MAINT Replace stats.mode calls with fixes._mode

azure-pipelines.yml

@@ -45,7 +45,7 @@ jobs:
         versionSpec: '3.9'
     - bash: |
         # Include pytest compatibility with mypy
-        pip install pytest flake8 mypy==0.782 black==22.3
+        pip install pytest flake8==5.0.4 mypy==0.782 black==22.3
       displayName: Install linters
     - bash: |
         black --check --diff .
@@ -146,7 +146,7 @@ jobs:
         CONDA_CHANNEL: 'conda-forge'
         PYTHON_VERSION: '3.8'
         BLAS: 'openblas'
-        NUMPY_VERSION: '1.19.5'  # we cannot get an older version of the dependencies resolution
+        NUMPY_VERSION: '1.21.0'  # we cannot get an older version of the dependencies resolution
         SCIPY_VERSION: 'min'
         SKLEARN_VERSION: 'min'
         MATPLOTLIB_VERSION: 'none'

imblearn/_min_dependencies.py

@@ -4,10 +4,10 @@
 NUMPY_MIN_VERSION = "1.17.3"
 SCIPY_MIN_VERSION = "1.3.2"
 PANDAS_MIN_VERSION = "1.0.5"
-SKLEARN_MIN_VERSION = "1.1.0"
+SKLEARN_MIN_VERSION = "1.1.3"
 TENSORFLOW_MIN_VERSION = "2.4.3"
 KERAS_MIN_VERSION = "2.4.3"
-JOBLIB_MIN_VERSION = "1.0.0"
+JOBLIB_MIN_VERSION = "1.1.1"
 THREADPOOLCTL_MIN_VERSION = "2.0.0"
 PYTEST_MIN_VERSION = "5.0.1"
 

imblearn/over_sampling/_smote/base.py

@@ -12,7 +12,6 @@
 
 import numpy as np
 from scipy import sparse
-from scipy import stats
 
 from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder
 from sklearn.utils import check_random_state
@@ -29,6 +28,7 @@
 from ...utils._docstring import _n_jobs_docstring
 from ...utils._docstring import _random_state_docstring
 from ...utils._validation import _deprecate_positional_args
+from ...utils.fixes import _mode
 
 
 class BaseSMOTE(BaseOverSampler):
@@ -786,7 +786,7 @@ def _make_samples(self, X_class, klass, y_dtype, nn_indices, n_samples):
         # where for each feature individually, each category generated is the
         # most common category
         X_new = np.squeeze(
-            stats.mode(X_class[nn_indices[samples_indices]], axis=1).mode, axis=1
+            _mode(X_class[nn_indices[samples_indices]], axis=1).mode, axis=1
         )
         y_new = np.full(n_samples, fill_value=klass, dtype=y_dtype)
         return X_new, y_new

imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py

@@ -9,7 +9,6 @@
 from collections import Counter
 
 import numpy as np
-from scipy.stats import mode
 
 from sklearn.utils import _safe_indexing
 
@@ -18,6 +17,8 @@
 from ...utils import Substitution
 from ...utils._docstring import _n_jobs_docstring
 from ...utils._validation import _deprecate_positional_args
+from ...utils.fixes import _mode
+
 
 SEL_KIND = ("all", "mode")
 
@@ -155,7 +156,7 @@ def _fit_resample(self, X, y):
                 nnhood_idx = self.nn_.kneighbors(X_class, return_distance=False)[:, 1:]
                 nnhood_label = y[nnhood_idx]
                 if self.kind_sel == "mode":
-                    nnhood_label, _ = mode(nnhood_label, axis=1)
+                    nnhood_label, _ = _mode(nnhood_label, axis=1)
                     nnhood_bool = np.ravel(nnhood_label) == y_class
                 elif self.kind_sel == "all":
                     nnhood_label = nnhood_label == target_class

imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py

@@ -7,7 +7,6 @@
 from collections import Counter
 
 import numpy as np
-from scipy.stats import mode
 
 from sklearn.utils import _safe_indexing
 
@@ -17,6 +16,8 @@
 from ...utils import Substitution
 from ...utils._docstring import _n_jobs_docstring
 from ...utils._validation import _deprecate_positional_args
+from ...utils.fixes import _mode
+
 
 SEL_KIND = ("all", "mode")
 
@@ -182,7 +183,7 @@ def _fit_resample(self, X, y):
         nnhood_idx = self.nn_.kneighbors(X_class, return_distance=False)[:, 1:]
         nnhood_label = y[nnhood_idx]
         if self.kind_sel == "mode":
-            nnhood_label_majority, _ = mode(nnhood_label, axis=1)
+            nnhood_label_majority, _ = _mode(nnhood_label, axis=1)
             nnhood_bool = np.ravel(nnhood_label_majority) == y_class
         elif self.kind_sel == "all":
             nnhood_label_majority = nnhood_label == class_minority

imblearn/utils/fixes.py

@@ -0,0 +1,26 @@
+"""Compatibility fixes for older version of python, numpy and scipy
+If you add content to this file, please give the version of the package
+at which the fix is no longer needed.
+
+Backdated from scikit-learn.
+"""
+# Authors: Emmanuelle Gouillart <emmanuelle.gouillart@normalesup.org>
+#          Gael Varoquaux <gael.varoquaux@normalesup.org>
+#          Fabian Pedregosa <fpedregosa@acm.org>
+#          Lars Buitinck
+#
+# License: BSD 3 clause
+
+from sklearn.externals._packaging.version import parse as parse_version
+import scipy
+import scipy.stats
+
+
+sp_version = parse_version(scipy.__version__)
+
+
+# TODO: Remove when SciPy 1.9 is the minimum supported version
+def _mode(a, axis=0):
+    if sp_version >= parse_version("1.9.0"):
+        return scipy.stats.mode(a, axis=axis, keepdims=True)
+    return scipy.stats.mode(a, axis=axis)