iter

glemaitre · glemaitre · commit acb8234cd21c · 2024-11-12T11:44:27.000+01:00
diff --git a/imblearn/base.py b/imblearn/base.py
@@ -37,7 +37,7 @@ class attribute, which is a dictionary `param_name: list of constraints`. See
             )
 
 
-class SamplerMixin(_ParamsValidationMixin, BaseEstimator, metaclass=ABCMeta):
+class SamplerMixin(_ParamsValidationMixin, metaclass=ABCMeta):
     """Mixin class for samplers with abstract method.
 
     Warning: This class should not be used directly. Use the derive classes
@@ -135,7 +135,7 @@ def _fit_resample(self, X, y):
         pass
 
 
-class BaseSampler(SamplerMixin, OneToOneFeatureMixin):
+class BaseSampler(SamplerMixin, OneToOneFeatureMixin, BaseEstimator):
     """Base class for sampling algorithms.
 
     Warning: This class should not be used directly. Use the derive classes
@@ -204,9 +204,15 @@ def _more_tags(self):
 
     @available_if(check_version_package("sklearn", ">=", "1.6"))
     def __sklearn_tags__(self):
-        tags = super().__sklearn_tags__()
-
-        from .utils._tags import InputTags
+        from .utils._tags import Tags, SamplerTags, TargetTags, InputTags
+        tags = Tags(
+            estimator_type="sampler",
+            target_tags=TargetTags(required=True),
+            transformer_tags=None,
+            regressor_tags=None,
+            classifier_tags=None,
+            sampler_tags=SamplerTags(),
+        )
         tags.input_tags = InputTags()
         tags.input_tags.two_d_array = True
         tags.input_tags.sparse = True
diff --git a/imblearn/ensemble/_bagging.py b/imblearn/ensemble/_bagging.py
@@ -382,17 +382,13 @@ def decision_function(self, X):
         check_is_fitted(self)
 
         # Check data
-        if sklearn_version < parse_version("1.6"):
-            kwargs = {"force_all_finite": False}
-        else:
-            kwargs = {"ensure_all_finite": False}
         X = validate_data(
             self,
             X=X,
             accept_sparse=["csr", "csc"],
             dtype=None,
             reset=False,
-            **kwargs
+            ensure_all_finite=False,
         )
 
         # Parallel loop
diff --git a/imblearn/ensemble/_easy_ensemble.py b/imblearn/ensemble/_easy_ensemble.py
@@ -310,17 +310,13 @@ def decision_function(self, X):
         check_is_fitted(self)
 
         # Check data
-        if sklearn_version < parse_version("1.6"):
-            kwargs = {"force_all_finite": False}
-        else:
-            kwargs = {"ensure_all_finite": False}
         X = validate_data(
             self,
             X=X,
             accept_sparse=["csr", "csc"],
             dtype=None,
             reset=False,
-            **kwargs,
+            ensure_all_finite=False,
         )
 
         # Parallel loop
diff --git a/imblearn/ensemble/_forest.py b/imblearn/ensemble/_forest.py
@@ -598,12 +598,9 @@ def fit(self, X, y, sample_weight=None):
         # TODO: remove when the minimum supported version of scipy will be 1.4
         # Support for missing values
         if parse_version(sklearn_version.base_version) >= parse_version("1.4"):
-            if sklearn_version >= parse_version("1.6"):
-                kwargs = {"ensure_all_finite": False}
-            else:
-                kwargs = {"force_all_finite": False}
+            ensure_all_finite = False
         else:
-            kwargs = {"force_all_finite": False}
+            ensure_all_finite = False
 
         X, y = validate_data(
             self,
@@ -612,7 +609,7 @@ def fit(self, X, y, sample_weight=None):
             multi_output=True,
             accept_sparse="csc",
             dtype=DTYPE,
-            **kwargs,
+            ensure_all_finite=ensure_all_finite,
         )
 
         # TODO: remove when the minimum supported version of scikit-learn will be 1.4
diff --git a/imblearn/metrics/tests/test_classification.py b/imblearn/metrics/tests/test_classification.py
@@ -4,6 +4,7 @@
 #          Christos Aridas
 # License: MIT
 
+import warnings
 from functools import partial
 
 import numpy as np
@@ -23,7 +24,6 @@
 from sklearn.utils._testing import (
     assert_allclose,
     assert_array_equal,
-    assert_no_warnings,
 )
 from sklearn.utils.validation import check_random_state
 
@@ -105,11 +105,13 @@ def test_sensitivity_specificity_score_binary():
     # binary class case the score is the value of the measure for the positive
     # class (e.g. label == 1). This is deprecated for average != 'binary'.
     for kwargs in ({}, {"average": "binary"}):
-        sen = assert_no_warnings(sensitivity_score, y_true, y_pred, **kwargs)
-        assert sen == pytest.approx(0.68, rel=R_TOL)
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            sen = sensitivity_score(y_true, y_pred, **kwargs)
+            assert sen == pytest.approx(0.68, rel=R_TOL)
 
-        spe = assert_no_warnings(specificity_score, y_true, y_pred, **kwargs)
-        assert spe == pytest.approx(0.88, rel=R_TOL)
+            spe = specificity_score(y_true, y_pred, **kwargs)
+            assert spe == pytest.approx(0.88, rel=R_TOL)
 
 
 @pytest.mark.filterwarnings("ignore:Specificity is ill-defined")
diff --git a/imblearn/over_sampling/_random_over_sampler.py b/imblearn/over_sampling/_random_over_sampler.py
@@ -261,3 +261,11 @@ def _more_tags(self):
                 "check_complex_data": "Robust to this type of data.",
             },
         }
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        tags.input_tags.string = True
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/over_sampling/_smote/base.py b/imblearn/over_sampling/_smote/base.py
@@ -829,6 +829,17 @@ def ohe_(self):
         )
         return self.categorical_encoder_
 
+    @available_if(check_version_package("sklearn", "<", "1.6"))
+    def _more_tags(self):
+        return {"X_types": ["2darray", "dataframe", "string"]}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.sparse = False
+        tags.input_tags.string = True
+        return tags
+
 
 @Substitution(
     sampling_strategy=BaseOverSampler._sampling_strategy_docstring,
@@ -1073,3 +1084,10 @@ def _fit_resample(self, X, y):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"X_types": ["2darray", "dataframe", "string"]}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.sparse = False
+        tags.input_tags.string = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py b/imblearn/under_sampling/_prototype_selection/_condensed_nearest_neighbour.py
@@ -264,3 +264,9 @@ def estimator_(self):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py b/imblearn/under_sampling/_prototype_selection/_edited_nearest_neighbours.py
@@ -194,6 +194,12 @@ def _fit_resample(self, X, y):
     def _more_tags(self):
         return {"sample_indices": True}
 
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
+
 
 @Substitution(
     sampling_strategy=BaseCleaningSampler._sampling_strategy_docstring,
@@ -416,6 +422,12 @@ def _fit_resample(self, X, y):
     def _more_tags(self):
         return {"sample_indices": True}
 
