation import validate_params, check_list_of_images
 
 from ..externals.python import CubicalComplex, PeriodicCubicalComplex
 
@@ -158,7 +158,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_arrays(X, allow_nd=True)
+        check_list_of_images(X, allow_nd=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
diff --git a/gtda/homology/simplicial.py b/gtda/homology/simplicial.py
index 219e8e55f..5f5a8a507 100644
--- a/gtda/homology/simplicial.py
+++ b/gtda/homology/simplicial.py
@@ -165,7 +165,8 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
+        check_list_of_point_clouds(X, ensure_2d=False, allow_nd=True,
+                                   force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -207,7 +208,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=True,
+        X = check_list_of_point_clouds(X, ensure_2d=False,
+                                       allow_nd=True,
                                        force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
@@ -382,7 +384,9 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_point_clouds(X, ensure_2d=True, force_all_finite=False)
+        check_list_of_point_clouds(X, ensure_2d=False,
+                                   allow_nd=True,
+                                   force_all_finite=False)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -424,7 +428,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=True,
+        X = check_list_of_point_clouds(X, ensure_2d=False,
+                                       allow_nd=True,
                                        force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
@@ -568,7 +573,7 @@ def fit(self, X, y=None):
                          'infinity_values_': self.infinity_values_,
                          '_homology_dimensions': self._homology_dimensions},
                         self._hyperparameters)
-        check_list_of_point_clouds(X, ensure_2d=True)
+        check_list_of_point_clouds(X, ensure_2d=False, allow_nd=True)
 
         self._max_homology_dimension = self._homology_dimensions[-1]
         return self
@@ -605,7 +610,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=True)
+        X = check_list_of_point_clouds(X, ensure_2d=False,
+                                       allow_nd=True,)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index e7c6a4ea2..4d794f115 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -243,14 +243,17 @@ def check_list_of_images(X, **kwargs):
         as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
-    kwargs_default = {'force_all_finite': True,
-                      'ensure_2d': False, 'allow_nd': True,
-                      'check_shapes': [('embedding_dimension',
-                                        lambda x: x.shape,
-                                        'The images should have exactly'
-                                        'the same shape')]}
-    kwargs_default.update(kwargs)
-    return check_list_of_arrays(X, **kwargs_default)
+    if hasattr(X, 'shape'):
+        return check_array(X, **kwargs)
+    else:
+        kwargs_default = {'force_all_finite': True,
+                          'ensure_2d': False, 'allow_nd': True,
+                          'check_shapes': [('embedding_dimension',
+                                            lambda x: x.shape,
+                                            'The images should have exactly'
+                                            'the same shape')]}
+        kwargs_default.update(kwargs)
+        return check_list_of_arrays(X, **kwargs_default)
 
 
 def check_list_of_point_clouds(X, **kwargs):
@@ -275,13 +278,16 @@ def check_list_of_point_clouds(X, **kwargs):
         as modified by :func:`~sklearn.utils.validation.check_array`
 
     """
-    kwargs_default = {'ensure_2d': True, 'force_all_finite': False,
-                      'check_shapes': [('embedding_dimension',
-                                        lambda x: x.shape[1:],
-                                        'Not all point clouds have the same'
-                                        'embedding dimension')]}
-    kwargs_default.update(kwargs)
-    return check_list_of_arrays(X, **kwargs_default)
+    if hasattr(X, 'shape'):
+        return check_array(X, **kwargs)
+    else:
+        kwargs_default = {'ensure_2d': False, 'force_all_finite': False,
+                          'check_shapes': [('embedding_dimension',
+                                            lambda x: x.shape[1:],
+                                            'Not all point clouds have the same'
+                                            'embedding dimension')]}
+        kwargs_default.update(kwargs)
+        return check_list_of_arrays(X, **kwargs_default)
 
 
 def check_dimensions(X, get_property):
@@ -345,7 +351,8 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
     for i, x in enumerate(X):
         try:
             # TODO: verifythe behavior depending on copy.
-            X[i] = check_array(x, **kwargs)
+            X[i] = check_array(x.reshape(1, *x.shape),
+                               **kwargs).reshape(*x.shape)
             messages = ['']
         except ValueError as e:
             is_check_failed = True

From be1bcf9373da13cac03969007b8d6e3a3f1fe62d Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 2 Mar 2020 23:01:06 +0100
Subject: [PATCH 25/45] Fix linting invalidation

---
 gtda/utils/validation.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 4d794f115..d91e31d1d 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -284,8 +284,8 @@ def check_list_of_point_clouds(X, **kwargs):
         kwargs_default = {'ensure_2d': False, 'force_all_finite': False,
                           'check_shapes': [('embedding_dimension',
                                             lambda x: x.shape[1:],
-                                            'Not all point clouds have the same'
-                                            'embedding dimension')]}
+                                            'Not all point clouds have the '
+                                            'same embedding dimension.')]}
         kwargs_default.update(kwargs)
         return check_list_of_arrays(X, **kwargs_default)
 

From 0d2f0b8890b9b9c45f1ae83280f4d04238299881 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Tue, 3 Mar 2020 09:25:15 +0100
Subject: [PATCH 26/45] Add a fail on small dimensional-images

---
 gtda/utils/validation.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index d91e31d1d..cfc138714 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -244,6 +244,10 @@ def check_list_of_images(X, **kwargs):
 
     """
     if hasattr(X, 'shape'):
+        if X.ndim < 3:
+            raise ValueError(f"An image in the collection X should be at "
+                             f"least of dimension 2, while it has dimension "
+                             f"{X.ndim - 1}.")
         return check_array(X, **kwargs)
     else:
         kwargs_default = {'force_all_finite': True,

From e719a8fb6293ad93374a5f2d1b42b8eb96828da3 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Sun, 8 Mar 2020 21:18:41 +0100
Subject: [PATCH 27/45] Merge  master into pcs_different_sizes

---
 gtda/diagrams/features.py    | 6 +++---
 gtda/homology/simplicial.py  | 3 +--
 gtda/images/filtrations.py   | 2 +-
 gtda/images/preprocessing.py | 4 ++--
 gtda/utils/validation.py     | 2 +-
 5 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/gtda/diagrams/features.py b/gtda/diagrams/features.py
index ec3e0b994..31b826e9c 100644
--- a/gtda/diagrams/features.py
+++ b/gtda/diagrams/features.py
@@ -569,9 +569,9 @@ class PersistenceImage(BaseEstimator, TransformerMixin):
         dimension, to sample during :meth:`fit`.
 
     weight_function : callable or None, default: ``None``
-        Function mapping the 1D array of persistence values of the points of an
-        input diagram to a 1D array of weights. ``None`` is equivalent to passing
-        the identity function.
+        Function mapping the 1D array of persistence values of the points of
+        an input diagram to a 1D array of weights. ``None`` is equivalent to
+        passing the identity function.
 
     n_jobs : int or None, optional, default: ``None``
         The number of jobs to use for the computation. ``None`` means 1 unless
diff --git a/gtda/homology/simplicial.py b/gtda/homology/simplicial.py
index 9a0416973..f28cd7d5b 100644
--- a/gtda/homology/simplicial.py
+++ b/gtda/homology/simplicial.py
@@ -9,7 +9,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 
 from sklearn.metrics.pairwise import pairwise_distances
-from sklearn.utils.validation import check_array, check_is_fitted
+from sklearn.utils.validation import check_is_fitted
 
 from ._utils import _postprocess_diagrams
 from ..externals.python import ripser, SparseRipsComplex, CechComplex
@@ -19,7 +19,6 @@
 from ..utils.validation import validate_params, check_list_of_point_clouds
 
 
-
 @adapt_fit_transform_docs
 class VietorisRipsPersistence(BaseEstimator, TransformerMixin):
     """`Persistence diagrams <https://giotto.ai/theory>`_ resulting from
diff --git a/gtda/images/filtrations.py b/gtda/images/filtrations.py
index 2ecdae0c6..99465c6a8 100644
--- a/gtda/images/filtrations.py
+++ b/gtda/images/filtrations.py
@@ -11,7 +11,7 @@
 from sklearn.metrics import pairwise_distances
 from sklearn.utils import gen_even_slices
 
-from sklearn.utils.validation import check_is_fitted, check_array
+from sklearn.utils.validation import check_is_fitted
 
 from ._utils import _dilate, _erode
 from ..utils._docs import adapt_fit_transform_docs
diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index de953428b..919c0e88e 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -9,7 +9,7 @@
 from joblib import Parallel, delayed, effective_n_jobs
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.utils import gen_even_slices
-from sklearn.utils.validation import check_is_fitted, check_array
+from sklearn.utils.validation import check_is_fitted
 
 from ..utils._docs import adapt_fit_transform_docs
 from ..utils.intervals import Interval
@@ -372,7 +372,7 @@ def __init__(self, n_jobs=None):
         self.n_jobs = n_jobs
 
     def _embed(self, X):
-        #Xpts = [np.stack(np.nonzero(x), axis=1) for x in X]
+        # Xpts = [np.stack(np.nonzero(x), axis=1) for x in X]
         Xpts = np.stack([self.mesh_ for _ in range(X.shape[0])]) * 1.
         Xpts[np.logical_not(X.reshape((X.shape[0], -1))), :] += np.inf
         return Xpts
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 1c4dd9908..1a468dcd9 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -2,10 +2,10 @@
 # License: GNU AGPLv3
 
 import numpy as np
-import types
 
 from sklearn.utils.validation import check_array
 
+
 def check_diagram(X, copy=False):
     """Input validation on a persistence diagram.
 

From 315575a6ac6f550f714ed6e908dbbfd5b2c64266 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 9 Mar 2020 09:00:26 +0100
Subject: [PATCH 28/45] Change docstrings on kwargs in utils.validation

---
 gtda/utils/validation.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 1a468dcd9..339224e48 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -159,8 +159,8 @@ def validate_params(parameters, references, exclude=None):
 
 
 def check_list_of_images(X, **kwargs):
-    """Check a list of arrays representing images, by integrating
-    through the input one by one. To pass a test when `kwargs` is ``None``,
+    """Check a list of arrays representing images, by iterating through
+    the input one by one. To pass a test when `kwargs` is empty,
     all images ``x``, ``y`` in `X` must satisfy:
         - ``x.ndim >= 2``,
         - ``all(np.isfinite(x))``,
@@ -171,7 +171,7 @@ def check_list_of_images(X, **kwargs):
     X : list of ndarray
         Each entry of `X` corresponds to an image.
 
-    kwargs : dict or None, optional, default: ``None``
+    kwargs : dict, optional, default: {}
         Parameters accepted by
         :func:`~gtda.utils.validation.check_list_of_arrays`.
 
@@ -200,7 +200,7 @@ def check_list_of_images(X, **kwargs):
 
 def check_list_of_point_clouds(X, **kwargs):
     """Check a list of arrays representing point clouds, by integrating
-    through the input one by one. To pass a test when `kwargs` is ``None``,
+    through the input one by one. To pass a test when `kwargs` is empty,
     all point clouds ``x``, ``y`` in X must satisfy:
         - ``x.ndim == 2``,
         - ``len(y.shape[1:]) == len(y.shape[1:])``.
@@ -210,7 +210,7 @@ def check_list_of_point_clouds(X, **kwargs):
     X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    kwargs : dict or None, optional, default: ``None``
+    kwargs : dict, optional, default: {}
         Parameters accepted by
         :func:`~`gtda.utils.validation.check_list_of_arrays``.
 
@@ -270,7 +270,7 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
         The checks are applied in the order they are provided, only until
         the first failure.
 
-    kwargs : dict or None, optional, default: ``None``
+    kwargs : dict, optional, default: {}
         Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
 
     Returns

From a648fd15eaf905f577c61d89cd95158fbed47824 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 9 Mar 2020 09:20:46 +0100
Subject: [PATCH 29/45] Add code formatting in docstrings in utils.validation

---
 gtda/utils/validation.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 339224e48..3e6716b55 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -171,7 +171,7 @@ def check_list_of_images(X, **kwargs):
     X : list of ndarray
         Each entry of `X` corresponds to an image.
 
