remove dead code

Author: glemaitre

imblearn/base.py

@@ -8,14 +8,7 @@
 
 import numpy as np
 import sklearn
-from sklearn.base import BaseEstimator
-
-try:
-    # scikit-learn >= 1.2
-    from sklearn.base import OneToOneFeatureMixin
-except ImportError:
-    from sklearn.base import _OneToOneFeatureMixin as OneToOneFeatureMixin
-
+from sklearn.base import BaseEstimator, OneToOneFeatureMixin
 from sklearn.preprocessing import label_binarize
 from sklearn.utils.fixes import parse_version
 from sklearn.utils.multiclass import check_classification_targets

imblearn/ensemble/_bagging.py

@@ -14,24 +14,17 @@
 from sklearn.ensemble import BaggingClassifier
 from sklearn.ensemble._bagging import _parallel_decision_function
 from sklearn.ensemble._base import _partition_estimators
-from sklearn.exceptions import NotFittedError
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.utils.fixes import parse_version
+from sklearn.utils.metaestimators import available_if
+from sklearn.utils.parallel import Parallel, delayed
 from sklearn.utils.validation import check_is_fitted
 
-try:
-    # scikit-learn >= 1.2
-    from sklearn.utils.parallel import Parallel, delayed
-except (ImportError, ModuleNotFoundError):
-    from joblib import Parallel
-    from sklearn.utils.fixes import delayed
-
 from ..base import _ParamsValidationMixin
 from ..pipeline import Pipeline
 from ..under_sampling import RandomUnderSampler
 from ..under_sampling.base import BaseUnderSampler
 from ..utils import Substitution, check_sampling_strategy, check_target_type
-from ..utils._available_if import available_if
 from ..utils._docstring import _n_jobs_docstring, _random_state_docstring
 from ..utils._param_validation import HasMethods, Interval, StrOptions
 from ..utils.fixes import _fit_context
@@ -443,14 +436,6 @@ def base_estimator_(self):
         error = AttributeError(
             f"{self.__class__.__name__} object has no attribute 'base_estimator_'."
         )
-        if sklearn_version < parse_version("1.2"):
-            # The base class require to have the attribute defined. For scikit-learn
-            # > 1.2, we are going to raise an error.
-            try:
-                check_is_fitted(self)
-                return self.estimator_
-            except NotFittedError:
-                raise error
         raise error
 
     def _more_tags(self):

imblearn/ensemble/_easy_ensemble.py

@@ -14,24 +14,17 @@
 from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier
 from sklearn.ensemble._bagging import _parallel_decision_function
 from sklearn.ensemble._base import _partition_estimators
-from sklearn.exceptions import NotFittedError
 from sklearn.utils._tags import _safe_tags
 from sklearn.utils.fixes import parse_version
+from sklearn.utils.metaestimators import available_if
+from sklearn.utils.parallel import Parallel, delayed
 from sklearn.utils.validation import check_is_fitted
 
-try:
-    # scikit-learn >= 1.2
-    from sklearn.utils.parallel import Parallel, delayed
-except (ImportError, ModuleNotFoundError):
-    from joblib import Parallel
-    from sklearn.utils.fixes import delayed
-
 from ..base import _ParamsValidationMixin
 from ..pipeline import Pipeline
 from ..under_sampling import RandomUnderSampler
 from ..under_sampling.base import BaseUnderSampler
 from ..utils import Substitution, check_sampling_strategy, check_target_type
-from ..utils._available_if import available_if
 from ..utils._docstring import _n_jobs_docstring, _random_state_docstring
 from ..utils._param_validation import Interval, StrOptions
 from ..utils.fixes import _fit_context
@@ -357,14 +350,6 @@ def base_estimator_(self):
         error = AttributeError(
             f"{self.__class__.__name__} object has no attribute 'base_estimator_'."
         )
-        if sklearn_version < parse_version("1.2"):
-            # The base class require to have the attribute defined. For scikit-learn
-            # > 1.2, we are going to raise an error.
-            try:
-                check_is_fitted(self)
-                return self.estimator_
-            except NotFittedError:
-                raise error
         raise error
 
     def _get_estimator(self):

imblearn/ensemble/_forest.py

@@ -25,15 +25,9 @@
 from sklearn.utils import _safe_indexing, check_random_state
 from sklearn.utils.fixes import parse_version
 from sklearn.utils.multiclass import type_of_target
+from sklearn.utils.parallel import Parallel, delayed
 from sklearn.utils.validation import _check_sample_weight
 
-try:
-    # scikit-learn >= 1.2
-    from sklearn.utils.parallel import Parallel, delayed
-except (ImportError, ModuleNotFoundError):
-    from joblib import Parallel
-    from sklearn.utils.fixes import delayed
-
 from ..base import _ParamsValidationMixin
 from ..pipeline import make_pipeline
 from ..under_sampling import RandomUnderSampler
@@ -80,6 +74,7 @@ def _local_parallel_build_trees(
         "verbose": verbose,
         "class_weight": class_weight,
         "n_samples_bootstrap": n_samples_bootstrap,
+        "bootstrap": bootstrap,
     }
 
     if parse_version(sklearn_version.base_version) >= parse_version("1.4"):
@@ -89,13 +84,6 @@ def _local_parallel_build_trees(
             missing_values_in_feature_mask
         )
 
-    # TODO: remove when the minimum supported version of scikit-learn will be 1.1
-    # change of signature in scikit-learn 1.1
-    if parse_version(sklearn_version.base_version) >= parse_version("1.1"):
-        params_parallel_build_trees["bootstrap"] = bootstrap
-    else:
-        params_parallel_build_trees["forest"] = forest
-
     tree = _parallel_build_trees(**params_parallel_build_trees)
 
     return sampler, tree

imblearn/over_sampling/_smote/tests/test_smote_nc.py

@@ -272,21 +272,17 @@ def test_smote_nc_with_null_median_std():
 def test_smotenc_categorical_encoder():
     """Check that we can pass our own categorical encoder."""
 
