FEA metadata routing for StackingClassifier and StackingRegressor

doc/metadata_routing.rst

@@ -277,6 +277,8 @@ Meta-estimators and functions supporting metadata routing:
 - :class:`sklearn.calibration.CalibratedClassifierCV`
 - :class:`sklearn.compose.ColumnTransformer`
 - :class:`sklearn.covariance.GraphicalLassoCV`
+- :class:`sklearn.ensemble.StackingClassifier`
+- :class:`sklearn.ensemble.StackingRegressor`
 - :class:`sklearn.ensemble.VotingClassifier`
 - :class:`sklearn.ensemble.VotingRegressor`
 - :class:`sklearn.ensemble.BaggingClassifier`
@@ -316,13 +318,9 @@ Meta-estimators and tools not supporting metadata routing yet:
 - :class:`sklearn.compose.TransformedTargetRegressor`
 - :class:`sklearn.ensemble.AdaBoostClassifier`
 - :class:`sklearn.ensemble.AdaBoostRegressor`
-- :class:`sklearn.ensemble.StackingClassifier`
-- :class:`sklearn.ensemble.StackingRegressor`
 - :class:`sklearn.feature_selection.RFE`
 - :class:`sklearn.feature_selection.RFECV`
 - :class:`sklearn.feature_selection.SequentialFeatureSelector`
-- :class:`sklearn.impute.IterativeImputer`
-- :class:`sklearn.linear_model.RANSACRegressor`
 - :class:`sklearn.model_selection.learning_curve`
 - :class:`sklearn.model_selection.permutation_test_score`
 - :class:`sklearn.model_selection.validation_curve`

doc/modules/ensemble.rst

@@ -1581,8 +1581,8 @@ availability, tested in the order of preference: `predict_proba`,
 `decision_function` and `predict`.
 
 A :class:`StackingRegressor` and :class:`StackingClassifier` can be used as
-any other regressor or classifier, exposing a `predict`, `predict_proba`, and
-`decision_function` methods, e.g.::
+any other regressor or classifier, exposing a `predict`, `predict_proba`, or
+`decision_function` method, e.g.::
 
    >>> y_pred = reg.predict(X_test)
    >>> from sklearn.metrics import r2_score

doc/whats_new/v1.6.rst

@@ -38,7 +38,19 @@ See :ref:`array_api` for more details.
 
 **Classes:**
 
-- 
+-
+
+Metadata Routing
+----------------
+
+The following models now support metadata routing in one or more of their
+methods. Refer to the :ref:`Metadata Routing User Guide <metadata_routing>` for
+more details.
+
+- |Feature| :class:`ensemble.StackingClassifier` and
+  :class:`ensemble.StackingRegressor` now support metadata routing and pass
+  ``**fit_params`` to the underlying estimators via their `fit` methods.
+  :pr:`28701` by :user:`Stefanie Senger <StefanieSenger>`.
 
 Changelog
 ---------

sklearn/ensemble/_base.py

@@ -21,7 +21,7 @@ def _fit_single_estimator(
     estimator, X, y, fit_params, message_clsname=None, message=None
 ):
     """Private function used to fit an estimator within a job."""
-    # TODO(SLEP6): remove if condition for unrouted sample_weight when metadata
+    # TODO(SLEP6): remove if-condition for unrouted sample_weight when metadata
     # routing can't be disabled.
     if not _routing_enabled() and "sample_weight" in fit_params:
         try: