iter

Author: glemaitre

imblearn/ensemble/_weight_boosting.py

@@ -1,5 +1,6 @@
 import copy
 import numbers
+import warnings
 from copy import deepcopy
 
 import numpy as np
@@ -68,9 +69,6 @@ class RUSBoostClassifier(_ParamsValidationMixin, AdaBoostClassifier):
 
         .. deprecated:: 0.12
             `algorithm` is deprecated in 0.12 and will be removed 0.14.
-            Depending on the `scikit-learn` version, the "SAMME.R" algorithm might not
-            be available. Refer to the documentation of
-            :class:`~sklearn.ensemble.AdaBoostClassifier` for more information.
 
     {sampling_strategy}
 
@@ -403,6 +401,12 @@ def _boost_discrete(self, iboost, X, y, sample_weight, random_state):
         return sample_weight, estimator_weight, estimator_error
 
     def _boost(self, iboost, X, y, sample_weight, random_state):
+        if self.algorithm != "deprecated":
+            warnings.warn(
+                "`algorithm` parameter is deprecated in 0.12 and will be removed in "
+                "0.14. In the future, the SAMME algorithm will always be used.",
+                FutureWarning,
+            )
         if self.algorithm == "SAMME.R":
             return self._boost_real(iboost, X, y, sample_weight, random_state)
 

imblearn/ensemble/tests/test_weight_boosting.py

@@ -24,7 +24,7 @@ def imbalanced_dataset():
 
 
 @pytest.mark.parametrize("algorithm", ["SAMME", "SAMME.R"])
-@pytest.mark.filterwarnings("ignore:The SAMME.R algorithm (the default) is")
+@pytest.mark.filterwarnings("ignore:`algorithm` parameter is deprecated in 0.12")
 def test_rusboost(imbalanced_dataset, algorithm):
     X, y = imbalanced_dataset
     X_train, X_test, y_train, y_test = train_test_split(
@@ -70,7 +70,7 @@ def test_rusboost(imbalanced_dataset, algorithm):
 
 
 @pytest.mark.parametrize("algorithm", ["SAMME", "SAMME.R"])
-@pytest.mark.filterwarnings("ignore:The SAMME.R algorithm (the default) is")
+@pytest.mark.filterwarnings("ignore:`algorithm` parameter is deprecated in 0.12")
 def test_rusboost_sample_weight(imbalanced_dataset, algorithm):
     X, y = imbalanced_dataset
     sample_weight = np.ones_like(y)
@@ -88,3 +88,13 @@ 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.parametrize("algorithm", ["SAMME", "SAMME.R"])
+def test_rusboost_algorithm_future_warning(imbalanced_dataset, algorithm):
+    X, y = imbalanced_dataset
+    rusboost = RUSBoostClassifier(algorithm=algorithm, random_state=0)
+
+    warning_msg = "`algorithm` parameter is deprecated in 0.12"
+    with pytest.warns(FutureWarning, match=warning_msg):
+        rusboost.fit(X, y)

imblearn/pipeline.py

@@ -95,6 +95,10 @@ class Pipeline(_ParamsValidationMixin, pipeline.Pipeline):
     n_features_in_ : int
         Number of features seen during first step `fit` method.
 
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Only defined if the
+        underlying estimator exposes such an attribute when fit.
+
     See Also
     --------
     make_pipeline : Helper function to make pipeline.

imblearn/utils/_tags.py

@@ -8,6 +8,7 @@
 
 if sklearn_version >= parse_version("1.6"):
     from sklearn.utils._tags import (
+        Tags,
         TargetTags,
         TransformerTags,
         ClassifierTags,
@@ -33,7 +34,7 @@ class SamplerTags:
         sample_indices: bool = False
 
     @dataclass(**_dataclass_args())
-    class Tags:
+    class Tags(Tags):
         """Tags for the estimator.
 
         See :ref:`estimator_tags` for more information.
@@ -86,15 +87,4 @@ class Tags:
             The input data(X) tags.
         """
 
-        estimator_type: str | None
-        target_tags: TargetTags
-        transformer_tags: TransformerTags | None
-        classifier_tags: ClassifierTags | None
-        regressor_tags: RegressorTags | None
-        sampler_tags: SamplerTags | None
-        array_api_support: bool = False
-        no_validation: bool = False
-        non_deterministic: bool = False
-        requires_fit: bool = True
-        _skip_test: bool = False
-        input_tags: InputTags = field(default_factory=InputTags)
+        sampler_tags: SamplerTags | None = None

imblearn/utils/_test_common/instance_generator.py

@@ -54,7 +54,10 @@
         dict(estimator=DecisionTreeClassifier(random_state=42), random_state=42),
     ],
     Pipeline: dict(
-        steps=[("sampler", RandomUnderSampler()), ("logistic", LogisticRegression())]
+        steps=[
+            ("sampler", RandomUnderSampler(random_state=0)),
+            ("logistic", LogisticRegression()),
+        ]
     ),
     # over-sampling
     ADASYN: dict(random_state=42),