diff --git a/README.rst b/README.rst
index dee6419cb..900d8dc67 100644
--- a/README.rst
+++ b/README.rst
@@ -30,7 +30,7 @@
 .. |PythonMinVersion| replace:: 3.8
 .. |NumPyMinVersion| replace:: 1.17.3
 .. |SciPyMinVersion| replace:: 1.3.2
-.. |ScikitLearnMinVersion| replace:: 1.1.0
+.. |ScikitLearnMinVersion| replace:: 1.1.3
 .. |MatplotlibMinVersion| replace:: 3.1.2
 .. |PandasMinVersion| replace:: 1.0.5
 .. |TensorflowMinVersion| replace:: 2.4.3
diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index 4605d2ced..e733ed93f 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -51,7 +51,7 @@ jobs:
         black --check --diff .
       displayName: Run black
     - bash: |
-        ./build_tools/circle/linting.sh
+        ./build_tools/azure/linting.sh
       displayName: Run linting
     - bash: |
         mypy imblearn/
@@ -112,7 +112,7 @@ jobs:
         ne(variables['Build.Reason'], 'Schedule')
       )
     matrix:
-      py37_conda_forge_openblas_ubuntu_1804:
+      py38_conda_forge_openblas_ubuntu_1804:
         DISTRIB: 'conda'
         CONDA_CHANNEL: 'conda-forge'
         PYTHON_VERSION: '3.8'
@@ -141,12 +141,12 @@ jobs:
         THREADPOOLCTL_VERSION: 'min'
         COVERAGE: 'false'
       # Linux + Python 3.8 build with OpenBLAS and without SITE_JOBLIB
-      py37_conda_defaults_openblas:
+      py38_conda_defaults_openblas:
         DISTRIB: 'conda'
         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'
@@ -275,6 +275,3 @@ jobs:
         PYTHON_ARCH: '64'
         PYTEST_VERSION: '*'
         COVERAGE: 'true'
-      py38_pip_openblas_32bit:
-        PYTHON_VERSION: '3.8'
-        PYTHON_ARCH: '32'
diff --git a/build_tools/azure/install.sh b/build_tools/azure/install.sh
index 932c5b150..250d56dea 100755
--- a/build_tools/azure/install.sh
+++ b/build_tools/azure/install.sh
@@ -67,7 +67,8 @@ elif [[ "$DISTRIB" == "conda-pip-latest" ]]; then
     make_conda "python=$PYTHON_VERSION"
     python -m pip install -U pip
 
-    python -m pip install scikit-learn pandas matplotlib
+    python -m pip install pandas matplotlib
+    python -m pip install --pre scikit-learn
 
 elif [[ "$DISTRIB" == "conda-pip-latest-tensorflow" ]]; then
     make_conda "python=$PYTHON_VERSION"
diff --git a/build_tools/azure/linting.sh b/build_tools/azure/linting.sh
new file mode 100755
index 000000000..21ef53c80
--- /dev/null
+++ b/build_tools/azure/linting.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+
+set -e
+# pipefail is necessary to propagate exit codes
+set -o pipefail
+
+flake8 --show-source .
+echo -e "No problem detected by flake8\n"
+
+# For docstrings and warnings of deprecated attributes to be rendered
+# properly, the property decorator must come before the deprecated decorator
+# (else they are treated as functions)
+
+# do not error when grep -B1 "@property" finds nothing
+set +e
+bad_deprecation_property_order=`git grep -A 10 "@property"  -- "*.py" | awk '/@property/,/def /' | grep -B1 "@deprecated"`
+
+if [ ! -z "$bad_deprecation_property_order" ]
+then
+    echo "property decorator should come before deprecated decorator"
+    echo "found the following occurrencies:"
+    echo $bad_deprecation_property_order
+    exit 1
+fi
+
+# Check for default doctest directives ELLIPSIS and NORMALIZE_WHITESPACE
+
+doctest_directive="$(git grep -nw -E "# doctest\: \+(ELLIPSIS|NORMALIZE_WHITESPACE)")"
+
+if [ ! -z "$doctest_directive" ]
+then
+    echo "ELLIPSIS and NORMALIZE_WHITESPACE doctest directives are enabled by default, but were found in:"
+    echo "$doctest_directive"
+    exit 1
+fi
+
+joblib_import="$(git grep -l -A 10 -E "joblib import.+delayed" -- "*.py" ":!sklearn/utils/_joblib.py" ":!sklearn/utils/fixes.py")"
+
+if [ ! -z "$joblib_import" ]; then
+    echo "Use from sklearn.utils.fixes import delayed instead of joblib delayed. The following files contains imports to joblib.delayed:"
+    echo "$joblib_import"
+    exit 1
+fi
diff --git a/doc/ensemble.rst b/doc/ensemble.rst
index dabaee4a7..21d6a6e0c 100644
--- a/doc/ensemble.rst
+++ b/doc/ensemble.rst
@@ -35,10 +35,10 @@ data set, this classifier will favor the majority classes::
   >>> X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
   >>> bc = BaggingClassifier(base_estimator=DecisionTreeClassifier(),
   ...                        random_state=0)
-  >>> bc.fit(X_train, y_train) #doctest: +ELLIPSIS
+  >>> bc.fit(X_train, y_train) #doctest:
   BaggingClassifier(...)
   >>> y_pred = bc.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
+  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
   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: +ELLIPSIS
+  >>> bbc.fit(X_train, y_train) # doctest:
   BalancedBaggingClassifier(...)
   >>> y_pred = bbc.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
+  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
   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: +ELLIPSIS
+  >>> brf.fit(X_train, y_train) # doctest:
   BalancedRandomForestClassifier(...)
   >>> y_pred = brf.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
+  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
   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: +ELLIPSIS
+  >>> rusboost.fit(X_train, y_train)  # doctest:
   RUSBoostClassifier(...)
   >>> y_pred = rusboost.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
+  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
   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: +ELLIPSIS
+  >>> eec.fit(X_train, y_train) # doctest:
   EasyEnsembleClassifier(...)
   >>> y_pred = eec.predict(X_test)
-  >>> balanced_accuracy_score(y_test, y_pred)  # doctest: +ELLIPSIS
+  >>> balanced_accuracy_score(y_test, y_pred)  # doctest:
   0.6...
 
 .. topic:: Examples
diff --git a/doc/over_sampling.rst b/doc/over_sampling.rst
index 1c2b6a3fe..63cdc0dfa 100644
--- a/doc/over_sampling.rst
+++ b/doc/over_sampling.rst
@@ -40,7 +40,7 @@ a classifier::
 
   >>> from sklearn.svm import LinearSVC
   >>> clf = LinearSVC()
-  >>> clf.fit(X_resampled, y_resampled) # doctest : +ELLIPSIS
+  >>> clf.fit(X_resampled, y_resampled)
   LinearSVC(...)
 
 In the figure below, we compare the decision functions of a classifier trained
diff --git a/imblearn/_min_dependencies.py b/imblearn/_min_dependencies.py
index a9e0d41eb..72976f2b1 100644
--- a/imblearn/_min_dependencies.py
+++ b/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"
 
diff --git a/imblearn/combine/_smote_enn.py b/imblearn/combine/_smote_enn.py
index 4d2e411e6..df84b07c9 100644
--- a/imblearn/combine/_smote_enn.py
+++ b/imblearn/combine/_smote_enn.py
@@ -91,7 +91,7 @@ class SMOTEENN(BaseSampler):
 
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
-    >>> from imblearn.combine import SMOTEENN # doctest: +NORMALIZE_WHITESPACE
+    >>> from imblearn.combine import SMOTEENN # doctest:
     >>> 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)
diff --git a/imblearn/combine/_smote_tomek.py b/imblearn/combine/_smote_tomek.py
index c0c9b6e80..ad2303ff0 100644
--- a/imblearn/combine/_smote_tomek.py
+++ b/imblearn/combine/_smote_tomek.py
@@ -90,7 +90,7 @@ class SMOTETomek(BaseSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.combine import \
-SMOTETomek # doctest: +NORMALIZE_WHITESPACE
+SMOTETomek # doctest:
     >>> 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)
diff --git a/imblearn/ensemble/_bagging.py b/imblearn/ensemble/_bagging.py
index b35e5e570..9afc4fc1d 100644
--- a/imblearn/ensemble/_bagging.py
+++ b/imblearn/ensemble/_bagging.py
@@ -4,7 +4,9 @@
 #          Christos Aridas
 # License: MIT
 
+import inspect
 import numbers
+import warnings
 
 import numpy as np
 
@@ -41,10 +43,12 @@ class BalancedBaggingClassifier(BaggingClassifier):
 
     Parameters
     ----------
-    base_estimator : estimator object, default=None
+    estimator : estimator object, default=None
         The base estimator to fit on random subsets of the dataset.
         If None, then the base estimator is a decision tree.
 