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
+
 
 @Substitution(
     sampling_strategy=BaseCleaningSampler._sampling_strategy_docstring,
@@ -625,3 +637,9 @@ def _fit_resample(self, X, y):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py b/imblearn/under_sampling/_prototype_selection/_instance_hardness_threshold.py
@@ -205,3 +205,9 @@ def _fit_resample(self, X, y):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_nearmiss.py b/imblearn/under_sampling/_prototype_selection/_nearmiss.py
@@ -315,3 +315,9 @@ def _more_tags(self):
             }
         }
     # fmt: on
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py b/imblearn/under_sampling/_prototype_selection/_neighbourhood_cleaning_rule.py
@@ -261,3 +261,9 @@ def _fit_resample(self, X, y):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py b/imblearn/under_sampling/_prototype_selection/_one_sided_selection.py
@@ -230,3 +230,9 @@ def estimator_(self):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py b/imblearn/under_sampling/_prototype_selection/_random_under_sampler.py
@@ -147,3 +147,11 @@ def _more_tags(self):
                 "check_complex_data": "Robust to this type of data.",
             },
         }
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        tags.input_tags.string = True
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/under_sampling/_prototype_selection/_tomek_links.py b/imblearn/under_sampling/_prototype_selection/_tomek_links.py
@@ -161,3 +161,9 @@ def _fit_resample(self, X, y):
     @available_if(check_version_package("sklearn", "<", "1.6"))
     def _more_tags(self):
         return {"sample_indices": True}
+
+    @available_if(check_version_package("sklearn", ">=", "1.6"))
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.sampler_tags.sample_indices = True
+        return tags
diff --git a/imblearn/utils/_tags.py b/imblearn/utils/_tags.py
@@ -1,13 +1,101 @@
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 
 import sklearn
 from sklearn.utils.fixes import parse_version
+from .fixes import _dataclass_args
 
 sklearn_version = parse_version(parse_version(sklearn.__version__).base_version)
 
 if sklearn_version >= parse_version("1.6"):
-    from sklearn.utils._tags import InputTags
+    from sklearn.utils._tags import (
+        TargetTags,
+        TransformerTags,
+        ClassifierTags,
+        RegressorTags,
+        InputTags,
+    )
 
-    @dataclass
+    @dataclass(**_dataclass_args())
     class InputTags(InputTags):
         dataframe: bool = True
+
+    @dataclass(**_dataclass_args())
+    class SamplerTags:
+        """Tags for the sampler.
+
+        Parameters
+        ----------
+        sample_indices : bool, default=False
+            Whether the sampler returns the indices of the samples that were
+            selected.
+        """
+
+        sample_indices: bool = False
+
+
+@dataclass(**_dataclass_args())
+class Tags:
+    """Tags for the estimator.
+
+    See :ref:`estimator_tags` for more information.
+
+    Parameters
+    ----------
+    estimator_type : str or None
+        The type of the estimator. Can be one of:
+        - "classifier"
+        - "regressor"
+        - "transformer"
+        - "clusterer"
+        - "outlier_detector"
+        - "density_estimator"
+
+    target_tags : :class:`TargetTags`
+        The target(y) tags.
+
+    transformer_tags : :class:`TransformerTags` or None
+        The transformer tags.
+
+    classifier_tags : :class:`ClassifierTags` or None
+        The classifier tags.
+
+    regressor_tags : :class:`RegressorTags` or None
+        The regressor tags.
+
+    sampler_tags : :class:`SamplerTags` or None
+        The sampler tags.
+
+    array_api_support : bool, default=False
+        Whether the estimator supports Array API compatible inputs.
+
+    no_validation : bool, default=False
+        Whether the estimator skips input-validation. This is only meant for
+        stateless and dummy transformers!
+
+    non_deterministic : bool, default=False
+        Whether the estimator is not deterministic given a fixed ``random_state``.
+
+    requires_fit : bool, default=True
+        Whether the estimator requires to be fitted before calling one of
+        `transform`, `predict`, `predict_proba`, or `decision_function`.
+
+    _skip_test : bool, default=False
+        Whether to skip common tests entirely. Don't use this unless
+        you have a *very good* reason.
+
+    input_tags : :class:`InputTags`
+        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)
diff --git a/imblearn/utils/_test_common/instance_generator.py b/imblearn/utils/_test_common/instance_generator.py
diff --git a/imblearn/utils/_validation.py b/imblearn/utils/_validation.py
diff --git a/imblearn/utils/estimator_checks.py b/imblearn/utils/estimator_checks.py
diff --git a/imblearn/utils/fixes.py b/imblearn/utils/fixes.py
diff --git a/imblearn/utils/tests/test_estimator_checks.py b/imblearn/utils/tests/test_estimator_checks.py