-    kwargs : dict, optional, default: {}
+    kwargs : dict, optional, default: ``{}``
         Parameters accepted by
         :func:`~gtda.utils.validation.check_list_of_arrays`.
 
@@ -210,7 +210,7 @@ def check_list_of_point_clouds(X, **kwargs):
     X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    kwargs : dict, optional, default: {}
+    kwargs : dict, optional, default: ``{}``
         Parameters accepted by
         :func:`~`gtda.utils.validation.check_list_of_arrays``.
 
@@ -270,7 +270,7 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
         The checks are applied in the order they are provided, only until
         the first failure.
 
-    kwargs : dict, optional, default: {}
+    kwargs : dict, optional, default: ``{}``
         Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
 
     Returns

From fc51502ec815b26b41253ed5866506c04447c044 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Mon, 9 Mar 2020 09:58:54 +0100
Subject: [PATCH 30/45] Add sklearn estimator checks known failures

---
 gtda/tests/test_common.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/gtda/tests/test_common.py b/gtda/tests/test_common.py
index 057e55b88..1e9a515f7 100644
--- a/gtda/tests/test_common.py
+++ b/gtda/tests/test_common.py
@@ -27,6 +27,19 @@
                 ],
 }
 
+LISTFAIL_TESTS = ['check_estimators_dtypes', 'check_fit_score_takes_y',
+                  'check_estimators_fit_returns_self',
+                  'check_estimators_fit_returns_self(readonly_memmap=True)',
+                  'check_complex_data', 'check_dtype_object',
+                  'check_estimators_empty_data_messages',
+                  'check_pipeline_consistency', 'check_estimators_nan_inf',
+                  'check_estimators_overwrite_params',
+                  'check_estimator_sparse_data', 'check_estimators_pickle',
+                  'check_fit2d_predict1d', 'check_methods_subset_invariance',
+                  'check_fit2d_1sample', 'check_fit2d_1feature',
+                  'check_dict_unchanged', 'check_dont_overwrite_parameters',
+                  'check_fit_idempotent']
+
 
 # adapted from sklearn.utils.estimator_check v0.22
 def _get_callable_name(obj):
@@ -86,4 +99,8 @@ def test_sklearn_api(check, estimator, request):
         request.applymarker(pytest.mark.xfail(
             run=True, reason='known failure'))
 
+    if check_name in LISTFAIL_TESTS:
+        request.applymarker(pytest.mark.xfail(
+            run=True, reason='Known failure: 2d input.'))
+
     check(estimator)

From eb3aca4ee539f30ecc35d0bd38c4d241f46e3693 Mon Sep 17 00:00:00 2001
From: Wojciech Reise <reisewojtus@gmail.com>
Date: Thu, 12 Mar 2020 09:03:37 +0100
Subject: [PATCH 31/45] Change the kwargs docuemntation in validation

---
 gtda/utils/validation.py | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 3e6716b55..bb511ec47 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -171,9 +171,9 @@ def check_list_of_images(X, **kwargs):
     X : list of ndarray
         Each entry of `X` corresponds to an image.
 
-    kwargs : dict, optional, default: ``{}``
-        Parameters accepted by
-        :func:`~gtda.utils.validation.check_list_of_arrays`.
+    kwargs :
+        Keyword arguments. For a list of accepted values, see the documentation
+        of :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Returns
     -------
@@ -210,9 +210,9 @@ def check_list_of_point_clouds(X, **kwargs):
     X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    kwargs : dict, optional, default: ``{}``
-        Parameters accepted by
-        :func:`~`gtda.utils.validation.check_list_of_arrays``.
+    kwargs :
+        Keyword arguments. For a list of accepted values, see the documentation
+        of :func:`~`gtda.utils.validation.check_list_of_arrays``.
 
     Returns
     -------
@@ -270,8 +270,9 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
         The checks are applied in the order they are provided, only until
         the first failure.
 
-    kwargs : dict, optional, default: ``{}``
-        Parameters accepted by :func:`~sklearn.utils.validation.check_array`.
+    kwargs :
+        Keyword arguments. For a list of accepted values, see the documentation
+        of :func:`~sklearn.utils.validation.check_array`.
 
     Returns
     -------

From b5f004234275fee536ce6c2770b8d07f752843fb Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sat, 21 Mar 2020 22:35:23 +0100
Subject: [PATCH 32/45] Rename functions

check_list_of_point_clouds -> check_point_clouds
check_list_of_images -> check_images
---
 gtda/homology/cubical.py     |  4 ++--
 gtda/homology/simplicial.py  | 30 +++++++++++++++---------------
 gtda/images/filtrations.py   | 22 +++++++++++-----------
 gtda/images/preprocessing.py | 18 +++++++++---------
 gtda/utils/validation.py     | 11 +++++------
 5 files changed, 42 insertions(+), 43 deletions(-)

diff --git a/gtda/homology/cubical.py b/gtda/homology/cubical.py
index ae137c96b..87ec462da 100644
--- a/gtda/homology/cubical.py
+++ b/gtda/homology/cubical.py
@@ -14,7 +14,7 @@
 from ..externals.python import CubicalComplex, PeriodicCubicalComplex
 from ..plotting import plot_diagram
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_list_of_images
+from ..utils.validation import validate_params, check_images
 
 
 class CubicalPersistence(BaseEstimator, TransformerMixin, PlotterMixin):
@@ -146,7 +146,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_list_of_images(X, allow_nd=True)
+        check_images(X, allow_nd=True)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
diff --git a/gtda/homology/simplicial.py b/gtda/homology/simplicial.py
index ef0f67006..d8b07d8a4 100644
--- a/gtda/homology/simplicial.py
+++ b/gtda/homology/simplicial.py
@@ -18,7 +18,7 @@
 from ..utils._docs import adapt_fit_transform_docs
 
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_list_of_point_clouds
+from ..utils.validation import validate_params, check_point_clouds
 
 
 @adapt_fit_transform_docs
@@ -169,8 +169,8 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_list_of_point_clouds(X, ensure_2d=False, allow_nd=True,
-                                   force_all_finite=False)
+        check_point_clouds(X, ensure_2d=False, allow_nd=True,
+                           force_all_finite=False)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -220,9 +220,9 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=False,
-                                       allow_nd=True,
-                                       force_all_finite=False)
+        X = check_point_clouds(X, ensure_2d=False,
+                               allow_nd=True,
+                               force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
                                           for i in range(len(X)))
@@ -417,9 +417,9 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_list_of_point_clouds(X, ensure_2d=False,
-                                   allow_nd=True,
-                                   force_all_finite=False)
+        check_point_clouds(X, ensure_2d=False,
+                           allow_nd=True,
+                           force_all_finite=False)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -469,9 +469,9 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=False,
-                                       allow_nd=True,
-                                       force_all_finite=False)
+        X = check_point_clouds(X, ensure_2d=False,
+                               allow_nd=True,
+                               force_all_finite=False)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
@@ -635,7 +635,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_list_of_point_clouds(X, ensure_2d=False, allow_nd=True)
+        check_point_clouds(X, ensure_2d=False, allow_nd=True)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -680,8 +680,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_list_of_point_clouds(X, ensure_2d=False,
-                                       allow_nd=True,)
+        X = check_point_clouds(X, ensure_2d=False,
+                               allow_nd=True, )
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
diff --git a/gtda/images/filtrations.py b/gtda/images/filtrations.py
index cecf7e992..88b712c09 100644
--- a/gtda/images/filtrations.py
+++ b/gtda/images/filtrations.py
@@ -18,7 +18,7 @@
 from ..plotting import plot_heatmap
 from ..utils._docs import adapt_fit_transform_docs
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_list_of_images
+from ..utils.validation import validate_params, check_images
 
 
 @adapt_fit_transform_docs
@@ -116,7 +116,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -171,7 +171,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_height)(X[s])
@@ -337,7 +337,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -398,7 +398,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_radial)(X[s])
@@ -529,7 +529,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
 
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
@@ -572,7 +572,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_dilation)(X[s])
@@ -703,7 +703,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -745,7 +745,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_erosion)(X[s])
@@ -886,7 +886,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -928,7 +928,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_signed_distance)(X[s])
diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index ae03a1023..73e04d19d 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -15,7 +15,7 @@
 from ..plotting import plot_point_cloud, plot_heatmap
 from ..utils._docs import adapt_fit_transform_docs
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_list_of_images
+from ..utils.validation import validate_params, check_images
 
 
 @adapt_fit_transform_docs
@@ -91,7 +91,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -127,7 +127,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._binarize)(Xt[s])
@@ -211,7 +211,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_list_of_images(X, allow_nd=True)
+        X = check_images(X, allow_nd=True)
 
         self._is_fitted = True
         return self
@@ -239,7 +239,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, ['_is_fitted'])
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.logical_not)(Xt[s])
@@ -345,7 +345,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_list_of_images(X, allow_nd=True)
+        check_images(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if n_dimensions < 2 or n_dimensions > 3:
             warn(f"Input of `fit` contains arrays of dimension "
@@ -391,7 +391,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.pad)(Xt[s], pad_width=self._pad_width,
@@ -497,7 +497,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        _ = check_list_of_images(X, allow_nd=True)
+        _ = check_images(X, allow_nd=True)
         self.is_fitted_ = True
         n_dimensions = X.ndim - 1
         if n_dimensions < 2 or n_dimensions > 3:
@@ -538,7 +538,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_list_of_images(X, allow_nd=True, copy=True)
+        Xt = check_images(X, allow_nd=True, copy=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._embed)(Xt[s])
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 042abce23..fcadb35c0 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -183,7 +183,7 @@ def validate_params(parameters, references, exclude=None):
     return _validate_params(parameters_, references)
 
 
-def check_list_of_images(X, **kwargs):
+def check_images(X, **kwargs):
     """Check a list of arrays representing images, by iterating through
     the input one by one. To pass a test when `kwargs` is empty,
     all images ``x``, ``y`` in `X` must satisfy:
@@ -196,7 +196,7 @@ def check_list_of_images(X, **kwargs):
     X : list of ndarray
         Each entry of `X` corresponds to an image.
 
-    kwargs :
+    kwargs
         Keyword arguments. For a list of accepted values, see the documentation
         of :func:`~gtda.utils.validation.check_list_of_arrays`.
 
@@ -223,7 +223,7 @@ def check_list_of_images(X, **kwargs):
         return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_list_of_point_clouds(X, **kwargs):
+def check_point_clouds(X, **kwargs):
     """Check a list of arrays representing point clouds, by integrating
     through the input one by one. To pass a test when `kwargs` is empty,
     all point clouds ``x``, ``y`` in X must satisfy:
@@ -235,7 +235,7 @@ def check_list_of_point_clouds(X, **kwargs):
     X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
         or an array `X.dim==3`
 
-    kwargs :
+    kwargs
         Keyword arguments. For a list of accepted values, see the documentation
         of :func:`~`gtda.utils.validation.check_list_of_arrays``.
 
@@ -306,7 +306,6 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
         :func:`~sklearn.utils.validation.check_array`
 
     """
-
     # if restrictions on the dimensions of the input are imposed
     for (test_name, get_property, err_message) in check_shapes:
         if check_dimensions(X, get_property):
@@ -318,7 +317,7 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
     messages = []
     for i, x in enumerate(X):
         try:
-            # TODO: verifythe behavior depending on copy.
+            # TODO: verify the behavior depending on copy.
             X[i] = check_array(x.reshape(1, *x.shape),
                                **kwargs).reshape(*x.shape)
             messages = ['']

From 72c811d827fd7f07d8b215d2ac33d66b97a9fc3a Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 12:56:32 +0100
Subject: [PATCH 33/45] Fixes in ImageToPointCloud

---
 gtda/images/preprocessing.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index 73e04d19d..c3f405c2b 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -472,7 +472,6 @@ def __init__(self, n_jobs=None):
         self.n_jobs = n_jobs
 
     def _embed(self, X):
-        # Xpts = [np.stack(np.nonzero(x), axis=1) for x in X]
         Xpts = np.stack([self.mesh_ for _ in range(X.shape[0])]) * 1.
         Xpts[np.logical_not(X.reshape((X.shape[0], -1))), :] += np.inf
         return Xpts
@@ -497,8 +496,8 @@ def fit(self, X, y=None):
         self : object
 
         """
-        _ = check_images(X, allow_nd=True)
-        self.is_fitted_ = True
+        check_images(X, allow_nd=True)
+
         n_dimensions = X.ndim - 1
         if n_dimensions < 2 or n_dimensions > 3:
             warn(f"Input of `fit` contains arrays of dimension "

From a41cb5d62d2889c48cba957aa33d26b8dfcf4837 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 18:38:56 +0100
Subject: [PATCH 34/45] Add mapper and utils to global __init__

---
 gtda/__init__.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gtda/__init__.py b/gtda/__init__.py
index 3080a7797..c738ddf0c 100644
--- a/gtda/__init__.py
+++ b/gtda/__init__.py
@@ -1,4 +1,4 @@
 from ._version import __version__
 
-__all__ = ['homology', 'time_series', 'graphs', 'diagrams', 'images',
-           'point_clouds', 'externals', 'plotting', '__version__']
+__all__ = ['mapper', 'homology', 'time_series', 'graphs', 'diagrams', 'images',
+           'utils', 'point_clouds', 'externals', 'plotting', '__version__']

From 4cd196e7ef66f9e446cc222f2c87dd5edd9c903a Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 19:25:10 +0100
Subject: [PATCH 35/45] Make check_shapes a list of pairs, fix validation
 docstrings, revise use of check_array throughout

---
 gtda/diagrams/representations.py  |  9 +++-----
 gtda/graphs/geodesic_distance.py  |  2 +-
 gtda/graphs/kneighbors.py         | 17 ++++++++--------
 gtda/graphs/transition.py         |  5 ++---
 gtda/images/_utils.py             |  3 +--
 gtda/mapper/cover.py              | 32 ++++++++++++++++-------------
 gtda/mapper/filter.py             | 34 +++++++++++++++++--------------
 gtda/plotting/images.py           |  2 --
 gtda/point_clouds/rescaling.py    | 29 +++++++++++++-------------
 gtda/time_series/embedding.py     |  7 ++++---
 gtda/time_series/features.py      |  8 ++++----
 gtda/time_series/multivariate.py  |  2 +-
 gtda/time_series/preprocessing.py |  4 +++-
 gtda/utils/validation.py          | 32 +++++++++++++++--------------
 14 files changed, 96 insertions(+), 90 deletions(-)

diff --git a/gtda/diagrams/representations.py b/gtda/diagrams/representations.py
index f59329895..bda0386fa 100644
--- a/gtda/diagrams/representations.py
+++ b/gtda/diagrams/representations.py
@@ -109,10 +109,10 @@ def fit(self, X, y=None):
 
         self.homology_dimensions_ = sorted(list(set(X[0, :, 2])))
         self._n_dimensions = len(self.homology_dimensions_)
-
         self._samplings, _ = _bin(X, metric='betti', n_bins=self.n_bins)
         self.samplings_ = {dim: s.flatten()
                            for dim, s in self._samplings.items()}
+
         return self
 
     def transform(self, X, y=None):
@@ -319,7 +319,6 @@ def fit(self, X, y=None):
 
         self.homology_dimensions_ = sorted(list(set(X[0, :, 2])))
         self._n_dimensions = len(self.homology_dimensions_)
-
         self._samplings, _ = _bin(X, metric="landscape", n_bins=self.n_bins)
         self.samplings_ = {dim: s.flatten()
                            for dim, s in self._samplings.items()}
@@ -553,11 +552,11 @@ def fit(self, X, y=None):
 
         self.homology_dimensions_ = sorted(list(set(X[0, :, 2])))
         self._n_dimensions = len(self.homology_dimensions_)
-
         self._samplings, self._step_size = _bin(
             X, metric='heat', n_bins=self.n_bins)
         self.samplings_ = {dim: s.flatten()
                            for dim, s in self._samplings.items()}
+
         return self
 
     def transform(self, X, y=None):
@@ -747,7 +746,6 @@ def fit(self, X, y=None):
 
         """
         X = check_diagrams(X)
-
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -758,13 +756,13 @@ def fit(self, X, y=None):
 
         self.homology_dimensions_ = sorted(list(set(X[0, :, 2])))
         self._n_dimensions = len(self.homology_dimensions_)
-
         self._samplings, self._step_size = _bin(
             X, metric='persistence_image', n_bins=self.n_bins)
         self.samplings_ = {dim: s.transpose()
                            for dim, s in self._samplings.items()}
         self.weights_ = _calculate_weights(X, self.effective_weight_function_,
                                            self._samplings)
+
         return self
 
     def transform(self, X, y=None):
@@ -945,7 +943,6 @@ def fit(self, X, y=None):
 
         self.homology_dimensions_ = sorted(list(set(X[0, :, 2])))
         self._n_dimensions = len(self.homology_dimensions_)
-
         self._samplings, _ = _bin(X, metric='silhouette', n_bins=self.n_bins)
         self.samplings_ = {dim: s.flatten()
                            for dim, s in self._samplings.items()}
diff --git a/gtda/graphs/geodesic_distance.py b/gtda/graphs/geodesic_distance.py
index 933445b65..00bc1cb92 100644
--- a/gtda/graphs/geodesic_distance.py
+++ b/gtda/graphs/geodesic_distance.py
@@ -121,7 +121,7 @@ def transform(self, X, y=None):
         X = check_graph(X)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._geodesic_distance)(X[i]) for i in range(X.shape[0]))
+            delayed(self._geodesic_distance)(x) for x in X)
         Xt = np.array(Xt)
         return Xt
 
diff --git a/gtda/graphs/kneighbors.py b/gtda/graphs/kneighbors.py
index 7711611af..4487ec743 100644
--- a/gtda/graphs/kneighbors.py
+++ b/gtda/graphs/kneighbors.py
@@ -33,7 +33,7 @@ class KNeighborsGraph(BaseEstimator, TransformerMixin):
     n_neighbors : int, optional, default: ``4``
         Number of neighbors to use.
 
-    metric : string or callable, default ``'minkowski'``
+    metric : string or callable, optional, default: ``'euclidean'``
         Metric to use for distance computation. Any metric from scikit-learn
         or :mod:`scipy.spatial.distance` can be used.
         If metric is a callable function, it is called on each
@@ -56,13 +56,14 @@ class KNeighborsGraph(BaseEstimator, TransformerMixin):
         See the documentation for :mod:`scipy.spatial.distance` for details on
         these metrics.
 
-    metric_params : dict, optional, default: ``{}``
+    metric_params : dict or None, optional, default: ``None``
         Additional keyword arguments for the metric function.
 
     p : int, optional, default: ``2``
         Parameter for the Minkowski (i.e. :math:`\\ell^p`) metric from
-        :func:`sklearn.metrics.pairwise.pairwise_distances`. `p` = 1 is the
-        Manhattan distance and `p` = 2 is the Euclidean distance.
+        :func:`sklearn.metrics.pairwise.pairwise_distances`. Only relevant
+        when `metric` is ``'minkowski'``. `p` = 1 is the Manhattan distance,
+        and `p` = 2 reduces to the Euclidean distance.
 
     metric_params : dict, optional, default: ``{}``
         Additional keyword arguments for the metric function.
@@ -90,9 +91,8 @@ class KNeighborsGraph(BaseEstimator, TransformerMixin):
 
     """
 
-    # TODO: Consider using an immutable default value for metric_params.
     def __init__(self, n_neighbors=4, metric='euclidean',
-                 p=2, metric_params={}, n_jobs=None):
+                 p=2, metric_params=None, n_jobs=None):
         self.n_neighbors = n_neighbors
         self.metric = metric
         self.p = p
@@ -158,10 +158,9 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_nearest_neighbors')
-        X = check_array(X, allow_nd=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._make_adjacency_matrix)(X[i]) for i in
-            range(X.shape[0]))
+            delayed(self._make_adjacency_matrix)(x) for x in Xt)
         Xt = np.array(Xt)
         return Xt
diff --git a/gtda/graphs/transition.py b/gtda/graphs/transition.py
index 526b4a78b..3022fa80e 100644
--- a/gtda/graphs/transition.py
+++ b/gtda/graphs/transition.py
@@ -16,8 +16,7 @@
 
 
 def identity(x):
-    """The identity function.
-    """
+    """The identity function."""
     return x
 
 
@@ -195,7 +194,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X, copy=True, allow_nd=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._make_adjacency_matrix)(Xt[i]) for i in
diff --git a/gtda/images/_utils.py b/gtda/images/_utils.py
index 825f1cc90..f2df1bda5 100644
--- a/gtda/images/_utils.py
+++ b/gtda/images/_utils.py
@@ -8,8 +8,7 @@
 def _dilate(X, min_iteration, max_iteration, min_value, max_value):
     X = X * 1.
     for iteration in range(min_iteration, min(max_iteration, max_value) + 1):
-        Xtemp = np.asarray([ndi.binary_dilation(X[i])
-                            for i in range(X.shape[0])])
+        Xtemp = np.asarray([ndi.binary_dilation(x) for x in X])
         Xnew = (X + Xtemp) == 1
         if np.any(Xnew):
             X[Xnew] = iteration + min_value
diff --git a/gtda/mapper/cover.py b/gtda/mapper/cover.py
index 58d543c7e..9fd85b977 100644
--- a/gtda/mapper/cover.py
+++ b/gtda/mapper/cover.py
@@ -182,11 +182,12 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_array(X, ensure_2d=False)
-        if X.ndim == 2:
-            _check_has_one_column(X)
+        Xt = check_array(X, ensure_2d=False)
+
+        if Xt.ndim == 2:
+            _check_has_one_column(Xt)
         else:
-            X = X[:, None]
+            Xt = Xt[:, None]
 
         if self.kind == 'balanced':
             # Test whether self.left_limits_ and self.right_limits_ have
@@ -194,7 +195,7 @@ def transform(self, X, y=None):
             # fit_transform but not after fit.
             self._check_limit_attrs()
 
-        Xt = self._transform(X)
+        Xt = self._transform(Xt)
         Xt = _remove_empty_and_duplicate_intervals(Xt)
         return Xt
 
@@ -242,14 +243,15 @@ def fit_transform(self, X, y=None, **fit_params):
             or duplicated cover sets are removed.
 
         """
+        Xt = check_array(X, ensure_2d=False)
         validate_params(self.get_params(), self._hyperparameters)
-        X = check_array(X, ensure_2d=False)
-        if X.ndim == 2:
-            _check_has_one_column(X)
+
+        if Xt.ndim == 2:
+            _check_has_one_column(Xt)
         else:
-            X = X[:, None]
+            Xt = Xt[:, None]
 
-        Xt = self._fit_transform(X)
+        Xt = self._fit_transform(Xt)
         Xt = _remove_empty_and_duplicate_intervals(Xt)
         return Xt
 
@@ -441,7 +443,7 @@ def fit(self, X, y=None):
         X = check_array(X, ensure_2d=False)
         validate_params(self.get_params(), self._hyperparameters)
 
-        # reshape filter function values derived from FunctionTransformer
+        # Reshape filter function values derived from FunctionTransformer
         if X.ndim == 1:
             X = X[:, None]
 
@@ -479,8 +481,9 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_coverers')
-        # Reshape filter function values derived from FunctionTransformer
         Xt = check_array(X, ensure_2d=False)
+
+        # Reshape filter function values derived from FunctionTransformer
         if Xt.ndim == 1:
             Xt = Xt[:, None]
 
@@ -519,9 +522,10 @@ def fit_transform(self, X, y=None, **fit_params):
             n_features` as empty or duplicated cover sets are removed.
 
         """
-        validate_params(self.get_params(), self._hyperparameters)
-        # reshape filter function values derived from FunctionTransformer
         Xt = check_array(X, ensure_2d=False)
+        validate_params(self.get_params(), self._hyperparameters)
+
+        # Reshape filter function values derived from FunctionTransformer
         if Xt.ndim == 1:
             Xt = Xt[:, None]
 
diff --git a/gtda/mapper/filter.py b/gtda/mapper/filter.py
index 83053e25e..0b6cc2cf1 100644
--- a/gtda/mapper/filter.py
+++ b/gtda/mapper/filter.py
@@ -69,10 +69,12 @@ def fit(self, X, y=None):
         #  may be computed. May be useful for supervised tasks with Mapper?
         #  Evaluate performance impact of doing this.
         check_array(X)
+
         if self.metric_params is None:
             self.effective_metric_params_ = dict()
         else:
             self.effective_metric_params_ = self.metric_params.copy()
+
         return self
 
     def transform(self, X, y=None):
@@ -95,13 +97,13 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_array(X)
-        if self.metric == 'precomputed':
-            Xt = X
-        else:
+        Xt = check_array(X)
+
+        if self.metric != 'precomputed':
             Xt = squareform(
-                pdist(X, metric=self.metric, **self.effective_metric_params_))
-        Xt = np.linalg.norm(Xt, axis=1, ord=self.exponent).reshape(-1, 1)
+                pdist(Xt, metric=self.metric, **self.effective_metric_params_))
+
+        Xt = np.linalg.norm(Xt, axis=1, ord=self.exponent, keepdims=True)
         return Xt
 
 
@@ -139,6 +141,7 @@ def fit(self, X, y=None):
 
         """
         check_array(X)
+
         self._is_fitted = True
         return self
 
@@ -165,15 +168,15 @@ def transform(self, X, y=None):
         #  consists of "probabilities" that sum to one. Consider normalisation
         #  in terms of bin counts?
         check_is_fitted(self, '_is_fitted')
-        X = check_array(X)
+        Xt = check_array(X)
 
-        if np.any(X < 0):
+        if np.any(Xt < 0):
             warnings.warn("Negative values detected in X! Taking absolute "
                           "value to calculate probabilities.")
-            X = np.abs(X)
+            Xt = np.abs(Xt)
 
-        probs = X / X.sum(axis=1, keepdims=True)
-        Xt = (entr(probs).sum(axis=1) / np.log(2)).reshape(-1, 1)
+        Xt = Xt / Xt.sum(axis=1, keepdims=True)
+        Xt = entr(Xt).sum(axis=1, keepdims=True) / np.log(2)
         return Xt
 
 
@@ -215,6 +218,7 @@ def fit(self, X, y=None):
 
         """
         check_array(X)
+
         self._is_fitted = True
         return self
 
@@ -240,9 +244,9 @@ def transform(self, X, y=None):
         # Simple duck typing to handle case of pandas dataframe input
         if hasattr(X, 'columns'):
             # NB in this case we do not check the health of other columns
-            Xt = check_array(X[self.columns], ensure_2d=False)
+            Xt = check_array(X[self.columns], ensure_2d=False, copy=True)
         else:
-            X = check_array(X)
-            Xt = X[:, self.columns]
-        Xt = Xt.reshape(len(X), -1)
+            Xt = check_array(X, copy=True)
+            Xt = Xt[:, self.columns]
+        Xt = Xt.reshape(len(Xt), -1)
         return Xt
diff --git a/gtda/plotting/images.py b/gtda/plotting/images.py
index 304418281..be8d7e25c 100644
--- a/gtda/plotting/images.py
+++ b/gtda/plotting/images.py
@@ -2,7 +2,6 @@
 # License: GNU AGPLv3
 
 import plotly.graph_objects as gobj
-from sklearn.utils.validation import check_array
 
 
 def plot_heatmap(data, x=None, y=None, colorscale='greys', origin='upper',
@@ -33,7 +32,6 @@ def plot_heatmap(data, x=None, y=None, colorscale='greys', origin='upper',
         Title of the resulting figure.
 
     """
-    check_array(data, ensure_2d=True)
     autorange = True if origin == 'lower' else 'reversed'
     layout = dict(
         xaxis=dict(scaleanchor='y', constrain='domain'),
diff --git a/gtda/point_clouds/rescaling.py b/gtda/point_clouds/rescaling.py
index 460fb08ca..7b6284f70 100644
--- a/gtda/point_clouds/rescaling.py
+++ b/gtda/point_clouds/rescaling.py
@@ -184,11 +184,10 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._consistent_rescaling)(Xt[i])
-            for i in range(Xt.shape[0]))
+            delayed(self._consistent_rescaling)(x) for x in Xt)
         Xt = np.array(Xt)
         return Xt
 
@@ -291,13 +290,6 @@ def __init__(self, metric='euclidean', metric_params=None, factor=0.,
         self.factor = factor
         self.n_jobs = n_jobs
 
-    def _consecutive_rescaling(self, X):
-        Xm = pairwise_distances(X, metric=self.metric, n_jobs=1,
-                                **self.effective_metric_params_)
-
-        Xm[range(Xm.shape[0]-1), range(1, Xm.shape[0])] *= self.factor
-        return Xm
-
     def fit(self, X, y=None):
         """Calculate :attr:`effective_metric_params_`. Then, return the
         estimator.
@@ -361,12 +353,21 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_array(X, allow_nd=True, copy=True)
+        is_precomputed = self.metric == 'precomputed'
+        X = check_array(X, allow_nd=True, copy=is_precomputed)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._consecutive_rescaling)(Xt[i])
-            for i in range(Xt.shape[0]))
-        Xt = np.array(Xt)
+            delayed(pairwise_distances)(
+                x, metric=self.metric, n_jobs=1,
+                **self.effective_metric_params_)
+            for x in X)
+
+        if is_precomputed:
+            # Parallel loop above serves only as additional input validation
+            Xt = X
+        else:
+            Xt = np.array(Xt)
+        Xt[:, range(Xt.shape[1] - 1), range(1, Xt.shape[1])] *= self.factor
         return Xt
 
     @staticmethod
diff --git a/gtda/time_series/embedding.py b/gtda/time_series/embedding.py
index 6c37a7870..9f4ec34d3 100644
--- a/gtda/time_series/embedding.py
+++ b/gtda/time_series/embedding.py
@@ -137,11 +137,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        X = check_array(X, ensure_2d=False, allow_nd=True)
+        Xt = check_array(X, ensure_2d=False, allow_nd=True)
 
-        window_slices = self._slice_windows(X)
+        window_slices = self._slice_windows(Xt)
 
-        Xt = np.stack([X[begin:end] for begin, end in window_slices])
+        Xt = np.stack([Xt[begin:end] for begin, end in window_slices])
         return Xt
 
     def resample(self, y, X=None):
@@ -470,6 +470,7 @@ def transform(self, X, y=None):
         """
         check_is_fitted(self)
         Xt = check_array(X, ensure_2d=False)
+
         if Xt.ndim == 1:
             Xt = Xt[:, None]
         Xt = self._embed(Xt, self.time_delay_, self.dimension_, self.stride)
diff --git a/gtda/time_series/features.py b/gtda/time_series/features.py
index 28dec9e8b..4274f0346 100644
--- a/gtda/time_series/features.py
+++ b/gtda/time_series/features.py
@@ -49,7 +49,7 @@ def _entropy(self, X):
 
     def _permutation_entropy(self, X):
         Xo = np.argsort(X, axis=2)
-        Xo = np.stack([self._entropy(Xo[i]) for i in range(Xo.shape[0])])
+        Xo = np.stack([self._entropy(x) for x in Xo])
         return Xo.reshape(-1, 1)
 
     def fit(self, X, y=None):
@@ -97,10 +97,10 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        X = check_array(X, allow_nd=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
-            self._permutation_entropy)(X[s])
-            for s in gen_even_slices(len(X), effective_n_jobs(self.n_jobs)))
+            self._permutation_entropy)(Xt[s])
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
         return Xt
diff --git a/gtda/time_series/multivariate.py b/gtda/time_series/multivariate.py
index 02239a44f..932933cc8 100644
--- a/gtda/time_series/multivariate.py
+++ b/gtda/time_series/multivariate.py
@@ -100,7 +100,7 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        check_array(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
 
         Xt = np.empty((X.shape[0], X.shape[2], X.shape[2]))
         for i, sample in enumerate(X):
diff --git a/gtda/time_series/preprocessing.py b/gtda/time_series/preprocessing.py
index af1f7b839..c5479a166 100644
--- a/gtda/time_series/preprocessing.py
+++ b/gtda/time_series/preprocessing.py
@@ -88,7 +88,8 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, '_is_fitted')
-        Xt = check_array(X, ensure_2d=False, allow_nd=True)
+        Xt = check_array(X, ensure_2d=False, allow_nd=True, copy=True)
+
         if Xt.ndim == 1:
             Xt = Xt[: None]
         Xt = Xt[::self.period]
@@ -209,6 +210,7 @@ def transform(self, X, y=None):
         """
         check_is_fitted(self, '_is_fitted')
         Xt = check_array(X, ensure_2d=False, allow_nd=True)
+
         if Xt.ndim == 1:
             Xt = Xt[:, None]
 
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index fcadb35c0..b55453eb0 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -237,7 +237,7 @@ def check_point_clouds(X, **kwargs):
 
     kwargs
         Keyword arguments. For a list of accepted values, see the documentation
-        of :func:`~`gtda.utils.validation.check_list_of_arrays``.
+        of :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Returns
     -------
@@ -248,11 +248,12 @@ def check_point_clouds(X, **kwargs):
     if hasattr(X, 'shape'):
         return check_array(X, **kwargs)
     else:
-        kwargs_default = {'ensure_2d': False, 'force_all_finite': False,
-                          'check_shapes': [('embedding_dimension',
-                                            lambda x: x.shape[1:],
-                                            'Not all point clouds have the '
-                                            'same embedding dimension.')]}
+        kwargs_default = {
+            'ensure_2d': True,
+            'force_all_finite': False,
+            'check_shapes': [
+                (lambda x: x.shape[1:], "Not all point clouds have the same "
+                                        "embedding dimension.")]}
         kwargs_default.update(kwargs)
         return check_list_of_arrays(X, **kwargs_default)
 
@@ -260,16 +261,20 @@ def check_point_clouds(X, **kwargs):
 def check_dimensions(X, get_property):
     """Check the dimensions of X are consistent, where the check is defined
     by get_property 'sample-wise'.
+
     Parameters
     ----------
-    X: list of ndarray,
+    X : list of ndarray,
         Usually represents point clouds or images- see
-        :func:`~`gtda.utils.validation.check_list_of_arrays``.
+        :func:`~gtda.utils.validation.check_list_of_arrays`.
 
-    get_property: function: ndarray -> _,
+    get_property : function: ndarray -> _,
         Defines a property to be conserved, across all arrays (samples)
         in X.
 
+    Returns
+    -------
+
     """
     from functools import reduce
     from operator import and_
@@ -307,10 +312,8 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
 
     """
     # if restrictions on the dimensions of the input are imposed
-    for (test_name, get_property, err_message) in check_shapes:
-        if check_dimensions(X, get_property):
-            continue
-        else:
+    for get_property, err_message in check_shapes:
+        if not check_dimensions(X, get_property):
             raise ValueError(err_message)
 
     is_check_failed = False
@@ -327,5 +330,4 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
     if is_check_failed:
         raise ValueError("The following errors were raised" +
                          "by the inputs: \n" + "\n".join(messages))
-    else:
-        return X
+    return X

From fca12726b0dab5476656fedb698fdacbfdb8eed2 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 19:59:29 +0100
Subject: [PATCH 36/45] Add check_point_clouds to utils __init__ and docs

---
 doc/modules/validation.rst | 1 +
 gtda/utils/__init__.py     | 5 ++---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/doc/modules/validation.rst b/doc/modules/validation.rst
index 0dc37db47..1e20375fb 100644
--- a/doc/modules/validation.rst
+++ b/doc/modules/validation.rst
@@ -12,4 +12,5 @@
    :template: function.rst
 
    utils.check_diagrams
+   utils.check_point_clouds
    utils.validate_params
diff --git a/gtda/utils/__init__.py b/gtda/utils/__init__.py
index a6e9b2077..919720e5a 100644
--- a/gtda/utils/__init__.py
+++ b/gtda/utils/__init__.py
@@ -1,12 +1,11 @@
 """The module :mod:`gtda.utils` implements hyperparameter and input
 validation functions."""
 
-from .validation import check_diagrams, check_graph
-from .validation import validate_params
+from .validation import check_diagrams, check_point_clouds, validate_params
 
 
 __all__ = [
     'check_diagrams',
-    'check_graph',
+    'check_point_clouds',
     'validate_params'
 ]

From 79b529a2da303e8ab1d572ee8d58a4cc182928f1 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 20:04:04 +0100
Subject: [PATCH 37/45] Remove check_images and additions to test_common

These are valuable and thank you @wreise, but in the interest of pushing at least check_point_clouds, I am opting for a more ad-hoc implementation of the latter and for the temporary removal of check_images. As we also did not have much time to discuss the additions to test_common, I will also revert that file to the state on master for now. It can be reintroduced in a later PR together with check_images
---
 gtda/homology/cubical.py     |  24 ++++----
 gtda/images/filtrations.py   |  42 ++++++--------
 gtda/images/preprocessing.py |  43 +++++++-------
 gtda/tests/test_common.py    |  17 ------
 gtda/utils/validation.py     | 107 ++++++++++++-----------------------
 5 files changed, 83 insertions(+), 150 deletions(-)

diff --git a/gtda/homology/cubical.py b/gtda/homology/cubical.py
index 87ec462da..4437947cc 100644
--- a/gtda/homology/cubical.py
+++ b/gtda/homology/cubical.py
@@ -5,16 +5,15 @@
 
 import numpy as np
 from joblib import Parallel, delayed
-
 from sklearn.base import BaseEstimator, TransformerMixin
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_array, check_is_fitted
 
 from ._utils import _pad_diagram
 from ..base import PlotterMixin
 from ..externals.python import CubicalComplex, PeriodicCubicalComplex
 from ..plotting import plot_diagram
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_images
+from ..utils.validation import validate_params
 
 
 class CubicalPersistence(BaseEstimator, TransformerMixin, PlotterMixin):
@@ -146,7 +145,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -202,24 +201,23 @@ def transform(self, X, y=None):
             `X`.
         """
         check_is_fitted(self)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
-                X.shape[0]))
+            delayed(self._gudhi_diagram)(x) for x in Xt)
 
         max_n_points = {
-            dim: max(1, np.max([Xt[i][dim].shape[0] for i in range(len(
-                Xt))])) for dim in self.homology_dimensions}
-        min_values = {
-            dim: min([np.min(Xt[i][dim][:, 0]) if Xt[i][dim].size else
-                      np.inf for i in range(len(Xt))]) for dim in
+            dim: max(1, np.max([x[dim].shape[0] for x in Xt])) for dim in
             self.homology_dimensions}
+        min_values = {
+            dim: min([np.min(x[dim][:, 0]) if x[dim].size else np.inf for x
+                      in Xt]) for dim in self.homology_dimensions}
         min_values = {
             dim: min_values[dim] if min_values[dim] != np.inf else 0 for dim
             in self.homology_dimensions}
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(_pad_diagram)(
-            Xt[i], self._homology_dimensions, max_n_points, min_values)
-            for i in range(len(Xt)))
+            x, self._homology_dimensions, max_n_points, min_values)
+            for x in Xt)
         Xt = np.stack(Xt)
         Xt = np.nan_to_num(Xt, posinf=self.infinity_values_)
         return Xt
diff --git a/gtda/images/filtrations.py b/gtda/images/filtrations.py
index 88b712c09..624da3f4e 100644
--- a/gtda/images/filtrations.py
+++ b/gtda/images/filtrations.py
@@ -10,15 +10,14 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.metrics import pairwise_distances
 from sklearn.utils import gen_even_slices
-
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_array, check_is_fitted
 
 from ._utils import _dilate, _erode
 from ..base import PlotterMixin
 from ..plotting import plot_heatmap
 from ..utils._docs import adapt_fit_transform_docs
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_images
+from ..utils.validation import validate_params
 
 
 @adapt_fit_transform_docs
@@ -87,7 +86,7 @@ def __init__(self, direction=None, n_jobs=None):
     def _calculate_height(self, X):
         Xh = np.full(X.shape, self.max_value_)
 
-        for i in range(Xh.shape[0]):
+        for i in range(len(Xh)):
             Xh[i][np.where(X[i])] = np.dot(self.mesh_[np.where(X[i])],
                                            self.direction_).reshape((-1,))
 
@@ -116,7 +115,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -171,12 +170,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_height)(X[s])
-            for s in gen_even_slices(Xt.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -337,7 +335,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -398,12 +396,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_radial)(X[s])
-            for s in gen_even_slices(Xt.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -529,7 +526,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
 
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
@@ -572,12 +569,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_dilation)(X[s])
-            for s in gen_even_slices(Xt.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -703,7 +699,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -745,12 +741,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_erosion)(X[s])
-            for s in gen_even_slices(Xt.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -886,7 +881,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if (n_dimensions < 2) or (n_dimensions > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -928,12 +923,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
             delayed(self._calculate_signed_distance)(X[s])
-            for s in gen_even_slices(Xt.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index c3f405c2b..9fb7fe84a 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -9,13 +9,13 @@
 from joblib import Parallel, delayed, effective_n_jobs
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.utils import gen_even_slices
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_array, check_is_fitted
 
 from ..base import PlotterMixin
 from ..plotting import plot_point_cloud, plot_heatmap
 from ..utils._docs import adapt_fit_transform_docs
 from ..utils.intervals import Interval
-from ..utils.validation import validate_params, check_images
+from ..utils.validation import validate_params
 
 
 @adapt_fit_transform_docs
@@ -91,7 +91,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         self.n_dimensions_ = X.ndim - 1
         if (self.n_dimensions_ < 2) or (self.n_dimensions_ > 3):
             warn(f"Input of `fit` contains arrays of dimension "
@@ -127,12 +127,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._binarize)(Xt[s])
-            for s in gen_even_slices(X.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         if self.n_dimensions_ == 2:
@@ -211,7 +210,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        X = check_images(X, allow_nd=True)
+        check_array(X, allow_nd=True)
 
         self._is_fitted = True
         return self
@@ -239,12 +238,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self, ['_is_fitted'])
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.logical_not)(Xt[s])
-            for s in gen_even_slices(X.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -345,7 +343,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_images(X, allow_nd=True)
+        X = check_array(X, allow_nd=True)
         n_dimensions = X.ndim - 1
         if n_dimensions < 2 or n_dimensions > 3:
             warn(f"Input of `fit` contains arrays of dimension "
@@ -391,13 +389,12 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             np.pad)(Xt[s], pad_width=self._pad_width,
                     constant_values=self.activated)
-            for s in gen_even_slices(X.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
         Xt = np.concatenate(Xt)
 
         return Xt
@@ -435,9 +432,10 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin, PlotterMixin):
 
     The coordinates of each point is calculated as follows. For each activated
     pixel, assign coordinates that are the pixel position on this image.
-    This transformer is meant to transform a collection of images to a point
-    cloud so that collection of point clouds-based persistent homology module
-    can be applied.
+
+    This transformer is meant to transform a collection of images to a
+    collection of point clouds so that persistent homology calculations can be
+    performed.
 
     Parameters
     ----------
@@ -477,9 +475,7 @@ def _embed(self, X):
         return Xpts
 
     def fit(self, X, y=None):
-        """Do nothing and return the estimator unchanged.
-        This method is here to implement the usual scikit-learn API and hence
-        work in pipelines.
+        """Compute :attr:`mesh_`, and return the estimator.
 
         Parameters
         ----------
@@ -496,7 +492,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_images(X, allow_nd=True)
+        check_array(X, allow_nd=True)
 
         n_dimensions = X.ndim - 1
         if n_dimensions < 2 or n_dimensions > 3:
@@ -537,12 +533,11 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        Xt = check_images(X, allow_nd=True, copy=True)
+        Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._embed)(Xt[s])
-            for s in gen_even_slices(X.shape[0],
-                                     effective_n_jobs(self.n_jobs)))
+            for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
 
         Xt = reduce(sum, Xt, [])
         return Xt
diff --git a/gtda/tests/test_common.py b/gtda/tests/test_common.py
index 1e9a515f7..057e55b88 100644
--- a/gtda/tests/test_common.py
+++ b/gtda/tests/test_common.py
@@ -27,19 +27,6 @@
                 ],
 }
 
-LISTFAIL_TESTS = ['check_estimators_dtypes', 'check_fit_score_takes_y',
-                  'check_estimators_fit_returns_self',
-                  'check_estimators_fit_returns_self(readonly_memmap=True)',
-                  'check_complex_data', 'check_dtype_object',
-                  'check_estimators_empty_data_messages',
-                  'check_pipeline_consistency', 'check_estimators_nan_inf',
-                  'check_estimators_overwrite_params',
-                  'check_estimator_sparse_data', 'check_estimators_pickle',
-                  'check_fit2d_predict1d', 'check_methods_subset_invariance',
-                  'check_fit2d_1sample', 'check_fit2d_1feature',
-                  'check_dict_unchanged', 'check_dont_overwrite_parameters',
-                  'check_fit_idempotent']
-
 
 # adapted from sklearn.utils.estimator_check v0.22
 def _get_callable_name(obj):
@@ -99,8 +86,4 @@ def test_sklearn_api(check, estimator, request):
         request.applymarker(pytest.mark.xfail(
             run=True, reason='known failure'))
 
-    if check_name in LISTFAIL_TESTS:
-        request.applymarker(pytest.mark.xfail(
-            run=True, reason='Known failure: 2d input.'))
-
     check(estimator)
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index b55453eb0..84a5f3f69 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -183,46 +183,6 @@ def validate_params(parameters, references, exclude=None):
     return _validate_params(parameters_, references)
 
 
-def check_images(X, **kwargs):
-    """Check a list of arrays representing images, by iterating through
-    the input one by one. To pass a test when `kwargs` is empty,
-    all images ``x``, ``y`` in `X` must satisfy:
-        - ``x.ndim >= 2``,
-        - ``all(np.isfinite(x))``,
-        - ``x.shape == y.shape``.
-
-    Parameters
-    ----------
-    X : list of ndarray
-        Each entry of `X` corresponds to an image.
-
-    kwargs
-        Keyword arguments. For a list of accepted values, see the documentation
-        of :func:`~gtda.utils.validation.check_list_of_arrays`.
-
-    Returns
-    -------
-    X : list of ndarray
-        as modified by :func:`~sklearn.utils.validation.check_array`
-
-    """
-    if hasattr(X, 'shape'):
-        if X.ndim < 3:
-            raise ValueError(f"An image in the collection X should be at "
-                             f"least of dimension 2, while it has dimension "
-                             f"{X.ndim - 1}.")
-        return check_array(X, **kwargs)
-    else:
-        kwargs_default = {'force_all_finite': True,
-                          'ensure_2d': False, 'allow_nd': True,
-                          'check_shapes': [('embedding_dimension',
-                                            lambda x: x.shape,
-                                            'The images should have exactly'
-                                            'the same shape')]}
-        kwargs_default.update(kwargs)
-        return check_list_of_arrays(X, **kwargs_default)
-
-
 def check_point_clouds(X, **kwargs):
     """Check a list of arrays representing point clouds, by integrating
     through the input one by one. To pass a test when `kwargs` is empty,
@@ -258,49 +218,27 @@ def check_point_clouds(X, **kwargs):
         return check_list_of_arrays(X, **kwargs_default)
 
 
-def check_dimensions(X, get_property):
-    """Check the dimensions of X are consistent, where the check is defined
-    by get_property 'sample-wise'.
-
-    Parameters
-    ----------
-    X : list of ndarray,
-        Usually represents point clouds or images- see
-        :func:`~gtda.utils.validation.check_list_of_arrays`.
-
-    get_property : function: ndarray -> _,
-        Defines a property to be conserved, across all arrays (samples)
-        in X.
-
-    Returns
-    -------
-
-    """
-    from functools import reduce
-    from operator import and_
-    reference = get_property(X[0])
-    return reduce(and_, map(lambda x: get_property(x) == reference, X[1:]),
-                  True)
-
-
 def check_list_of_arrays(X, check_shapes=list(), **kwargs):
-    """Input validation on a list of lists, arrays, sparse matrices, or similar.
+    """Input validation on a list of arrays, sparse matrices, or similar.
 
-    The constraints are to be specified in `kwargs`. On top of
-    parameters from :func:`~sklearn.utils.validation.check_array`,
-    the optional parameters are listed below.
+    Each entry in the list is validated using
+    :func:`~sklearn.utils.validation.check_array`. Optionally, some shared
+    shapes of
+    all
+    optional
+    parameters are
+    are listed below.
 
     Parameters
     ----------
     X : list
         Input list of objects to check / convert.
 
-    check_shapes: list of tuples t, where t = (str, function to pass to
-        check_dimensions, error message if test fails).
+    check_shapes : list of tuple
         The checks are applied in the order they are provided, only until
         the first failure.
 
-    kwargs :
+    kwargs
         Keyword arguments. For a list of accepted values, see the documentation
         of :func:`~sklearn.utils.validation.check_array`.
 
@@ -311,6 +249,31 @@ def check_list_of_arrays(X, check_shapes=list(), **kwargs):
         :func:`~sklearn.utils.validation.check_array`
 
     """
+
+    def check_dimensions(X, get_property):
+        """Check the dimensions of X are consistent, where the check is defined
+        by get_property 'sample-wise'.
+
+        Parameters
+        ----------
+        X : list of ndarray,
+            Usually represents point clouds or images- see
+            :func:`~gtda.utils.validation.check_list_of_arrays`.
+
+        get_property : function: ndarray -> _,
+            Defines a property to be conserved, across all arrays (samples)
+            in X.
+
+        Returns
+        -------
+
+        """
+        from functools import reduce
+        from operator import and_
+        reference = get_property(X[0])
+        return reduce(and_, map(lambda x: get_property(x) == reference, X[1:]),
+                      True)
+
     # if restrictions on the dimensions of the input are imposed
     for get_property, err_message in check_shapes:
         if not check_dimensions(X, get_property):

From 811fe87edd61cc776699adae2f675154f36d1c6d Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Sun, 22 Mar 2020 20:17:43 +0100
Subject: [PATCH 38/45] Linting

---
 gtda/homology/cubical.py      |  6 +++---
 gtda/images/preprocessing.py  | 11 ++++++-----
 gtda/time_series/embedding.py |  2 +-
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/gtda/homology/cubical.py b/gtda/homology/cubical.py
index 4437947cc..373fb3b1a 100644
--- a/gtda/homology/cubical.py
+++ b/gtda/homology/cubical.py
@@ -133,7 +133,7 @@ def fit(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray, shape (n_samples, n_pixels_1, ..., n_pixels_d)
+        X : ndarray of shape (n_samples, n_pixels_1, ..., n_pixels_d)
             Input data. Array of d-dimensional images.
 
         y : None
@@ -184,7 +184,7 @@ def transform(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray, shape (n_samples, n_pixels_1, ..., n_pixels_d)
+        X : ndarray of shape (n_samples, n_pixels_1, ..., n_pixels_d)
             Input data. Array of d-dimensional images.
 
         y : None
@@ -193,7 +193,7 @@ def transform(self, X, y=None):
 
         Returns
         -------
-        Xt : ndarray, shape (n_samples, n_features, 3)
+        Xt : ndarray of shape (n_samples, n_features, 3)
             Array of persistence diagrams computed from the feature arrays or
             distance matrices in `X`. ``n_features`` equals
             :math:`\\sum_q n_q`, where :math:`n_q` is the maximum number of
diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index 9fb7fe84a..0d300f4bb 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -446,7 +446,7 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin, PlotterMixin):
 
     Attributes
     ----------
-    mesh_ : ndarray, shape (n_pixels_x * n_pixels_y [* n_pixels_z], \
+    mesh_ : ndarray of shape (n_pixels_x * n_pixels_y [* n_pixels_z], \
         n_dimensions)
         Mesh image for which each pixel value is its coordinates in a
         ``n_dimensions``-dimensional space, where ``n_dimensions`` is the
@@ -479,7 +479,7 @@ def fit(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray, shape (n_samples, n_pixels_x, n_pixels_y [, n_pixels_z])
+        X : ndarray of shape (n_samples, n_pixels_x, n_pixels_y [, n_pixels_z])
             Input data. Each entry along axis 0 is interpreted as a 2D or 3D
             binary image.
 
@@ -516,7 +516,7 @@ def transform(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray, shape (n_samples, n_pixels_x, n_pixels_y [, n_pixels_z])
+        X : ndarray of shape (n_samples, n_pixels_x, n_pixels_y [, n_pixels_z])
             Input data. Each entry along axis 0 is interpreted as a 2D or 3D
             binary image.
 
@@ -526,7 +526,8 @@ def transform(self, X, y=None):
 
         Returns
         -------
-        Xt : ndarray, shape (n_samples, n_pixels_x * n_pixels_y [* n_pixels_z],
+        Xt : ndarray of shape (n_samples, n_pixels_x * n_pixels_y [* \
+            n_pixels_z],
             n_dimensions)
             Transformed collection of images. Each entry along axis 0 is a
             point cloud in ``n_dimensions``-dimensional space.
@@ -549,7 +550,7 @@ def plot(Xt, sample=0):
 
         Parameters
         ----------
-        Xt : ndarray, shape (n_samples, n_points, n_dimensions)
+        Xt : ndarray of shape (n_samples, n_points, n_dimensions)
             Collection of point clouds in ``n_dimension``-dimensional space,
             such as returned by :meth:`transform`.
 
diff --git a/gtda/time_series/embedding.py b/gtda/time_series/embedding.py
index 9f4ec34d3..a909c7e71 100644
--- a/gtda/time_series/embedding.py
+++ b/gtda/time_series/embedding.py
@@ -184,7 +184,7 @@ def plot(Xt, sample=0):
 
         Parameters
         ----------
-        Xt : ndarray, shape (n_samples, n_points, n_dimensions)
+        Xt : ndarray of shape (n_samples, n_points, n_dimensions)
             Collection of sliding windows, each containing ``n_points``
             points in ``n_dimensions``-dimensional space, such as returned by
             :meth:`transform`.

From e6c311b02676703c36dc498cfed4f3976b06fa82 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 01:38:48 +0100
Subject: [PATCH 39/45] Refactor ImageToPointCloud to return lists of point
 clouds

---
 gtda/images/preprocessing.py | 35 +++++++++++------------------------
 1 file changed, 11 insertions(+), 24 deletions(-)

diff --git a/gtda/images/preprocessing.py b/gtda/images/preprocessing.py
index 0d300f4bb..dc996f8d5 100644
--- a/gtda/images/preprocessing.py
+++ b/gtda/images/preprocessing.py
@@ -2,6 +2,7 @@
 # License: GNU AGPLv3
 
 from functools import reduce
+from operator import iconcat
 from numbers import Real
 from warnings import warn
 
@@ -431,7 +432,8 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin, PlotterMixin):
     """Represent active pixels in 2D/3D binary images as points in 2D/3D space.
 
     The coordinates of each point is calculated as follows. For each activated
-    pixel, assign coordinates that are the pixel position on this image.
+    pixel, assign coordinates that are the pixel index on this image, after
+    flipping the rows and then swapping between rows and columns.
 
     This transformer is meant to transform a collection of images to a
     collection of point clouds so that persistent homology calculations can be
@@ -444,14 +446,6 @@ class ImageToPointCloud(BaseEstimator, TransformerMixin, PlotterMixin):
         in a :obj:`joblib.parallel_backend` context. ``-1`` means using all
         processors.
 
-    Attributes
-    ----------
-    mesh_ : ndarray of shape (n_pixels_x * n_pixels_y [* n_pixels_z], \
-        n_dimensions)
-        Mesh image for which each pixel value is its coordinates in a
-        ``n_dimensions``-dimensional space, where ``n_dimensions`` is the
-        dimension of the images of the input collection. Set in meth:`fit`.
-
     See also
     --------
     gtda.homology.VietorisRipsPersistence, gtda.homology.SparseRipsPersistence,
@@ -470,12 +464,12 @@ def __init__(self, n_jobs=None):
         self.n_jobs = n_jobs
 
     def _embed(self, X):
-        Xpts = np.stack([self.mesh_ for _ in range(X.shape[0])]) * 1.
-        Xpts[np.logical_not(X.reshape((X.shape[0], -1))), :] += np.inf
-        return Xpts
+        return [np.argwhere(x) for x in X]
 
     def fit(self, X, y=None):
-        """Compute :attr:`mesh_`, and return the estimator.
+        """Do nothing and return the estimator unchanged.
+        This method is here to implement the usual scikit-learn API and hence
+        work in pipelines.
 
         Parameters
         ----------
@@ -499,14 +493,7 @@ def fit(self, X, y=None):
             warn(f"Input of `fit` contains arrays of dimension "
                  f"{self.n_dimensions_}.")
 
-        axis_order = [2, 1, 3]
-        mesh_range_list = [np.arange(0, X.shape[i])
-                           for i in axis_order[:n_dimensions]]
-
-        self.mesh_ = np.flip(np.stack(np.meshgrid(*mesh_range_list),
-                                      axis=n_dimensions),
-                             axis=0).reshape((-1, n_dimensions))
-
+        self._is_fitted = True
         return self
 
     def transform(self, X, y=None):
@@ -533,14 +520,14 @@ def transform(self, X, y=None):
             point cloud in ``n_dimensions``-dimensional space.
 
         """
-        check_is_fitted(self)
+        check_is_fitted(self, '_is_fitted')
         Xt = check_array(X, allow_nd=True)
 
+        Xt = np.swapaxes(np.flip(Xt, axis=1), 1, 2)
         Xt = Parallel(n_jobs=self.n_jobs)(delayed(
             self._embed)(Xt[s])
             for s in gen_even_slices(len(Xt), effective_n_jobs(self.n_jobs)))
-
-        Xt = reduce(sum, Xt, [])
+        Xt = reduce(iconcat, Xt, [])
         return Xt
 
     @staticmethod

From 5fb744f93988d3f1870e9e181db14959a211aae9 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 02:51:33 +0100
Subject: [PATCH 40/45] Refactor check_point_clouds making it more ad-hoc

---
 gtda/homology/simplicial.py |  32 ++++-----
 gtda/utils/validation.py    | 136 ++++++++++++------------------------
 2 files changed, 56 insertions(+), 112 deletions(-)

diff --git a/gtda/homology/simplicial.py b/gtda/homology/simplicial.py
index d8b07d8a4..52d9857b8 100644
--- a/gtda/homology/simplicial.py
+++ b/gtda/homology/simplicial.py
@@ -169,10 +169,10 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_point_clouds(X, ensure_2d=False, allow_nd=True,
-                           force_all_finite=False)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
+        self._is_precomputed = self.metric == 'precomputed'
+        check_point_clouds(X, distance_matrix=self._is_precomputed)
 
         if self.infinity_values is None:
             self.infinity_values_ = self.max_edge_length
@@ -220,12 +220,10 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_point_clouds(X, ensure_2d=False,
-                               allow_nd=True,
-                               force_all_finite=False)
+        X = check_point_clouds(X, distance_matrix=self._is_precomputed)
 
-        Xt = Parallel(n_jobs=self.n_jobs)(delayed(self._ripser_diagram)(X[i])
-                                          for i in range(len(X)))
+        Xt = Parallel(n_jobs=self.n_jobs)(
+            delayed(self._ripser_diagram)(x) for x in X)
 
         Xt = _postprocess_diagrams(Xt, self._homology_dimensions,
                                    self.infinity_values_, self.n_jobs)
@@ -417,11 +415,10 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_point_clouds(X, ensure_2d=False,
-                           allow_nd=True,
-                           force_all_finite=False)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
+        self._is_precomputed = self.metric == 'precomputed'
+        check_point_clouds(X, distance_matrix=self._is_precomputed)
 
         if self.infinity_values is None:
             self.infinity_values_ = self.max_edge_length
@@ -469,13 +466,10 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_point_clouds(X, ensure_2d=False,
-                               allow_nd=True,
-                               force_all_finite=False)
+        X = check_point_clouds(X, distance_matrix=self._is_precomputed)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
-                X.shape[0]))
+            delayed(self._gudhi_diagram)(x) for x in X)
 
         Xt = _postprocess_diagrams(Xt, self._homology_dimensions,
                                    self.infinity_values_, self.n_jobs)
@@ -635,7 +629,7 @@ def fit(self, X, y=None):
         self : object
 
         """
-        check_point_clouds(X, ensure_2d=False, allow_nd=True)
+        check_point_clouds(X)
         validate_params(
             self.get_params(), self._hyperparameters, exclude=['n_jobs'])
 
@@ -680,12 +674,10 @@ def transform(self, X, y=None):
 
         """
         check_is_fitted(self)
-        X = check_point_clouds(X, ensure_2d=False,
-                               allow_nd=True, )
+        X = check_point_clouds(X)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._gudhi_diagram)(X[i, :, :]) for i in range(
-                X.shape[0]))
+            delayed(self._gudhi_diagram)(x) for x in X)
 
         Xt = _postprocess_diagrams(Xt, self._homology_dimensions,
                                    self.infinity_values_, self.n_jobs)
diff --git a/gtda/utils/validation.py b/gtda/utils/validation.py
index 84a5f3f69..a96ba460a 100644
--- a/gtda/utils/validation.py
+++ b/gtda/utils/validation.py
@@ -1,8 +1,11 @@
 """Utilities for input validation."""
 # License: GNU AGPLv3
 
-import numpy as np
+from functools import reduce
+from operator import and_
+from warnings import warn
 
+import numpy as np
 from sklearn.utils.validation import check_array
 
 
@@ -183,114 +186,63 @@ def validate_params(parameters, references, exclude=None):
     return _validate_params(parameters_, references)
 
 
-def check_point_clouds(X, **kwargs):
-    """Check a list of arrays representing point clouds, by integrating
-    through the input one by one. To pass a test when `kwargs` is empty,
-    all point clouds ``x``, ``y`` in X must satisfy:
-        - ``x.ndim == 2``,
-        - ``len(y.shape[1:]) == len(y.shape[1:])``.
-
-    Parameters
-    ----------
-    X : list of ndarray, such that ``X[i].ndim==2`` (n_points, n_dimensions),
-        or an array `X.dim==3`
+def check_point_clouds(X, distance_matrix=False, **kwargs):
+    """Input validation on an array or list representing a collection of point
+    clouds or distance matrices.
 
-    kwargs
-        Keyword arguments. For a list of accepted values, see the documentation
-        of :func:`~gtda.utils.validation.check_list_of_arrays`.
+    The input is checked to be either a single 3D array using a single call
+    to :func:`~sklearn.utils.validation.check_array`, or a list of 2D arrays by
+    calling :func:`~sklearn.utils.validation.check_array` on each entry. In
+    the latter case, warnings are issued when not all point clouds are in
+    the same Euclidean space.
 
-    Returns
-    -------
-    X : list of input arrays
-        as modified by :func:`~sklearn.utils.validation.check_array`
-
-    """
-    if hasattr(X, 'shape'):
-        return check_array(X, **kwargs)
-    else:
-        kwargs_default = {
-            'ensure_2d': True,
-            'force_all_finite': False,
-            'check_shapes': [
-                (lambda x: x.shape[1:], "Not all point clouds have the same "
-                                        "embedding dimension.")]}
-        kwargs_default.update(kwargs)
-        return check_list_of_arrays(X, **kwargs_default)
-
-
-def check_list_of_arrays(X, check_shapes=list(), **kwargs):
-    """Input validation on a list of arrays, sparse matrices, or similar.
-
-    Each entry in the list is validated using
-    :func:`~sklearn.utils.validation.check_array`. Optionally, some shared
-    shapes of
-    all
-    optional
-    parameters are
-    are listed below.
+    Conversions and copies may be triggered as per
+    :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Parameters
     ----------
-    X : list
-        Input list of objects to check / convert.
+    X : object
+        Input object to check / convert.
 
-    check_shapes : list of tuple
-        The checks are applied in the order they are provided, only until
-        the first failure.
+    distance_matrix : bool, optional, default: ``False``
+        Whether the input represents a collection of distance matrices or of
+        concrete point clouds in Euclidean space. In the first case, entries
+        are allowed to be infinite unless otherwise specified in `kwargs`.
 
     kwargs
-        Keyword arguments. For a list of accepted values, see the documentation
-        of :func:`~sklearn.utils.validation.check_array`.
+        Keyword arguments accepted by
+        :func:`~gtda.utils.validation.check_list_of_arrays`.
 
     Returns
     -------
-    X : list
-        Output list of objects, each checked / converted by
-        :func:`~sklearn.utils.validation.check_array`
+    Xnew : ndarray or list
+        The converted and validated object.
 
     """
+    kwargs_ = {'force_all_finite': not distance_matrix}
+    kwargs_.update(kwargs)
+    if hasattr(X, 'shape'):
+        if X.ndim != 3:
+            raise ValueError("ndarray input must be 3D.")
+        return check_array(X, allow_nd=True, **kwargs_)
+    else:
+        if not distance_matrix:
+            reference = X[0].shape[1]  # Embedding dimension of first sample
+            if not reduce(
+                    and_, (x.shape[1] == reference for x in X[1:]), True):
+                warn("Not all point clouds have the same embedding dimension.")
 
-    def check_dimensions(X, get_property):
-        """Check the dimensions of X are consistent, where the check is defined
-        by get_property 'sample-wise'.
-
-        Parameters
-        ----------
-        X : list of ndarray,
-            Usually represents point clouds or images- see
-            :func:`~gtda.utils.validation.check_list_of_arrays`.
-
-        get_property : function: ndarray -> _,
-            Defines a property to be conserved, across all arrays (samples)
-            in X.
-
-        Returns
-        -------
-
-        """
-        from functools import reduce
-        from operator import and_
-        reference = get_property(X[0])
-        return reduce(and_, map(lambda x: get_property(x) == reference, X[1:]),
-                      True)
-
-    # if restrictions on the dimensions of the input are imposed
-    for get_property, err_message in check_shapes:
-        if not check_dimensions(X, get_property):
-            raise ValueError(err_message)
-
-    is_check_failed = False
+    has_check_failed = False
     messages = []
+    Xnew = []
     for i, x in enumerate(X):
         try:
-            # TODO: verify the behavior depending on copy.
-            X[i] = check_array(x.reshape(1, *x.shape),
-                               **kwargs).reshape(*x.shape)
+            Xnew.append(check_array(x, **kwargs_))
             messages = ['']
         except ValueError as e:
-            is_check_failed = True
+            has_check_failed = True
             messages.append(str(e))
-    if is_check_failed:
-        raise ValueError("The following errors were raised" +
-                         "by the inputs: \n" + "\n".join(messages))
-    return X
+    if has_check_failed:
+        raise ValueError("The following errors were raised by the inputs: \n"
+                         "\n".join(messages))
+    return Xnew

From d4abe519731ff74d5d3f2740e68b351d96558369 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 03:01:25 +0100
Subject: [PATCH 41/45] Fix some incorrect links to GH pages

---
 CONTRIBUTING.rst            | 2 +-
 PULL_REQUEST_TEMPLATE.md    | 4 ++--
 README.rst                  | 4 ++--
 examples/plotting_api.ipynb | 8 ++++----
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/CONTRIBUTING.rst b/CONTRIBUTING.rst
index 0493a881b..5c0654a6d 100644
--- a/CONTRIBUTING.rst
+++ b/CONTRIBUTING.rst
@@ -1,7 +1,7 @@
 Contributing guidelines
 =======================
 
-This document only redirects to more `detailed instructions <https://giotto-ai.github.io/gtda-docs/dev/contributing>`_,
+This document only redirects to more `detailed instructions <https://giotto-ai.github.io/gtda-docs/latest/contributing>`_,
 which consist of:
 - a pull request checklist,
 - a Contributor License Agreement,
diff --git a/PULL_REQUEST_TEMPLATE.md b/PULL_REQUEST_TEMPLATE.md
index 73db335ec..21041aade 100644
--- a/PULL_REQUEST_TEMPLATE.md
+++ b/PULL_REQUEST_TEMPLATE.md
@@ -1,6 +1,6 @@
 <!--
 Thanks for contributing a pull request! Please ensure you have taken a look at
-the guidelines for contributing: https://giotto-ai.github.io/gtda-docs/dev/contributing/#guidelines
+the guidelines for contributing: https://giotto-ai.github.io/gtda-docs/latest/contributing/#guidelines
 -->
 
 **Reference issues/PRs**
@@ -37,7 +37,7 @@ Describe your changes in detail.
 Go over all the following points, and put an `x` in all the boxes that apply. 
 If you're unsure about any of these, don't hesitate to ask. We're here to help!
 -->
-- [ ] I have read the [guidelines for contributing](https://giotto-ai.github.io/gtda-docs/dev/contributing/#guidelines).
+- [ ] I have read the [guidelines for contributing](https://giotto-ai.github.io/gtda-docs/latest/contributing/#guidelines).
 - [ ] My code follows the code style of this project. I used `flake8` to check my Python changes.
 - [ ] My change requires a change to the documentation.
 - [ ] I have updated the documentation accordingly.
diff --git a/README.rst b/README.rst
index 84ce12254..d6938665f 100644
--- a/README.rst
+++ b/README.rst
@@ -96,7 +96,7 @@ the same environment.
 Developer installation
 ----------------------
 
-Please consult the `relevant page <https://giotto-ai.github.io/gtda-docs/dev/installation.html#developer-installation>`_
+Please consult the `relevant page <https://giotto-ai.github.io/gtda-docs/latest/installation.html#developer-installation>`_
 for detailed instructions on how to build ``giotto-tda`` from sources across different platforms.
 
 .. _contributing-section:
@@ -107,7 +107,7 @@ Contributing
 We welcome new contributors of all experience levels. The Giotto
 community goals are to be helpful, welcoming, and effective. To learn more about
 making a contribution to ``giotto-tda``, please consult the `relevant page
-<https://giotto-ai.github.io/gtda-docs/dev/contributing/index.html>`_.
+<https://giotto-ai.github.io/gtda-docs/latest/contributing/index.html>`_.
 