+        .. versionadded:: 0.10
+
     n_estimators : int, default=10
         The number of base estimators in the ensemble.
 
@@ -100,18 +104,37 @@ class BalancedBaggingClassifier(BaggingClassifier):
 
         .. versionadded:: 0.8
 
+    base_estimator : estimator object, default=None
+        The base estimator to fit on random subsets of the dataset.
+        If None, then the base estimator is a decision tree.
+
+        .. deprecated:: 0.10
+           `base_estimator` was renamed to `estimator` in version 0.10 and
+           will be removed in 0.12.
+
     Attributes
     ----------
+    estimator_ : estimator
+        The base estimator from which the ensemble is grown.
+
+        .. versionadded:: 0.10
+
     base_estimator_ : estimator
         The base estimator from which the ensemble is grown.
 
+        .. deprecated:: 1.2
+           `base_estimator_` is deprecated in `scikit-learn` 1.2 and will be
+           removed in 1.4. Use `estimator_` instead. When the minimum version
+           of `scikit-learn` supported by `imbalanced-learn` will reach 1.4,
+           this attribute will be removed.
+
     n_features_ : int
         The number of features when `fit` is performed.
 
         .. deprecated:: 1.0
            `n_features_` is deprecated in `scikit-learn` 1.0 and will be removed
-           in version 1.2. Depending of the version of `scikit-learn` installed,
-           you will get be warned or not.
+           in version 1.2. When the minimum version of `scikit-learn` supported
+           by `imbalanced-learn` will reach 1.2, this attribute will be removed.
 
     estimators_ : list of estimators
         The collection of fitted base estimators.
@@ -209,7 +232,7 @@ class BalancedBaggingClassifier(BaggingClassifier):
     >>> from sklearn.model_selection import train_test_split
     >>> from sklearn.metrics import confusion_matrix
     >>> from imblearn.ensemble import \
-BalancedBaggingClassifier # doctest: +NORMALIZE_WHITESPACE
+BalancedBaggingClassifier # doctest:
     >>> 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)
@@ -218,7 +241,7 @@ class BalancedBaggingClassifier(BaggingClassifier):
     >>> X_train, X_test, y_train, y_test = train_test_split(X, y,
     ...                                                     random_state=0)
     >>> bbc = BalancedBaggingClassifier(random_state=42)
-    >>> bbc.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> bbc.fit(X_train, y_train) # doctest:
     BalancedBaggingClassifier(...)
     >>> y_pred = bbc.predict(X_test)
     >>> print(confusion_matrix(y_test, y_pred))
@@ -229,7 +252,7 @@ class BalancedBaggingClassifier(BaggingClassifier):
     @_deprecate_positional_args
     def __init__(
         self,
-        base_estimator=None,
+        estimator=None,
         n_estimators=10,
         *,
         max_samples=1.0,
@@ -244,10 +267,18 @@ def __init__(
         random_state=None,
         verbose=0,
         sampler=None,
+        base_estimator="deprecated",
     ):
+        # TODO: remove when supporting scikit-learn>=1.2
+        bagging_classifier_signature = inspect.signature(super().__init__)
+        estimator_params = {"base_estimator": base_estimator}
+        if "estimator" in bagging_classifier_signature.parameters:
+            estimator_params["estimator"] = estimator
+        else:
+            self.estimator = estimator
 
         super().__init__(
-            base_estimator,
+            **estimator_params,
             n_estimators=n_estimators,
             max_samples=max_samples,
             max_features=max_features,
@@ -294,7 +325,21 @@ def _validate_estimator(self, default=DecisionTreeClassifier()):
                 f"n_estimators must be greater than zero, " f"got {self.n_estimators}."
             )
 
-        if self.base_estimator is not None:
+        if self.estimator is not None and (
+            self.base_estimator not in [None, "deprecated"]
+        ):
+            raise ValueError(
+                "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+            )
+
+        if self.estimator is not None:
+            base_estimator = clone(self.estimator)
+        elif self.base_estimator not in [None, "deprecated"]:
+            warnings.warn(
+                "`base_estimator` was renamed to `estimator` in version 0.10 and "
+                "will be removed in 0.12.",
+                FutureWarning,
+            )
             base_estimator = clone(self.base_estimator)
         else:
             base_estimator = clone(default)
@@ -302,12 +347,32 @@ def _validate_estimator(self, default=DecisionTreeClassifier()):
         if self.sampler_._sampling_type != "bypass":
             self.sampler_.set_params(sampling_strategy=self._sampling_strategy)
 
-        self.base_estimator_ = Pipeline(
-            [
-                ("sampler", self.sampler_),
-                ("classifier", base_estimator),
-            ]
+        self._estimator = Pipeline(
+            [("sampler", self.sampler_), ("classifier", base_estimator)]
+        )
+        try:
+            # scikit-learn < 1.2
+            self.base_estimator_ = self._estimator
+        except AttributeError:
+            pass
+
+    # TODO: remove when supporting scikit-learn>=1.4
+    @property
+    def estimator_(self):
+        """Estimator used to grow the ensemble."""
+        return self._estimator
+
+    # TODO: remove when supporting scikit-learn>=1.2
+    @property
+    def n_features_(self):
+        """Number of features when ``fit`` is performed."""
+        warnings.warn(
+            "`n_features_` was deprecated in scikit-learn 1.0. This attribute will "
+            "not be accessible when the minimum supported version of scikit-learn "
+            "is 1.2.",
+            FutureWarning,
         )
+        return self.n_features_in_
 
     def fit(self, X, y):
         """Build a Bagging ensemble of estimators from the training set (X, y).
diff --git a/imblearn/ensemble/_easy_ensemble.py b/imblearn/ensemble/_easy_ensemble.py
index 40b9f3953..16030020d 100644
--- a/imblearn/ensemble/_easy_ensemble.py
+++ b/imblearn/ensemble/_easy_ensemble.py
@@ -4,7 +4,9 @@
 #          Christos Aridas
 # License: MIT
 
+import inspect
 import numbers
+import warnings
 
 import numpy as np
 
@@ -44,10 +46,12 @@ class EasyEnsembleClassifier(BaggingClassifier):
     n_estimators : int, default=10
         Number of AdaBoost learners in the ensemble.
 
-    base_estimator : estimator object, default=AdaBoostClassifier()
+    estimator : estimator object, default=AdaBoostClassifier()
         The base AdaBoost classifier used in the inner ensemble. Note that you
         can set the number of inner learner by passing your own instance.
 
+        .. versionadded:: 0.10
+
     warm_start : bool, default=False
         When set to True, reuse the solution of the previous call to fit
         and add more estimators to the ensemble, otherwise, just fit
@@ -65,11 +69,30 @@ class EasyEnsembleClassifier(BaggingClassifier):
     verbose : int, default=0
         Controls the verbosity of the building process.
 
+    base_estimator : estimator object, default=AdaBoostClassifier()
+        The base AdaBoost classifier used in the inner ensemble. Note that you
+        can set the number of inner learner by passing your own instance.
+
+        .. deprecated:: 0.10
+           `base_estimator` was renamed to `estimator` in version 0.10 and will
+           be removed in 0.12.
+
     Attributes
     ----------
+    estimator_ : estimator
+        The base estimator from which the ensemble is grown.
+
+        .. versionadded:: 0.10
+
     base_estimator_ : estimator
         The base estimator from which the ensemble is grown.
 
+        .. deprecated:: 1.2
+           `base_estimator_` is deprecated in `scikit-learn` 1.2 and will be
+           removed in 1.4. Use `estimator_` instead. When the minimum version
+           of `scikit-learn` supported by `imbalanced-learn` will reach 1.4,
+           this attribute will be removed.
+
     estimators_ : list of estimators
         The collection of fitted base estimators.
 
@@ -86,12 +109,12 @@ class EasyEnsembleClassifier(BaggingClassifier):
         The number of classes.
 
     n_features_ : int
-        The number of features when ``fit`` is performed.
+        The number of features when `fit` is performed.
 
         .. deprecated:: 1.0
            `n_features_` is deprecated in `scikit-learn` 1.0 and will be removed
-           in version 1.2. Depending of the version of `scikit-learn` installed,
-           you will get be warned or not.
+           in version 1.2. When the minimum version of `scikit-learn` supported
+           by `imbalanced-learn` will reach 1.2, this attribute will be removed.
 
     n_features_in_ : int
         Number of features in the input dataset.
@@ -135,7 +158,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
     >>> from sklearn.model_selection import train_test_split
     >>> from sklearn.metrics import confusion_matrix
     >>> from imblearn.ensemble import \
-EasyEnsembleClassifier # doctest: +NORMALIZE_WHITESPACE
+EasyEnsembleClassifier # doctest:
     >>> 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)
@@ -144,7 +167,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
     >>> X_train, X_test, y_train, y_test = train_test_split(X, y,
     ...                                                     random_state=0)
     >>> eec = EasyEnsembleClassifier(random_state=42)
-    >>> eec.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> eec.fit(X_train, y_train) # doctest:
     EasyEnsembleClassifier(...)
     >>> y_pred = eec.predict(X_test)
     >>> print(confusion_matrix(y_test, y_pred))
@@ -156,7 +179,7 @@ class EasyEnsembleClassifier(BaggingClassifier):
     def __init__(
         self,
         n_estimators=10,
-        base_estimator=None,
+        estimator=None,
         *,
         warm_start=False,
         sampling_strategy="auto",
@@ -164,9 +187,18 @@ def __init__(
         n_jobs=None,
         random_state=None,
         verbose=0,
+        base_estimator="deprecated",
     ):
+        # TODO: remove when supporting scikit-learn>=1.2
+        bagging_classifier_signature = inspect.signature(super().__init__)
+        estimator_params = {"base_estimator": base_estimator}
+        if "estimator" in bagging_classifier_signature.parameters:
+            estimator_params["estimator"] = estimator
+        else:
+            self.estimator = estimator
+
         super().__init__(
-            base_estimator,
+            **estimator_params,
             n_estimators=n_estimators,
             max_samples=1.0,
             max_features=1.0,
@@ -209,23 +241,55 @@ def _validate_estimator(self, default=AdaBoostClassifier()):
                 f"n_estimators must be greater than zero, " f"got {self.n_estimators}."
             )
 
-        if self.base_estimator is not None:
+        if self.estimator is not None and (
+            self.base_estimator not in [None, "deprecated"]
+        ):
+            raise ValueError(
+                "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+            )
+
+        if self.estimator is not None:
+            base_estimator = clone(self.estimator)
+        elif self.base_estimator not in [None, "deprecated"]:
+            warnings.warn(
+                "`base_estimator` was renamed to `estimator` in version 0.10 and "
+                "will be removed in 0.12.",
+                FutureWarning,
+            )
             base_estimator = clone(self.base_estimator)
         else:
             base_estimator = clone(default)
 
-        self.base_estimator_ = Pipeline(
-            [
-                (
-                    "sampler",
-                    RandomUnderSampler(
-                        sampling_strategy=self._sampling_strategy,
-                        replacement=self.replacement,
-                    ),
-                ),
-                ("classifier", base_estimator),
-            ]
+        sampler = RandomUnderSampler(
+            sampling_strategy=self._sampling_strategy,
+            replacement=self.replacement,
+        )
+        self._estimator = Pipeline(
+            [("sampler", sampler), ("classifier", base_estimator)]
+        )
+        try:
+            self.base_estimator_ = self._estimator
+        except AttributeError:
+            # scikit-learn < 1.2
+            pass
+
+    # TODO: remove when supporting scikit-learn>=1.4
+    @property
+    def estimator_(self):
+        """Estimator used to grow the ensemble."""
+        return self._estimator
+
+    # TODO: remove when supporting scikit-learn>=1.2
+    @property
+    def n_features_(self):
+        """Number of features when ``fit`` is performed."""
+        warnings.warn(
+            "`n_features_` was deprecated in scikit-learn 1.0. This attribute will "
+            "not be accessible when the minimum supported version of scikit-learn "
+            "is 1.2.",
+            FutureWarning,
         )
+        return self.n_features_in_
 
     def fit(self, X, y):
         """Build a Bagging ensemble of estimators from the training set (X, y).
diff --git a/imblearn/ensemble/_forest.py b/imblearn/ensemble/_forest.py
index 77c2de908..3af09c8f7 100644
--- a/imblearn/ensemble/_forest.py
+++ b/imblearn/ensemble/_forest.py
@@ -12,7 +12,7 @@
 from numpy import float64 as DOUBLE
 from scipy.sparse import issparse
 
-from joblib import Parallel, delayed
+from joblib import Parallel
 
 from sklearn.base import clone, is_classifier
 from sklearn.ensemble import RandomForestClassifier
@@ -24,6 +24,7 @@
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.utils import check_random_state
 from sklearn.utils import _safe_indexing
+from sklearn.utils.fixes import delayed
 from sklearn.utils.multiclass import type_of_target
 from sklearn.utils.validation import _check_sample_weight
 
@@ -230,10 +231,22 @@ class BalancedRandomForestClassifier(RandomForestClassifier):
 
     Attributes
     ----------
+    estimator_ : :class:`~sklearn.tree.DecisionTreeClassifier` instance
+        The child estimator template used to create the collection of fitted
+        sub-estimators.
+
+        .. versionadded:: 0.10
+
     base_estimator_ : :class:`~sklearn.tree.DecisionTreeClassifier` instance
         The child estimator template used to create the collection of fitted
         sub-estimators.
 
+        .. deprecated:: 1.2
+           `base_estimator_` is deprecated in `scikit-learn` 1.2 and will be
+           removed in 1.4. Use `estimator_` instead. When the minimum version
+           of `scikit-learn` supported by `imbalanced-learn` will reach 1.4,
+           this attribute will be removed.
+
     estimators_ : list of :class:`~sklearn.tree.DecisionTreeClassifier`
         The collection of fitted sub-estimators.
 
@@ -255,12 +268,12 @@ class labels (multi-output problem).
         number of classes for each output (multi-output problem).
 
     n_features_ : int
-        The number of features when ``fit`` is performed.
+        The number of features when `fit` is performed.
 
         .. deprecated:: 1.0
            `n_features_` is deprecated in `scikit-learn` 1.0 and will be removed
-           in version 1.2. Depending of the version of `scikit-learn` installed,
-           you will get be warned or not.
+           in version 1.2. When the minimum version of `scikit-learn` supported
+           by `imbalanced-learn` will reach 1.2, this attribute will be removed.
 
     n_features_in_ : int
         Number of features in the input dataset.
@@ -314,9 +327,9 @@ class labels (multi-output problem).
     ...                            n_informative=4, weights=[0.2, 0.3, 0.5],
     ...                            random_state=0)
     >>> clf = BalancedRandomForestClassifier(max_depth=2, random_state=0)
-    >>> clf.fit(X, y)  # doctest: +ELLIPSIS
+    >>> clf.fit(X, y)  # doctest:
     BalancedRandomForestClassifier(...)
-    >>> print(clf.feature_importances_)  # doctest: +ELLIPSIS
+    >>> print(clf.feature_importances_)  # doctest:
     [...]
     >>> print(clf.predict([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
     ...                     0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]))
@@ -385,10 +398,21 @@ def _validate_estimator(self, default=DecisionTreeClassifier()):
                 f"n_estimators must be greater than zero, " f"got {self.n_estimators}."
             )
 
-        if self.base_estimator is not None:
-            self.base_estimator_ = clone(self.base_estimator)
+        if hasattr(self, "estimator"):
+            base_estimator = self.estimator
         else:
-            self.base_estimator_ = clone(default)
+            base_estimator = self.base_estimator
+
+        if base_estimator is not None:
+            self._estimator = clone(base_estimator)
+        else:
+            self._estimator = clone(default)
+
+        try:
+            # scikit-learn < 1.2
+            self.base_estimator_ = self._estimator
+        except AttributeError:
+            pass
 
         self.base_sampler_ = RandomUnderSampler(
             sampling_strategy=self._sampling_strategy,
@@ -400,7 +424,7 @@ def _make_sampler_estimator(self, random_state=None):
         Warning: This method should be used to properly instantiate new
         sub-estimators.
         """
-        estimator = clone(self.base_estimator_)
+        estimator = clone(self._estimator)
         estimator.set_params(**{p: getattr(self, p) for p in self.estimator_params})
         sampler = clone(self.base_sampler_)
 
