MAINT add compatibilty for sklearn 1.0 (#949)

Author: glemaitre

README.rst

@@ -30,7 +30,7 @@
 .. |PythonMinVersion| replace:: 3.8
 .. |NumPyMinVersion| replace:: 1.17.3
 .. |SciPyMinVersion| replace:: 1.3.2
-.. |ScikitLearnMinVersion| replace:: 1.1.3
+.. |ScikitLearnMinVersion| replace:: 1.0.2
 .. |MatplotlibMinVersion| replace:: 3.1.2
 .. |PandasMinVersion| replace:: 1.0.5
 .. |TensorflowMinVersion| replace:: 2.4.3

azure-pipelines.yml

@@ -158,7 +158,7 @@ jobs:
       # Linux environment to test the latest available dependencies and MKL.
       pylatest_pip_openblas_pandas:
         DISTRIB: 'conda-pip-latest'
-        PYTHON_VERSION: '3.9'
+        PYTHON_VERSION: '*'
         TEST_DOCS: 'true'
         TEST_DOCSTRINGS: 'true'
         CHECK_WARNINGS: 'true'
@@ -185,7 +185,7 @@ jobs:
         TENSORFLOW_VERSION: 'min'
         TEST_DOCS: 'true'
         TEST_DOCSTRINGS: 'false'  # it is going to fail because of scikit-learn inheritance
-        CHECK_WARNINGS: 'true'
+        CHECK_WARNINGS: 'false'  # in case the older version raise some FutureWarnings
       pylatest_pip_keras:
         DISTRIB: 'conda-pip-latest-keras'
         CONDA_CHANNEL: 'conda-forge'
@@ -209,7 +209,7 @@ jobs:
         KERAS_VERSION: 'min'
         TEST_DOCS: 'true'
         TEST_DOCSTRINGS: 'false'  # it is going to fail because of scikit-learn inheritance
-        CHECK_WARNINGS: 'true'
+        CHECK_WARNINGS: 'false'  # in case the older version raise some FutureWarnings
 
 # Currently runs on Python 3.8 while only Python 3.7 available
 # - template: build_tools/azure/posix-docker.yml

build_tools/azure/posix-docker.yml

@@ -30,6 +30,7 @@ jobs:
     THREADPOOLCTL_VERSION: 'latest'
     COVERAGE: 'false'
     TEST_DOCSTRINGS: 'false'
+    CHECK_WARNINGS: 'false'
     BLAS: 'openblas'
     # Set in azure-pipelines.yml
     DISTRIB: ''

build_tools/azure/posix.yml

@@ -36,6 +36,7 @@ jobs:
     COVERAGE: 'true'
     TEST_DOCS: 'false'
     TEST_DOCSTRINGS: 'false'
+    CHECK_WARNINGS: 'false'
     SHOW_SHORT_SUMMARY: 'false'
   strategy:
     matrix:

build_tools/azure/test_script.sh

@@ -34,7 +34,7 @@ if [[ "$COVERAGE" == "true" ]]; then
     TEST_CMD="$TEST_CMD --cov-config='$COVERAGE_PROCESS_START' --cov imblearn --cov-report="
 fi
 
-if [[ -n "$CHECK_WARNINGS" ]]; then
+if [[ "$CHECK_WARNINGS" == "true" ]]; then
     # numpy's 1.19.0's tostring() deprecation is ignored until scipy and joblib removes its usage
     TEST_CMD="$TEST_CMD -Werror::DeprecationWarning -Werror::FutureWarning -Wignore:tostring:DeprecationWarning"
 

build_tools/azure/windows.yml

@@ -21,6 +21,7 @@ jobs:
     PYTEST_XDIST_VERSION: 'latest'
     TEST_DIR: '$(Agent.WorkFolder)/tmp_folder'
     CPU_COUNT: '2'
+    CHECK_WARNINGS: 'false'
   strategy:
     matrix:
       ${{ insert }}: ${{ parameters.matrix }}

doc/ensemble.rst

@@ -38,7 +38,7 @@ data set, this classifier will favor the majority classes::
   >>> bc.fit(X_train, y_train) #doctest:
   BaggingClassifier(...)
   >>> y_pred = bc.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
+  >>> balanced_accuracy_score(y_test, y_pred)
   0.77...
 