 Testing
 -------
diff --git a/examples/plotting_api.ipynb b/examples/plotting_api.ipynb
index 107e73ef2..22dc13186 100644
--- a/examples/plotting_api.ipynb
+++ b/examples/plotting_api.ipynb
@@ -8,7 +8,7 @@
     "\n",
     "`giotto-tda` includes a set of plotting functions and class methods, powered by `plotly`. The library's plotting API is designed to facilitate the exploration of intermediate results in pipelines by harnessing the highly visual nature of topological signatures.\n",
     "\n",
-    "This notebook is a quick tutorial on how to use `giotto-tda`'s plotting functionalities and unified plotting API. The plotting functions in `gtda.mapper` are not covered here as they are somewhat tailored to the Mapper algorithm, see the [dedicated tutorial](https://giotto-ai.github.io/gtda-docs/dev/notebooks/mapper_quickstart.html).\n",
+    "This notebook is a quick tutorial on how to use `giotto-tda`'s plotting functionalities and unified plotting API. The plotting functions in `gtda.mapper` are not covered here as they are somewhat tailored to the Mapper algorithm, see the [dedicated tutorial](https://giotto-ai.github.io/gtda-docs/latest/notebooks/mapper_quickstart.html).\n",
     "\n",
     "If you are looking at a static version of this notebook and would like to run its contents, head over to [github](https://github.com/giotto-ai/giotto-tda/blob/master/examples/plotting_api.ipynb).\n",
     "\n",
@@ -43,9 +43,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Plotting functions\n",
+    "### 1.1 Plotting functions\n",
     "\n",
-    "Several `plot` methods in `giotto-tda` actually fall back to specialised functions which can be found in the [plotting subpackage](https://giotto-ai.github.io/gtda-docs/dev/modules/pipeline.html) and which can be used directly instead. However, unless the additional degree of control is necessary, `plot` methods should be preferred as they often exploit class parameters and/or attributes (e.g. those computed during `fit`) to automatically fill some parameters in the corresponding functions."
+    "Several `plot` methods in `giotto-tda` actually fall back to specialised functions which can be found in the [plotting subpackage](https://giotto-ai.github.io/gtda-docs/latest/modules/plotting.html) and which can be used directly instead. However, unless the additional degree of control is necessary, `plot` methods should be preferred as they often exploit class parameters and/or attributes (e.g. those computed during `fit`) to automatically fill some parameters in the corresponding functions."
    ]
   },
   {
@@ -54,7 +54,7 @@
    "source": [
     "### 1.2 Example: Plotting persistence diagrams with `VietorisRipsPersistence`\n",
     "\n",
-    "Let's take the example of `VietorisRipsPersistence` – a transformer also covered in [another notebook](https://giotto-ai.github.io/gtda-docs/dev/notebooks/vietoris_rips_quickstart.html). Let's create the input collection `X` for this transformer as a collection of randomly generated point clouds, each containing 100 points positioned along two circles."
+    "Let's take the example of `VietorisRipsPersistence` – a transformer also covered in [another notebook](https://giotto-ai.github.io/gtda-docs/latest/notebooks/vietoris_rips_quickstart.html). Let's create the input collection `X` for this transformer as a collection of randomly generated point clouds, each containing 100 points positioned along two circles."
    ]
   },
   {

From 34ae7ac859a15f0277a62ec26c101866f07e10e4 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 03:04:35 +0100
Subject: [PATCH 42/45] Delete test expecting ValueError on point clouds in
 different embedding dims

---
 gtda/homology/tests/test_simplicial.py | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/gtda/homology/tests/test_simplicial.py b/gtda/homology/tests/test_simplicial.py
index 38292053f..4af1633e1 100644
--- a/gtda/homology/tests/test_simplicial.py
+++ b/gtda/homology/tests/test_simplicial.py
@@ -100,17 +100,7 @@ def test_cp_transform():
 
 
 def test_vrp_list_of_arrays():
-    """Verify that a list of point clouds"""
     pc_2 = np.array([[0, 1], [1, 2]])
     pc_list = [pc[0].copy(), pc_2]
     vrp = VietorisRipsPersistence()
     vrp.fit(pc_list)
-
-
-def test_vrp_list_invalid_arrays():
-    pc_2 = np.array([[0, 1, 2]])
-    pc_invalid = [pc[0].copy(), pc_2]
-
-    vrp = VietorisRipsPersistence()
-    with pytest.raises(ValueError):
-        vrp.fit(pc_invalid)

From 3f2f53b479113549b41a5d31a7a1f22886610f6d Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 03:09:42 +0100
Subject: [PATCH 43/45] Small code simplification

---
 gtda/graphs/transition.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/gtda/graphs/transition.py b/gtda/graphs/transition.py
index 3022fa80e..4e7be4ab1 100644
--- a/gtda/graphs/transition.py
+++ b/gtda/graphs/transition.py
@@ -197,7 +197,6 @@ def transform(self, X, y=None):
         Xt = check_array(X, allow_nd=True)
 
         Xt = Parallel(n_jobs=self.n_jobs)(
-            delayed(self._make_adjacency_matrix)(Xt[i]) for i in
-            range(Xt.shape[0]))
+            delayed(self._make_adjacency_matrix)(x) for x in Xt)
         Xt = np.asarray(Xt)
         return Xt

From d577250495c1211762048848e73d4713c1523156 Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 09:20:23 +0100
Subject: [PATCH 44/45] Update docs in homology/simplicial.py following
 refactoring of check_point_clouds

---
 gtda/homology/simplicial.py | 86 ++++++++++++++++++++++---------------
 1 file changed, 51 insertions(+), 35 deletions(-)

diff --git a/gtda/homology/simplicial.py b/gtda/homology/simplicial.py
index 52d9857b8..1b6c0bc0c 100644
--- a/gtda/homology/simplicial.py
+++ b/gtda/homology/simplicial.py
@@ -39,7 +39,7 @@ class VietorisRipsPersistence(BaseEstimator, TransformerMixin, PlotterMixin):
     Parameters
     ----------
     metric : string or callable, optional, default: ``'euclidean'``
-        If set to `'precomputed'`, input data is to be interpreted as a
+        If set to ``'precomputed'``, input data is to be interpreted as a
         collection of distance matrices. Otherwise, input data is to be
         interpreted as a collection of point clouds (i.e. feature arrays),
         and `metric` determines a rule with which to calculate distances
@@ -152,13 +152,15 @@ def fit(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray of shape (n_samples, n_points, n_points) or \
-            (n_samples, n_points, n_dimensions)
-            Input data. If ``metric == 'precomputed'``, the input should be an
-            ndarray whose each entry along axis 0 is a distance matrix of shape
-            ``(n_points, n_points)``. Otherwise, each such entry will be
-            interpreted as an ndarray of ``n_points`` row vectors in
-            ``n_dimensions``-dimensional space.
+        X : ndarray or list
+            Input data representing a collection of point clouds or of distance
+            matrices. Can be either a 3D ndarray whose zeroth dimension has
+            size ``n_samples``, or a list containing ``n_samples`` 2D ndarrays.
+            If ``metric == 'precomputed'``, elements of `X` must be square
+            arrays representing distance matrices; otherwise, their rows are
+            interpreted as vectors in Euclidean space and, when `X` is a list,
+            warnings are issued when the number of columns (dimension of the
+            Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline
@@ -197,13 +199,15 @@ def transform(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray of shape (n_samples, n_points, n_points) or \
-            (n_samples, n_points, n_dimensions)
-            Input data. If ``metric == 'precomputed'``, the input should be an
-            ndarray whose each entry along axis 0 is a distance matrix of shape
-            ``(n_points, n_points)``. Otherwise, each such entry will be
-            interpreted as an ndarray of ``n_points`` row vectors in
-            ``n_dimensions``-dimensional space.
+        X : ndarray or list
+            Input data representing a collection of point clouds or of distance
+            matrices. Can be either a 3D ndarray whose zeroth dimension has
+            size ``n_samples``, or a list containing ``n_samples`` 2D ndarrays.
+            If ``metric == 'precomputed'``, elements of `X` must be square
+            arrays representing distance matrices; otherwise, their rows are
+            interpreted as vectors in Euclidean space and, when `X` is a list,
+            warnings are issued when the number of columns (dimension of the
+            Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline
@@ -270,7 +274,7 @@ class SparseRipsPersistence(BaseEstimator, TransformerMixin, PlotterMixin):
     Parameters
     ----------
     metric : string or callable, optional, default: ``'euclidean'``
-        If set to `'precomputed'`, input data is to be interpreted as a
+        If set to ``'precomputed'``, input data is to be interpreted as a
         collection of distance matrices. Otherwise, input data is to be
         interpreted as a collection of point clouds (i.e. feature arrays),
         and `metric` determines a rule with which to calculate distances
@@ -398,13 +402,15 @@ def fit(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray of shape (n_samples, n_points, n_points) or \
-            (n_samples, n_points, n_dimensions)
-            Input data. If ``metric == 'precomputed'``, the input should be an
-            ndarray whose each entry along axis 0 is a distance matrix of shape
-            ``(n_points, n_points)``. Otherwise, each such entry will be
-            interpreted as an ndarray of ``n_points`` row vectors in
-            ``n_dimensions``-dimensional space.
+        X : ndarray or list
+            Input data representing a collection of point clouds or of distance
+            matrices. Can be either a 3D ndarray whose zeroth dimension has
+            size ``n_samples``, or a list containing ``n_samples`` 2D ndarrays.
+            If ``metric == 'precomputed'``, elements of `X` must be square
+            arrays representing distance matrices; otherwise, their rows are
+            interpreted as vectors in Euclidean space and, when `X` is a list,
+            warnings are issued when the number of columns (dimension of the
+            Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline
@@ -443,13 +449,15 @@ def transform(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray of shape (n_samples, n_points, n_points) or \
-            (n_samples, n_points, n_dimensions)
-            Input data. If ``metric == 'precomputed'``, the input should be an
-            ndarray whose each entry along axis 0 is a distance matrix of shape
-            ``(n_points, n_points)``. Otherwise, each such entry will be
-            interpreted as an ndarray of ``n_points`` row vectors in
-            ``n_dimensions``-dimensional space.
+        X : ndarray or list
+            Input data representing a collection of point clouds or of distance
+            matrices. Can be either a 3D ndarray whose zeroth dimension has
+            size ``n_samples``, or a list containing ``n_samples`` 2D ndarrays.
+            If ``metric == 'precomputed'``, elements of `X` must be square
+            arrays representing distance matrices; otherwise, their rows are
+            interpreted as vectors in Euclidean space and, when `X` is a list,
+            warnings are issued when the number of columns (dimension of the
+            Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline
@@ -616,9 +624,13 @@ def fit(self, X, y=None):
 
         Parameters
         ----------
-        X : ndarray of shape (n_samples, n_points, n_dimensions)
-            Input data. Each entry along axis 0 is a point cloud of
-            ``n_points`` row vectors in ``n_dimensions``-dimensional space.
+        X : ndarray or list
+            Input data representing a collection of point clouds. Can be
+            either a 3D ndarray whose zeroth dimension has size ``n_samples``,
+            or a list containing ``n_samples`` 2D ndarrays. The rows of
+            elements in `X` are interpreted as vectors in Euclidean space and.
+            and, when `X` is a list, warnings are issued when the number of
+            columns (dimension of the Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline
@@ -657,8 +669,12 @@ def transform(self, X, y=None):
         Parameters
         ----------
         X : ndarray of shape (n_samples, n_points, n_dimensions)
-            Input data. Each entry along axis 0 is a point cloud of
-            ``n_points`` row vectors in ``n_dimensions``-dimensional space.
+            Input data representing a collection of point clouds. Can be
+            either a 3D ndarray whose zeroth dimension has size ``n_samples``,
+            or a list containing ``n_samples`` 2D ndarrays. The rows of
+            elements in `X` are interpreted as vectors in Euclidean space and.
+            and, when `X` is a list, warnings are issued when the number of
+            columns (dimension of the Euclidean space) differs among samples.
 
         y : None
             There is no need for a target in a transformer, yet the pipeline

From 2ed3ad164d13c82495942396e5f23b01af9134da Mon Sep 17 00:00:00 2001
From: Umberto <u.lupo@l2f.ch>
Date: Mon, 23 Mar 2020 09:41:35 +0100
Subject: [PATCH 45/45] Revert to trivial slicing in transform_plot method of
 PlotterMixin

Needed to cover the case of list input
---
 gtda/base.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gtda/base.py b/gtda/base.py
index e6a10f2e2..25a981e63 100644
--- a/gtda/base.py
+++ b/gtda/base.py
@@ -139,7 +139,7 @@ def transform_plot(self, X, sample=0, **plot_params):
             Transformed one-sample slice from the input.
 
         """
-        Xt = self.transform(X[[sample]])
+        Xt = self.transform(X[sample:sample+1])
         self.plot(Xt, sample=0, **plot_params)
 
         return Xt