@@ -691,10 +715,23 @@ def _compute_oob_predictions(self, X, y):
 
         return oob_pred
 
+    # TODO: remove when supporting scikit-learn>=1.4
+    @property
+    def estimator_(self):
+        """Estimator used to grow the ensemble."""
+        return self._estimator
+
+    # TODO: remove when supporting scikit-learn>=1.2
     @property
     def n_features_(self):
-        """Number of features when fitting the estimator."""
-        return getattr(self.n_features_in_, "n_features_", self._n_features)
+        """Number of features when ``fit`` is performed."""
+        warn(
+            "`n_features_` was deprecated in scikit-learn 1.0. This attribute will "
+            "not be accessible when the minimum supported version of scikit-learn "
+            "is 1.2.",
+            FutureWarning,
+        )
+        return self.n_features_in_
 
     def _more_tags(self):
         return {
diff --git a/imblearn/ensemble/_weight_boosting.py b/imblearn/ensemble/_weight_boosting.py
index 6376c3865..b7fdd2f65 100644
--- a/imblearn/ensemble/_weight_boosting.py
+++ b/imblearn/ensemble/_weight_boosting.py
@@ -1,3 +1,6 @@
+import inspect
+import numbers
+import warnings
 from copy import deepcopy
 
 import numpy as np
@@ -5,7 +8,9 @@
 from sklearn.base import clone
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.ensemble._base import _set_random_states
+from sklearn.tree import DecisionTreeClassifier
 from sklearn.utils import _safe_indexing
+from sklearn.utils.validation import has_fit_parameter
 
 from ..under_sampling.base import BaseUnderSampler
 from ..under_sampling import RandomUnderSampler
@@ -31,12 +36,14 @@ class RUSBoostClassifier(AdaBoostClassifier):
 
     Parameters
     ----------
-    base_estimator : estimator object, default=None
+    estimator : estimator object, default=None
         The base estimator from which the boosted ensemble is built.
         Support for sample weighting is required, as well as proper
         ``classes_`` and ``n_classes_`` attributes. If ``None``, then
         the base estimator is ``DecisionTreeClassifier(max_depth=1)``.
 
+        .. versionadded:: 0.12
+
     n_estimators : int, default=50
         The maximum number of estimators at which boosting is terminated.
         In case of perfect fit, the learning procedure is stopped early.
@@ -60,11 +67,32 @@ class RUSBoostClassifier(AdaBoostClassifier):
 
     {random_state}
 
+    base_estimator : estimator object, default=None
+        The base estimator from which the boosted ensemble is built.
+        Support for sample weighting is required, as well as proper
+        ``classes_`` and ``n_classes_`` attributes. If ``None``, then
+        the base estimator is ``DecisionTreeClassifier(max_depth=1)``.
+
+        .. deprecated:: 0.10
+           `base_estimator` is deprecated in version 0.10 and will be removed
+           in 0.12. Use `estimator` instead.
+
     Attributes
     ----------
+    estimator_ : estimator
+        The base estimator from which the ensemble is grown.
+
+        .. versionadded:: 0.10
+
     base_estimator_ : estimator
         The base estimator from which the ensemble is grown.
 
+        .. deprecated:: 1.2
+           `base_estimator_` is deprecated in `scikit-learn` 1.2 and will be
+           removed in 1.4. Use `estimator_` instead. When the minimum version
+           of `scikit-learn` supported by `imbalanced-learn` will reach 1.4,
+           this attribute will be removed.
+
     estimators_ : list of classifiers
         The collection of fitted sub-estimators.
 
@@ -125,16 +153,16 @@ class RUSBoostClassifier(AdaBoostClassifier):
     ...                            n_informative=4, weights=[0.2, 0.3, 0.5],
     ...                            random_state=0)
     >>> clf = RUSBoostClassifier(random_state=0)
-    >>> clf.fit(X, y)  # doctest: +ELLIPSIS
+    >>> clf.fit(X, y)  # doctest:
     RUSBoostClassifier(...)
-    >>> clf.predict(X)  # doctest: +ELLIPSIS
+    >>> clf.predict(X)  # doctest:
     array([...])
     """
 
     @_deprecate_positional_args
     def __init__(
         self,
-        base_estimator=None,
+        estimator=None,
         *,
         n_estimators=50,
         learning_rate=1.0,
@@ -142,9 +170,18 @@ def __init__(
         sampling_strategy="auto",
         replacement=False,
         random_state=None,
+        base_estimator="deprecated",
     ):
+        # TODO: remove when supporting scikit-learn>=1.2
+        bagging_classifier_signature = inspect.signature(super().__init__)
+        estimator_params = {"base_estimator": base_estimator}
+        if "estimator" in bagging_classifier_signature.parameters:
+            estimator_params["estimator"] = estimator
+        else:
+            self.estimator = estimator
+
         super().__init__(
-            base_estimator=base_estimator,
+            **estimator_params,
             n_estimators=n_estimators,
             learning_rate=learning_rate,
             algorithm=algorithm,
@@ -181,9 +218,65 @@ def fit(self, X, y, sample_weight=None):
         return self
 
     def _validate_estimator(self):
-        """Check the estimator and the n_estimator attribute, set the
-        `base_estimator_` attribute."""
-        super()._validate_estimator()
+        """Check the estimator and the n_estimator attribute.
+
+        Sets the `estimator_` attributes.
+        """
+        if not isinstance(self.n_estimators, numbers.Integral):
+            raise ValueError(
+                "n_estimators must be an integer, got {0}.".format(
+                    type(self.n_estimators)
+                )
+            )
+
+        if self.n_estimators <= 0:
+            raise ValueError(
+                "n_estimators must be greater than zero, got {0}.".format(
+                    self.n_estimators
+                )
+            )
+
+        if self.estimator is not None and (
+            self.base_estimator not in [None, "deprecated"]
+        ):
+            raise ValueError(
+                "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+            )
+
+        default = DecisionTreeClassifier(max_depth=1)
+        if self.estimator is not None:
+            base_estimator = clone(self.estimator)
+        elif self.base_estimator not in [None, "deprecated"]:
+            warnings.warn(
+                "`base_estimator` was renamed to `estimator` in version 0.10 and "
+                "will be removed in 0.12.",
+                FutureWarning,
+            )
+            base_estimator = clone(self.base_estimator)
+        else:
+            base_estimator = clone(default)
+
+        self._estimator = base_estimator
+        try:
+            # scikit-learn < 1.2
+            self.base_estimator_ = self._estimator
+        except AttributeError:
+            pass
+
+        #  SAMME-R requires predict_proba-enabled estimators
+        if self.algorithm == "SAMME.R":
+            if not hasattr(self._estimator, "predict_proba"):
+                raise TypeError(
+                    "AdaBoostClassifier with algorithm='SAMME.R' requires "
+                    "that the weak learner supports the calculation of class "
+                    "probabilities with a predict_proba method.\n"
+                    "Please change the base estimator or set "
+                    "algorithm='SAMME' instead."
+                )
+        if not has_fit_parameter(self._estimator, "sample_weight"):
+            raise ValueError(
+                f"{self._estimator.__class__.__name__} doesn't support sample_weight."
+            )
 
         self.base_sampler_ = RandomUnderSampler(
             sampling_strategy=self.sampling_strategy,
@@ -195,7 +288,7 @@ def _make_sampler_estimator(self, append=True, random_state=None):
         Warning: This method should be used to properly instantiate new
         sub-estimators.
         """
-        estimator = clone(self.base_estimator_)
+        estimator = clone(self._estimator)
         estimator.set_params(**{p: getattr(self, p) for p in self.estimator_params})
         sampler = clone(self.base_sampler_)
 
@@ -323,3 +416,9 @@ def _boost_discrete(self, iboost, X, y, sample_weight, random_state):
             sample_weight *= np.exp(estimator_weight * incorrect * (sample_weight > 0))
 
         return sample_weight, estimator_weight, estimator_error
+
+    # TODO: remove when supporting scikit-learn>=1.4
+    @property
+    def estimator_(self):
+        """Estimator used to grow the ensemble."""
+        return self._estimator
diff --git a/imblearn/ensemble/tests/test_bagging.py b/imblearn/ensemble/tests/test_bagging.py
index f3eff340a..c398f1ded 100644
--- a/imblearn/ensemble/tests/test_bagging.py
+++ b/imblearn/ensemble/tests/test_bagging.py
@@ -8,18 +8,21 @@
 import numpy as np
 import pytest
 