 In :class:`BalancedBaggingClassifier`, each bootstrap sample will be further
@@ -54,10 +54,10 @@ sampling is controlled by the parameter `sampler` or the two parameters
   ...                                 sampling_strategy='auto',
   ...                                 replacement=False,
   ...                                 random_state=0)
-  >>> bbc.fit(X_train, y_train) # doctest:
+  >>> bbc.fit(X_train, y_train)
   BalancedBaggingClassifier(...)
   >>> y_pred = bbc.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
+  >>> balanced_accuracy_score(y_test, y_pred)
   0.8...
 
 Changing the `sampler` will give rise to different known implementation
@@ -78,10 +78,10 @@ each tree of the forest will be provided a balanced bootstrap sample
 
   >>> from imblearn.ensemble import BalancedRandomForestClassifier
   >>> brf = BalancedRandomForestClassifier(n_estimators=100, random_state=0)
-  >>> brf.fit(X_train, y_train) # doctest:
+  >>> brf.fit(X_train, y_train)
   BalancedRandomForestClassifier(...)
   >>> y_pred = brf.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
+  >>> balanced_accuracy_score(y_test, y_pred)
   0.8...
 
 .. _boosting:
@@ -97,10 +97,10 @@ a boosting iteration :cite:`seiffert2009rusboost`::
   >>> from imblearn.ensemble import RUSBoostClassifier
   >>> rusboost = RUSBoostClassifier(n_estimators=200, algorithm='SAMME.R',
   ...                               random_state=0)
-  >>> rusboost.fit(X_train, y_train)  # doctest:
+  >>> rusboost.fit(X_train, y_train)
   RUSBoostClassifier(...)
   >>> y_pred = rusboost.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
+  >>> balanced_accuracy_score(y_test, y_pred)
   0...
 
 A specific method which uses :class:`~sklearn.ensemble.AdaBoostClassifier` as
@@ -111,10 +111,10 @@ the :class:`BalancedBaggingClassifier` API, one can construct the ensemble as::
 
   >>> from imblearn.ensemble import EasyEnsembleClassifier
   >>> eec = EasyEnsembleClassifier(random_state=0)
-  >>> eec.fit(X_train, y_train) # doctest:
+  >>> eec.fit(X_train, y_train)
   EasyEnsembleClassifier(...)
   >>> y_pred = eec.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
+  >>> balanced_accuracy_score(y_test, y_pred)
   0.6...
 
 .. topic:: Examples

imblearn/_min_dependencies.py

@@ -4,7 +4,7 @@
 NUMPY_MIN_VERSION = "1.17.3"
 SCIPY_MIN_VERSION = "1.3.2"
 PANDAS_MIN_VERSION = "1.0.5"
-SKLEARN_MIN_VERSION = "1.1.3"
+SKLEARN_MIN_VERSION = "1.0.2"
 TENSORFLOW_MIN_VERSION = "2.4.3"
 KERAS_MIN_VERSION = "2.4.3"
 JOBLIB_MIN_VERSION = "1.1.1"

imblearn/combine/_smote_enn.py

@@ -89,7 +89,7 @@ class SMOTEENN(BaseSampler):
 
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
-    >>> from imblearn.combine import SMOTEENN # doctest:
+    >>> from imblearn.combine import SMOTEENN
     >>> X, y = make_classification(n_classes=2, class_sep=2,
     ... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0,
     ... n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10)

imblearn/combine/_smote_tomek.py

@@ -87,8 +87,7 @@ class SMOTETomek(BaseSampler):
 
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
-    >>> from imblearn.combine import \
-SMOTETomek # doctest:
+    >>> from imblearn.combine import SMOTETomek
     >>> X, y = make_classification(n_classes=2, class_sep=2,
     ... weights=[0.1, 0.9], n_informative=3, n_redundant=1, flip_y=0,
     ... n_features=20, n_clusters_per_class=1, n_samples=1000, random_state=10)