-    # TODO: only use `sparse_output` when sklearn >= 1.2
-    param = "sparse" if sklearn_version < parse_version("1.2") else "sparse_output"
-
     X, y, categorical_features = data_heterogneous_unordered()
     smote = SMOTENC(categorical_features=categorical_features, random_state=0)
     smote.fit_resample(X, y)
 
-    assert getattr(smote.categorical_encoder_, param) is True
+    assert getattr(smote.categorical_encoder_, "sparse_output") is True
 
-    encoder = OneHotEncoder()
-    encoder.set_params(**{param: False})
+    encoder = OneHotEncoder(sparse_output=False)
     smote.set_params(categorical_encoder=encoder).fit_resample(X, y)
     assert smote.categorical_encoder is encoder
     assert smote.categorical_encoder_ is not encoder
-    assert getattr(smote.categorical_encoder_, param) is False
+    assert getattr(smote.categorical_encoder_, "sparse_output") is False
 
 
 # TODO(0.13): remove this test

imblearn/tests/test_docstring_parameters.py

@@ -16,18 +16,12 @@
     check_docstring_parameters,
     ignore_warnings,
 )
-from sklearn.utils.estimator_checks import _enforce_estimator_tags_y
-
-try:
-    from sklearn.utils.estimator_checks import _enforce_estimator_tags_x
-except ImportError:
-    # scikit-learn >= 1.2
-    from sklearn.utils.estimator_checks import (
-        _enforce_estimator_tags_X as _enforce_estimator_tags_x,
-    )
-
 from sklearn.utils.deprecation import _is_deprecated
-from sklearn.utils.estimator_checks import _construct_instance
+from sklearn.utils.estimator_checks import (
+    _construct_instance,
+    _enforce_estimator_tags_X,
+    _enforce_estimator_tags_y,
+)
 
 import imblearn
 from imblearn.base import is_sampler
@@ -197,7 +191,7 @@ def test_fit_docstring_attributes(name, Estimator):
     )
 
     y = _enforce_estimator_tags_y(est, y)
-    X = _enforce_estimator_tags_x(est, X)
+    X = _enforce_estimator_tags_X(est, X)
 
     if "oob_score" in est.get_params():
         est.set_params(bootstrap=True, oob_score=True)

imblearn/tests/test_pipeline.py

@@ -1338,9 +1338,6 @@ def test_pipeline_param_validation():
     check_param_validation("Pipeline", model)
 
 
-@pytest.mark.skipif(
-    sklearn_version < parse_version("1.2"), reason="requires scikit-learn >= 1.2"
-)
 def test_pipeline_with_set_output():
     pd = pytest.importorskip("pandas")
     X, y = load_iris(return_X_y=True, as_frame=True)

imblearn/utils/_available_if.py

@@ -1,6 +1,4 @@
-"""This is a copy of sklearn/utils/_param_validation.py. It can be removed when
-we support scikit-learn >= 1.2.
-"""
+"""This is a copy of sklearn/utils/_param_validation.py."""
 # mypy: ignore-errors
 import functools
 import math

imblearn/utils/_param_validation.py

@@ -35,19 +35,11 @@
     set_random_state,
 )
 from sklearn.utils.estimator_checks import (
+    _enforce_estimator_tags_X,
     _enforce_estimator_tags_y,
     _get_check_estimator_ids,
     _maybe_mark_xfail,
 )
-
-try:
-    from sklearn.utils.estimator_checks import _enforce_estimator_tags_x
-except ImportError:
-    # scikit-learn >= 1.2
-    from sklearn.utils.estimator_checks import (
-        _enforce_estimator_tags_X as _enforce_estimator_tags_x,
-    )
-
 from sklearn.utils.fixes import parse_version
 from sklearn.utils.multiclass import type_of_target
 
@@ -602,7 +594,7 @@ def check_dataframe_column_names_consistency(name, estimator_orig):
 
     X_orig = rng.normal(size=(150, 8))
 
-    X_orig = _enforce_estimator_tags_x(estimator, X_orig)
+    X_orig = _enforce_estimator_tags_X(estimator, X_orig)
     n_samples, n_features = X_orig.shape
 
     names = np.array([f"col_{i}" for i in range(n_features)])
@@ -756,7 +748,7 @@ def check_sampler_get_feature_names_out(name, sampler_orig):
     X = StandardScaler().fit_transform(X)
 
     sampler = clone(sampler_orig)
-    X = _enforce_estimator_tags_x(sampler, X)
+    X = _enforce_estimator_tags_X(sampler, X)
 
     n_features = X.shape[1]
     set_random_state(sampler)
@@ -804,7 +796,7 @@ def check_sampler_get_feature_names_out_pandas(name, sampler_orig):
     X = StandardScaler().fit_transform(X)
 
     sampler = clone(sampler_orig)
-    X = _enforce_estimator_tags_x(sampler, X)
+    X = _enforce_estimator_tags_X(sampler, X)
 
     n_features = X.shape[1]
     set_random_state(sampler)