+import sklearn
 from sklearn.datasets import load_iris, make_hastie_10_2, make_classification
 from sklearn.model_selection import (
     GridSearchCV,
     ParameterGrid,
     train_test_split,
 )
+from sklearn.cluster import KMeans
 from sklearn.dummy import DummyClassifier
 from sklearn.linear_model import Perceptron, LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.svm import SVC
 from sklearn.feature_selection import SelectKBest
+from sklearn.utils.fixes import parse_version
 from sklearn.utils._testing import assert_array_equal
 from sklearn.utils._testing import assert_array_almost_equal
 from sklearn.utils._testing import assert_allclose
@@ -31,11 +34,12 @@
 from imblearn.pipeline import make_pipeline
 from imblearn.under_sampling import ClusterCentroids, RandomUnderSampler
 
+sklearn_version = parse_version(sklearn.__version__)
 iris = load_iris()
 
 
 @pytest.mark.parametrize(
-    "base_estimator",
+    "estimator",
     [
         None,
         DummyClassifier(strategy="prior"),
@@ -56,7 +60,7 @@
         }
     ),
 )
-def test_balanced_bagging_classifier(base_estimator, params):
+def test_balanced_bagging_classifier(estimator, params):
     # Check classification for various parameter settings.
     X, y = make_imbalance(
         iris.data,
@@ -66,9 +70,9 @@ def test_balanced_bagging_classifier(base_estimator, params):
     )
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
-    BalancedBaggingClassifier(
-        base_estimator=base_estimator, random_state=0, **params
-    ).fit(X_train, y_train).predict(X_test)
+    BalancedBaggingClassifier(estimator=estimator, random_state=0, **params).fit(
+        X_train, y_train
+    ).predict(X_test)
 
 
 def test_bootstrap_samples():
@@ -81,12 +85,12 @@ def test_bootstrap_samples():
     )
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
-    base_estimator = DecisionTreeClassifier().fit(X_train, y_train)
+    estimator = DecisionTreeClassifier().fit(X_train, y_train)
 
     # without bootstrap, all trees are perfect on the training set
     # disable the resampling by passing an empty dictionary.
     ensemble = BalancedBaggingClassifier(
-        base_estimator=DecisionTreeClassifier(),
+        estimator=DecisionTreeClassifier(),
         max_samples=1.0,
         bootstrap=False,
         n_estimators=10,
@@ -94,17 +98,17 @@ def test_bootstrap_samples():
         random_state=0,
     ).fit(X_train, y_train)
 
-    assert ensemble.score(X_train, y_train) == base_estimator.score(X_train, y_train)
+    assert ensemble.score(X_train, y_train) == estimator.score(X_train, y_train)
 
     # with bootstrap, trees are no longer perfect on the training set
     ensemble = BalancedBaggingClassifier(
-        base_estimator=DecisionTreeClassifier(),
+        estimator=DecisionTreeClassifier(),
         max_samples=1.0,
         bootstrap=True,
         random_state=0,
     ).fit(X_train, y_train)
 
-    assert ensemble.score(X_train, y_train) < base_estimator.score(X_train, y_train)
+    assert ensemble.score(X_train, y_train) < estimator.score(X_train, y_train)
 
 
 def test_bootstrap_features():
@@ -118,7 +122,7 @@ def test_bootstrap_features():
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
     ensemble = BalancedBaggingClassifier(
-        base_estimator=DecisionTreeClassifier(),
+        estimator=DecisionTreeClassifier(),
         max_features=1.0,
         bootstrap_features=False,
         random_state=0,
@@ -128,7 +132,7 @@ def test_bootstrap_features():
         assert np.unique(features).shape[0] == X.shape[1]
 
     ensemble = BalancedBaggingClassifier(
-        base_estimator=DecisionTreeClassifier(),
+        estimator=DecisionTreeClassifier(),
         max_features=1.0,
         bootstrap_features=True,
         random_state=0,
@@ -153,7 +157,7 @@ def test_probability():
     with np.errstate(divide="ignore", invalid="ignore"):
         # Normal case
         ensemble = BalancedBaggingClassifier(
-            base_estimator=DecisionTreeClassifier(), random_state=0
+            estimator=DecisionTreeClassifier(), random_state=0
         ).fit(X_train, y_train)
 
         assert_array_almost_equal(
@@ -168,7 +172,7 @@ def test_probability():
 
         # Degenerate case, where some classes are missing
         ensemble = BalancedBaggingClassifier(
-            base_estimator=LogisticRegression(solver="lbfgs", multi_class="auto"),
+            estimator=LogisticRegression(solver="lbfgs", multi_class="auto"),
             random_state=0,
             max_samples=5,
         )
@@ -196,9 +200,9 @@ def test_oob_score_classification():
     )
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
-    for base_estimator in [DecisionTreeClassifier(), SVC(gamma="scale")]:
+    for estimator in [DecisionTreeClassifier(), SVC(gamma="scale")]:
         clf = BalancedBaggingClassifier(
-            base_estimator=base_estimator,
+            estimator=estimator,
             n_estimators=100,
             bootstrap=True,
             oob_score=True,
@@ -212,7 +216,7 @@ def test_oob_score_classification():
         # Test with few estimators
         with pytest.warns(UserWarning):
             BalancedBaggingClassifier(
-                base_estimator=base_estimator,
+                estimator=estimator,
                 n_estimators=1,
                 bootstrap=True,
                 oob_score=True,
@@ -231,7 +235,7 @@ def test_single_estimator():
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
 
     clf1 = BalancedBaggingClassifier(
-        base_estimator=KNeighborsClassifier(),
+        estimator=KNeighborsClassifier(),
         n_estimators=1,
         bootstrap=False,
         bootstrap_features=False,
@@ -269,7 +273,7 @@ def test_balanced_bagging_classifier_error(params):
         iris.data, iris.target, sampling_strategy={0: 20, 1: 25, 2: 50}
     )
     base = DecisionTreeClassifier()
-    clf = BalancedBaggingClassifier(base_estimator=base, **params)
+    clf = BalancedBaggingClassifier(estimator=base, **params)
     with pytest.raises(ValueError):
         clf.fit(X, y)
 
@@ -284,7 +288,7 @@ def test_gridsearch():
     y[y == 2] = 1
 
     # Grid search with scoring based on decision_function
-    parameters = {"n_estimators": (1, 2), "base_estimator__C": (1, 2)}
+    parameters = {"n_estimators": (1, 2), "estimator__C": (1, 2)}
 
     GridSearchCV(
         BalancedBaggingClassifier(SVC(gamma="scale")),
@@ -294,8 +298,8 @@ def test_gridsearch():
     ).fit(X, y)
 
 
-def test_base_estimator():
-    # Check base_estimator and its default values.
+def test_estimator():
+    # Check estimator and its default values.
     X, y = make_imbalance(
         iris.data,
         iris.target,
@@ -308,19 +312,19 @@ def test_base_estimator():
         X_train, y_train
     )
 
-    assert isinstance(ensemble.base_estimator_.steps[-1][1], DecisionTreeClassifier)
+    assert isinstance(ensemble.estimator_.steps[-1][1], DecisionTreeClassifier)
 
     ensemble = BalancedBaggingClassifier(
         DecisionTreeClassifier(), n_jobs=3, random_state=0
     ).fit(X_train, y_train)
 
-    assert isinstance(ensemble.base_estimator_.steps[-1][1], DecisionTreeClassifier)
+    assert isinstance(ensemble.estimator_.steps[-1][1], DecisionTreeClassifier)
 
     ensemble = BalancedBaggingClassifier(
         Perceptron(max_iter=1000, tol=1e-3), n_jobs=3, random_state=0
     ).fit(X_train, y_train)
 
-    assert isinstance(ensemble.base_estimator_.steps[-1][1], Perceptron)
+    assert isinstance(ensemble.estimator_.steps[-1][1], Perceptron)
 
 
 def test_bagging_with_pipeline():
@@ -518,12 +522,16 @@ def fit(self, X, y, sample_weight=None):
         return super().fit(X, y, sample_weight=sample_weight)
 
 
+@pytest.mark.filterwarnings("ignore:Number of distinct clusters")
 @pytest.mark.parametrize(
     "sampler, n_samples_bootstrap",
     [
         (None, 15),
         (RandomUnderSampler(), 15),  # under-sampling with sample_indices_
-        (ClusterCentroids(), 15),  # under-sampling without sample_indices_
+        (
+            ClusterCentroids(estimator=KMeans(n_init=1)),
+            15,
+        ),  # under-sampling without sample_indices_
         (RandomOverSampler(), 40),  # over-sampling with sample_indices_
         (SMOTE(), 40),  # over-sampling without sample_indices_
     ],
@@ -538,7 +546,7 @@ def test_balanced_bagging_classifier_samplers(sampler, n_samples_bootstrap):
     )
     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
     clf = BalancedBaggingClassifier(
-        base_estimator=CountDecisionTreeClassifier(),
+        estimator=CountDecisionTreeClassifier(),
         n_estimators=2,
         sampler=sampler,
         random_state=0,
@@ -593,7 +601,7 @@ def roughly_balanced_bagging(X, y, replace=False):
 
     # Roughly Balanced Bagging
     rbb = BalancedBaggingClassifier(
-        base_estimator=CountDecisionTreeClassifier(),
+        estimator=CountDecisionTreeClassifier(),
         n_estimators=2,
         sampler=FunctionSampler(
             func=roughly_balanced_bagging, kw_args={"replace": replace}
@@ -604,3 +612,33 @@ def roughly_balanced_bagging(X, y, replace=False):
     for estimator in rbb.estimators_:
         class_counts = estimator[-1].class_counts_
         assert (class_counts[0] / class_counts[1]) > 0.8
+
+
+def test_balanced_bagging_classifier_n_features():
+    """Check that we raise a FutureWarning when accessing `n_features_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = BalancedBaggingClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`n_features_` was deprecated"):
+        estimator.n_features_
+
+
+@pytest.mark.skipif(
+    sklearn_version < parse_version("1.2"), reason="requires scikit-learn>=1.2"
+)
+def test_balanced_bagging_classifier_base_estimator():
+    """Check that we raise a FutureWarning when accessing `base_estimator_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = BalancedBaggingClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`base_estimator_` was deprecated"):
+        estimator.base_estimator_
+
+
+def test_balanced_bagging_classifier_set_both_estimator_and_base_estimator():
+    """Check that we raise a ValueError when setting both `estimator` and
+    `base_estimator`."""
+    X, y = load_iris(return_X_y=True)
+    err_msg = "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+    with pytest.raises(ValueError, match=err_msg):
+        BalancedBaggingClassifier(
+            estimator=KNeighborsClassifier(), base_estimator=KNeighborsClassifier()
+        ).fit(X, y)
diff --git a/imblearn/ensemble/tests/test_easy_ensemble.py b/imblearn/ensemble/tests/test_easy_ensemble.py
index fb118a92f..e5d8f6d93 100644
--- a/imblearn/ensemble/tests/test_easy_ensemble.py
+++ b/imblearn/ensemble/tests/test_easy_ensemble.py
@@ -6,11 +6,13 @@
 import pytest
 import numpy as np
 
+import sklearn
 from sklearn.datasets import load_iris, make_hastie_10_2
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.model_selection import GridSearchCV
 from sklearn.feature_selection import SelectKBest
+from sklearn.utils.fixes import parse_version
 from sklearn.utils._testing import assert_allclose
 from sklearn.utils._testing import assert_array_equal
 
@@ -19,6 +21,7 @@
 from imblearn.under_sampling import RandomUnderSampler
 from imblearn.pipeline import make_pipeline
 
+sklearn_version = parse_version(sklearn.__version__)
 iris = load_iris()
 
 # Generate a global dataset to use
@@ -42,10 +45,10 @@
 
 @pytest.mark.parametrize("n_estimators", [10, 20])
 @pytest.mark.parametrize(
-    "base_estimator",
+    "estimator",
     [AdaBoostClassifier(n_estimators=5), AdaBoostClassifier(n_estimators=10)],
 )
-def test_easy_ensemble_classifier(n_estimators, base_estimator):
+def test_easy_ensemble_classifier(n_estimators, estimator):
     # Check classification for various parameter settings.
     X, y = make_imbalance(
         iris.data,
@@ -57,14 +60,14 @@ def test_easy_ensemble_classifier(n_estimators, base_estimator):
 
     eec = EasyEnsembleClassifier(
         n_estimators=n_estimators,
-        base_estimator=base_estimator,
+        estimator=estimator,
         n_jobs=-1,
         random_state=RND_SEED,
     )
     eec.fit(X_train, y_train).score(X_test, y_test)
     assert len(eec.estimators_) == n_estimators
     for est in eec.estimators_:
-        assert len(est.named_steps["classifier"]) == base_estimator.n_estimators
+        assert len(est.named_steps["classifier"]) == estimator.n_estimators
     # test the different prediction function
     eec.predict(X_test)
     eec.predict_proba(X_test)
@@ -72,8 +75,8 @@ def test_easy_ensemble_classifier(n_estimators, base_estimator):
     eec.decision_function(X_test)
 
 
-def test_base_estimator():
-    # Check base_estimator and its default values.
+def test_estimator():
+    # Check estimator and its default values.
     X, y = make_imbalance(
         iris.data,
         iris.target,
@@ -86,13 +89,13 @@ def test_base_estimator():
         X_train, y_train
     )
 
-    assert isinstance(ensemble.base_estimator_.steps[-1][1], AdaBoostClassifier)
+    assert isinstance(ensemble.estimator_.steps[-1][1], AdaBoostClassifier)
 
     ensemble = EasyEnsembleClassifier(
         2, AdaBoostClassifier(), n_jobs=-1, random_state=0
     ).fit(X_train, y_train)
 
-    assert isinstance(ensemble.base_estimator_.steps[-1][1], AdaBoostClassifier)
+    assert isinstance(ensemble.estimator_.steps[-1][1], AdaBoostClassifier)
 
 
 def test_bagging_with_pipeline():
@@ -104,7 +107,7 @@ def test_bagging_with_pipeline():
     )
     estimator = EasyEnsembleClassifier(
         n_estimators=2,
-        base_estimator=make_pipeline(SelectKBest(k=1), AdaBoostClassifier()),
+        estimator=make_pipeline(SelectKBest(k=1), AdaBoostClassifier()),
     )
     estimator.fit(X, y).predict(X)
 
@@ -184,21 +187,15 @@ def test_warm_start_equivalence():
     assert_allclose(y1, y2)
 
 
-@pytest.mark.parametrize(
-    "n_estimators, msg_error",
-    [
-        (1.0, "n_estimators must be an integer"),
-        (-10, "n_estimators must be greater than zero"),
-    ],
-)
-def test_easy_ensemble_classifier_error(n_estimators, msg_error):
+@pytest.mark.parametrize("n_estimators", [1.0, -10])
+def test_easy_ensemble_classifier_error(n_estimators):
     X, y = make_imbalance(
         iris.data,
         iris.target,
         sampling_strategy={0: 20, 1: 25, 2: 50},
         random_state=0,
     )
-    with pytest.raises(ValueError, match=msg_error):
+    with pytest.raises(ValueError):
         eec = EasyEnsembleClassifier(n_estimators=n_estimators)
         eec.fit(X, y)
 
@@ -230,11 +227,41 @@ def test_easy_ensemble_classifier_grid_search():
 
     parameters = {
         "n_estimators": [1, 2],
-        "base_estimator__n_estimators": [3, 4],
+        "estimator__n_estimators": [3, 4],
     }
     grid_search = GridSearchCV(
-        EasyEnsembleClassifier(base_estimator=AdaBoostClassifier()),
+        EasyEnsembleClassifier(estimator=AdaBoostClassifier()),
         parameters,
         cv=5,
     )
     grid_search.fit(X, y)
+
+
+def test_easy_ensemble_classifier_n_features():
+    """Check that we raise a FutureWarning when accessing `n_features_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = EasyEnsembleClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`n_features_` was deprecated"):
+        estimator.n_features_
+
+
+@pytest.mark.skipif(
+    sklearn_version < parse_version("1.2"), reason="warns for scikit-learn>=1.2"
+)
+def test_easy_ensemble_classifier_base_estimator():
+    """Check that we raise a FutureWarning when accessing `base_estimator_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = EasyEnsembleClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`base_estimator_` was deprecated"):
+        estimator.base_estimator_
+
+
+def test_easy_ensemble_classifier_set_both_estimator_and_base_estimator():
+    """Check that we raise a ValueError when setting both `estimator` and
+    `base_estimator`."""
+    X, y = load_iris(return_X_y=True)
+    err_msg = "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+    with pytest.raises(ValueError, match=err_msg):
+        EasyEnsembleClassifier(
+            estimator=AdaBoostClassifier(), base_estimator=AdaBoostClassifier()
+        ).fit(X, y)
diff --git a/imblearn/ensemble/tests/test_forest.py b/imblearn/ensemble/tests/test_forest.py
index ad1420631..5e35eb43f 100644
--- a/imblearn/ensemble/tests/test_forest.py
+++ b/imblearn/ensemble/tests/test_forest.py
@@ -2,14 +2,18 @@
 
 import numpy as np
 
-from sklearn.datasets import make_classification
+import sklearn
+from sklearn.datasets import make_classification, load_iris
 from sklearn.model_selection import GridSearchCV
 from sklearn.model_selection import train_test_split
+from sklearn.utils.fixes import parse_version
 from sklearn.utils._testing import assert_allclose
 from sklearn.utils._testing import assert_array_equal
 
 from imblearn.ensemble import BalancedRandomForestClassifier
 
+sklearn_version = parse_version(sklearn.__version__)
+
 
 @pytest.fixture
 def imbalanced_dataset():
@@ -188,3 +192,22 @@ def test_balanced_random_forest_oob_binomial(ratio):
     erf = BalancedRandomForestClassifier(oob_score=True, random_state=42)
     erf.fit(X, y)
     assert np.abs(erf.oob_score_ - 0.5) < 0.1
+
+
+def test_balanced_bagging_classifier_n_features():
+    """Check that we raise a FutureWarning when accessing `n_features_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = BalancedRandomForestClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`n_features_` was deprecated"):
+        estimator.n_features_
+
+
+@pytest.mark.skipif(
+    sklearn_version < parse_version("1.2"), reason="requires scikit-learn>=1.2"
+)
+def test_balanced_bagging_classifier_base_estimator():
+    """Check that we raise a FutureWarning when accessing `base_estimator_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = BalancedRandomForestClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`base_estimator_` was deprecated"):
+        estimator.base_estimator_
diff --git a/imblearn/ensemble/tests/test_weight_boosting.py b/imblearn/ensemble/tests/test_weight_boosting.py
index e1394a2b5..c69e39500 100644
--- a/imblearn/ensemble/tests/test_weight_boosting.py
+++ b/imblearn/ensemble/tests/test_weight_boosting.py
@@ -2,12 +2,17 @@
 
 import numpy as np
 
-from sklearn.datasets import make_classification
+import sklearn
+from sklearn.datasets import make_classification, load_iris
 from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.utils.fixes import parse_version
 from sklearn.utils._testing import assert_array_equal
 
 from imblearn.ensemble import RUSBoostClassifier
 
+sklearn_version = parse_version(sklearn.__version__)
+
 
 @pytest.fixture
 def imbalanced_dataset():
@@ -26,19 +31,11 @@ def imbalanced_dataset():
 
 
 @pytest.mark.parametrize(
-    "boosting_params, err_type, err_msg",
-    [
-        (
-            {"n_estimators": "whatever"},
-            TypeError,
-            "n_estimators must be an instance of int, not str.",
-        ),
-        ({"n_estimators": -100}, ValueError, "n_estimators == -100, must be >= 1."),
-    ],
+    "boosting_params", [{"n_estimators": "whatever"}, {"n_estimators": -100}]
 )
-def test_rusboost_error(imbalanced_dataset, boosting_params, err_type, err_msg):
+def test_rusboost_error(imbalanced_dataset, boosting_params):
     rusboost = RUSBoostClassifier(**boosting_params)
-    with pytest.raises(err_type, match=err_msg):
+    with pytest.raises((ValueError, TypeError)):
         rusboost.fit(*imbalanced_dataset)
 
 
@@ -105,3 +102,25 @@ def test_rusboost_sample_weight(imbalanced_dataset, algorithm):
 
     with pytest.raises(AssertionError):
         assert_array_equal(y_pred_no_sample_weight, y_pred_sample_weight)
+
+
+@pytest.mark.skipif(
+    sklearn_version < parse_version("1.2"), reason="requires scikit-learn>=1.2"
+)
+def test_rus_boost_classifier_base_estimator():
+    """Check that we raise a FutureWarning when accessing `base_estimator_`."""
+    X, y = load_iris(return_X_y=True)
+    estimator = RUSBoostClassifier().fit(X, y)
+    with pytest.warns(FutureWarning, match="`base_estimator_` was deprecated"):
+        estimator.base_estimator_
+
+
+def test_rus_boost_classifier_set_both_estimator_and_base_estimator():
+    """Check that we raise a ValueError when setting both `estimator` and
+    `base_estimator`."""
+    X, y = load_iris(return_X_y=True)
+    err_msg = "Both `estimator` and `base_estimator` were set. Only set `estimator`."
+    with pytest.raises(ValueError, match=err_msg):
+        RUSBoostClassifier(
+            estimator=DecisionTreeClassifier(), base_estimator=DecisionTreeClassifier()
+        ).fit(X, y)
diff --git a/imblearn/metrics/_classification.py b/imblearn/metrics/_classification.py
index 0f6141f8f..49a59fadc 100644
--- a/imblearn/metrics/_classification.py
+++ b/imblearn/metrics/_classification.py
@@ -856,9 +856,8 @@ def classification_report_imbalanced(
     >>> import numpy as np
     >>> from imblearn.metrics import classification_report_imbalanced
     >>> y_true = [0, 1, 2, 2, 2]
-    >>> y_pred = [0, 0, 2, 2, 1] # doctest : +NORMALIZE_WHITESPACE
-    >>> target_names = ['class 0', 'class 1', \
-    'class 2'] # doctest : +NORMALIZE_WHITESPACE
+    >>> y_pred = [0, 0, 2, 2, 1]
+    >>> target_names = ['class 0', 'class 1', 'class 2']
     >>> print(classification_report_imbalanced(y_true, y_pred, \
     target_names=target_names))
                        pre       rec       spe        f1       geo       iba\
diff --git a/imblearn/over_sampling/_adasyn.py b/imblearn/over_sampling/_adasyn.py
index 23939ef25..a0f4383ed 100644
--- a/imblearn/over_sampling/_adasyn.py
+++ b/imblearn/over_sampling/_adasyn.py
@@ -107,7 +107,7 @@ class ADASYN(BaseOverSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.over_sampling import \
-ADASYN # doctest: +NORMALIZE_WHITESPACE
+ADASYN # doctest:
     >>> 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,
diff --git a/imblearn/over_sampling/_random_over_sampler.py b/imblearn/over_sampling/_random_over_sampler.py
index 8df574c20..6323e04da 100644
--- a/imblearn/over_sampling/_random_over_sampler.py
+++ b/imblearn/over_sampling/_random_over_sampler.py
@@ -121,7 +121,7 @@ class RandomOverSampler(BaseOverSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.over_sampling import \
-RandomOverSampler # doctest: +NORMALIZE_WHITESPACE
+RandomOverSampler # doctest:
     >>> 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)
diff --git a/imblearn/over_sampling/_smote/base.py b/imblearn/over_sampling/_smote/base.py
index 6249dc876..29dcabf6e 100644
--- a/imblearn/over_sampling/_smote/base.py
+++ b/imblearn/over_sampling/_smote/base.py
@@ -294,7 +294,7 @@ class SMOTE(BaseSMOTE):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.over_sampling import \
-SMOTE # doctest: +NORMALIZE_WHITESPACE
+SMOTE # doctest:
     >>> 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)
diff --git a/imblearn/over_sampling/_smote/filter.py b/imblearn/over_sampling/_smote/filter.py
index df01e9b2b..b3ec3d46c 100644
--- a/imblearn/over_sampling/_smote/filter.py
+++ b/imblearn/over_sampling/_smote/filter.py
@@ -139,7 +139,7 @@ class BorderlineSMOTE(BaseSMOTE):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.over_sampling import \
-BorderlineSMOTE # doctest: +NORMALIZE_WHITESPACE
+BorderlineSMOTE # doctest:
     >>> 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)
@@ -393,7 +393,7 @@ class SVMSMOTE(BaseSMOTE):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.over_sampling import \
-SVMSMOTE # doctest: +NORMALIZE_WHITESPACE
+SVMSMOTE # doctest:
     >>> 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)
diff --git a/imblearn/over_sampling/base.py b/imblearn/over_sampling/base.py
index abeecc729..7165ab9c9 100644
--- a/imblearn/over_sampling/base.py
+++ b/imblearn/over_sampling/base.py
@@ -52,4 +52,4 @@ class BaseOverSampler(BaseSampler):
         - When callable, function taking ``y`` and returns a ``dict``. The keys
           correspond to the targeted classes. The values correspond to the
           desired number of samples for each class.
-        """.strip()
+        """.strip()  # noqa: E501
diff --git a/imblearn/pipeline.py b/imblearn/pipeline.py
index b112a0a20..320f086d1 100644
--- a/imblearn/pipeline.py
+++ b/imblearn/pipeline.py
@@ -90,7 +90,7 @@ class Pipeline(pipeline.Pipeline):
     >>> from sklearn.neighbors import KNeighborsClassifier as KNN
     >>> from sklearn.metrics import classification_report
     >>> from imblearn.over_sampling import SMOTE
-    >>> from imblearn.pipeline import Pipeline # doctest: +NORMALIZE_WHITESPACE
+    >>> from imblearn.pipeline import Pipeline # doctest:
     >>> 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)
@@ -101,7 +101,7 @@ class Pipeline(pipeline.Pipeline):
     >>> knn = KNN()
     >>> pipeline = Pipeline([('smt', smt), ('pca', pca), ('knn', knn)])
     >>> X_train, X_test, y_train, y_test = tts(X, y, random_state=42)
-    >>> pipeline.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> pipeline.fit(X_train, y_train) # doctest:
     Pipeline(...)
     >>> y_hat = pipeline.predict(X_test)
     >>> print(classification_report(y_test, y_hat))
@@ -437,7 +437,7 @@ def make_pipeline(*steps, memory=None, verbose=False):
     >>> from sklearn.naive_bayes import GaussianNB
     >>> from sklearn.preprocessing import StandardScaler
     >>> make_pipeline(StandardScaler(), GaussianNB(priors=None))
-    ... # doctest: +NORMALIZE_WHITESPACE
+    ... # doctest:
     Pipeline(steps=[('standardscaler', StandardScaler()),
                     ('gaussiannb', GaussianNB())])
     """
diff --git a/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py b/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
index 556f0c980..8295adf84 100644
--- a/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
+++ b/imblearn/under_sampling/_prototype_generation/_cluster_centroids.py
@@ -95,7 +95,7 @@ class ClusterCentroids(BaseUnderSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-ClusterCentroids # doctest: +NORMALIZE_WHITESPACE
+ClusterCentroids # doctest:
     >>> 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)
@@ -104,7 +104,7 @@ class ClusterCentroids(BaseUnderSampler):
     >>> cc = ClusterCentroids(random_state=42)
     >>> X_res, y_res = cc.fit_resample(X, y)
     >>> print('Resampled dataset shape %s' % Counter(y_res))
-    ... # doctest: +ELLIPSIS
+    ... # doctest:
     Resampled dataset shape Counter({{...}})
     """
 
diff --git a/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py b/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
index d06a867be..be12d0bf0 100644
--- a/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
+++ b/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
@@ -104,7 +104,7 @@ class EditedNearestNeighbours(BaseCleaningSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-EditedNearestNeighbours # doctest: +NORMALIZE_WHITESPACE
+EditedNearestNeighbours # doctest:
     >>> 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)
@@ -272,8 +272,7 @@ class RepeatedEditedNearestNeighbours(BaseCleaningSampler):
     --------
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
-    >>> from imblearn.under_sampling import \
-RepeatedEditedNearestNeighbours # doctest : +NORMALIZE_WHITESPACE
+    >>> from imblearn.under_sampling import RepeatedEditedNearestNeighbours
     >>> 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)
@@ -473,7 +472,7 @@ class without early stopping.
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-AllKNN # doctest: +NORMALIZE_WHITESPACE
+AllKNN # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py b/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
index 65aceadb1..32e2d754c 100644
--- a/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
+++ b/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
@@ -101,7 +101,7 @@ class InstanceHardnessThreshold(BaseUnderSampler):
     Original dataset shape Counter({{1: 900, 0: 100}})
     >>> iht = InstanceHardnessThreshold(random_state=42)
     >>> X_res, y_res = iht.fit_resample(X, y)
-    >>> print('Resampled dataset shape %s' % Counter(y_res))  # doctest: +ELLIPSIS
+    >>> print('Resampled dataset shape %s' % Counter(y_res))  # doctest:
     Resampled dataset shape Counter({{1: 5..., 0: 100}})
     """
 
diff --git a/imblearn/under_sampling/_prototype_selection/_nearmiss.py b/imblearn/under_sampling/_prototype_selection/_nearmiss.py
index 5246e54f0..8913b4c4f 100644
--- a/imblearn/under_sampling/_prototype_selection/_nearmiss.py
+++ b/imblearn/under_sampling/_prototype_selection/_nearmiss.py
@@ -96,7 +96,7 @@ class NearMiss(BaseUnderSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-NearMiss # doctest: +NORMALIZE_WHITESPACE
+NearMiss # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py b/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
index 3cb3d5320..f73e1397e 100644
--- a/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
+++ b/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
@@ -105,7 +105,7 @@ class NeighbourhoodCleaningRule(BaseCleaningSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-NeighbourhoodCleaningRule # doctest: +NORMALIZE_WHITESPACE
+NeighbourhoodCleaningRule # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py b/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
index abe9484d9..bd7863791 100644
--- a/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
+++ b/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
@@ -92,7 +92,7 @@ class OneSidedSelection(BaseCleaningSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-    OneSidedSelection # doctest: +NORMALIZE_WHITESPACE
+    OneSidedSelection # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py b/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py
index fe2b9b7a2..4447efbfb 100644
--- a/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py
+++ b/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py
@@ -69,7 +69,7 @@ class RandomUnderSampler(BaseUnderSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-RandomUnderSampler # doctest: +NORMALIZE_WHITESPACE
+RandomUnderSampler # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/_prototype_selection/_tomek_links.py b/imblearn/under_sampling/_prototype_selection/_tomek_links.py
index 7ee8d31d9..3e7907939 100644
--- a/imblearn/under_sampling/_prototype_selection/_tomek_links.py
+++ b/imblearn/under_sampling/_prototype_selection/_tomek_links.py
@@ -72,7 +72,7 @@ class TomekLinks(BaseCleaningSampler):
     >>> from collections import Counter
     >>> from sklearn.datasets import make_classification
     >>> from imblearn.under_sampling import \
-TomekLinks # doctest: +NORMALIZE_WHITESPACE
+TomekLinks # doctest:
     >>> 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)
diff --git a/imblearn/under_sampling/base.py b/imblearn/under_sampling/base.py
index fc1e09314..82db6bdd0 100644
--- a/imblearn/under_sampling/base.py
+++ b/imblearn/under_sampling/base.py
@@ -52,7 +52,7 @@ class BaseUnderSampler(BaseSampler):
         - When callable, function taking ``y`` and returns a ``dict``. The keys
           correspond to the targeted classes. The values correspond to the
           desired number of samples for each class.
-        """.rstrip()
+        """.rstrip()  # noqa: E501
 
 
 class BaseCleaningSampler(BaseSampler):
diff --git a/setup.cfg b/setup.cfg
index 8b15065af..05df1039a 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -2,13 +2,13 @@
 current_version = 0.10.0.dev0
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<dev>\d+))?
-serialize = 
+serialize =
 	{major}.{minor}.{patch}.{release}{dev}
 	{major}.{minor}.{patch}
 
 [bumpversion:part:release]
 optional_value = gamma
-values = 
+values =
 	dev
 	gamma
 
@@ -22,20 +22,55 @@ test = pytest
 [tool:pytest]
 doctest_optionflags = NORMALIZE_WHITESPACE ELLIPSIS
 testpaths = imblearn
-addopts = 
+addopts =
 	--doctest-modules
 	--color=yes
 	-rs
-filterwarnings = 
+filterwarnings =
 	ignore:the matrix subclass:PendingDeprecationWarning
 
 [flake8]
+# max line length for black
 max-line-length = 88
-ignore = E121,E123,E126,E226,E24,E704,W503,W504,E203
-per-file-ignores = 
-	examples/*: E402
+target-version = ['py37']
+# Default flake8 3.5 ignored flags
+ignore=
+    # check ignored by default in flake8. Meaning unclear.
+    E24,
+    # continuation line under-indented
+    E121,
+    # closing bracket does not match indentation
+    E123,
+    # continuation line over-indented for hanging indent
+    E126,
+    # space before : (needed for how black formats slicing)
+    E203,
+    # missing whitespace around arithmetic operator
+    E226,
+    # multiple statements on one line (def)
+    E704,
+    # do not assign a lambda expression, use a def
+    E731,
+    # do not use variables named 'l', 'O', or 'I'
+    E741,
+    # line break before binary operator
+    W503,
+    # line break after binary operator
+    W504
+exclude=
+    .git,
+    __pycache__,
+    dist,
+    doc/_build,
+    doc/auto_examples,
+    build,
+
+# It's fine not to put the import at the top of the file in the examples
+# folder.
+per-file-ignores =
+    examples/*: E402
+    doc/conf.py: E402
 
 [mypy]
 ignore_missing_imports = True
 allow_redefinition = True
-