FEA Add metadata routing to OrthogonalMatchingPursuitCV (scikit-learn#27500)

Co-authored-by: Adrin Jalali <adrin.jalali@gmail.com>

Author: StefanieSenger

doc/metadata_routing.rst

@@ -266,6 +266,7 @@ Meta-estimators and functions supporting metadata routing:
 - :class:`sklearn.multioutput.ClassifierChain`
 - :class:`sklearn.multioutput.MultiOutputClassifier`
 - :class:`sklearn.multioutput.MultiOutputRegressor`
+- :class:`sklearn.linear_model.OrthogonalMatchingPursuitCV`
 - :class:`sklearn.multioutput.RegressorChain`
 - :class:`sklearn.pipeline.Pipeline`
 
@@ -292,7 +293,6 @@ Meta-estimators and tools not supporting metadata routing yet:
 - :class:`sklearn.linear_model.LassoLarsCV`
 - :class:`sklearn.linear_model.MultiTaskElasticNetCV`
 - :class:`sklearn.linear_model.MultiTaskLassoCV`
-- :class:`sklearn.linear_model.OrthogonalMatchingPursuitCV`
 - :class:`sklearn.linear_model.RANSACRegressor`
 - :class:`sklearn.linear_model.RidgeClassifierCV`
 - :class:`sklearn.linear_model.RidgeCV`

doc/whats_new/v1.4.rst

@@ -96,6 +96,11 @@ more details.
   ``**score_params`` which are passed to the underlying scorer.
   :pr:`26525` by :user:`Omar Salman <OmarManzoor>`.
 
+- |Feature| :class:`linear_model.OrthogonalMatchingPursuitCV` now supports
+  metadata routing. Its `fit` now accepts ``**fit_params``, which are passed to
+  the underlying splitter. :pr:`27500` by :user:`Stefanie Senger
+  <StefanieSenger>`.
+
 - |Fix| All meta-estimators for which metadata routing is not yet implemented
   now raise a `NotImplementedError` on `get_metadata_routing` and on `fit` if
   metadata routing is enabled and any metadata is passed to them. :pr:`27389`

sklearn/linear_model/_omp.py

@@ -15,9 +15,15 @@
 
 from ..base import MultiOutputMixin, RegressorMixin, _fit_context
 from ..model_selection import check_cv
-from ..utils import as_float_array, check_array
+from ..utils import Bunch, as_float_array, check_array
 from ..utils._param_validation import Hidden, Interval, StrOptions, validate_params
-from ..utils.metadata_routing import _RoutingNotSupportedMixin
+from ..utils.metadata_routing import (
+    MetadataRouter,
+    MethodMapping,
+    _raise_for_params,
+    _routing_enabled,
+    process_routing,
+)
 from ..utils.parallel import Parallel, delayed
 from ._base import LinearModel, _deprecate_normalize, _pre_fit
 
@@ -904,9 +910,7 @@ def _omp_path_residues(
     return np.dot(coefs.T, X_test.T) - y_test
 
 
-class OrthogonalMatchingPursuitCV(
-    _RoutingNotSupportedMixin, RegressorMixin, LinearModel
-):
+class OrthogonalMatchingPursuitCV(RegressorMixin, LinearModel):
     """Cross-validated Orthogonal Matching Pursuit model (OMP).
 
     See glossary entry for :term:`cross-validation estimator`.
@@ -1060,7 +1064,7 @@ def __init__(
         self.verbose = verbose
 
     @_fit_context(prefer_skip_nested_validation=True)
-    def fit(self, X, y):
+    def fit(self, X, y, **fit_params):
         """Fit the model using X, y as training data.
 
         Parameters
@@ -1071,18 +1075,36 @@ def fit(self, X, y):
         y : array-like of shape (n_samples,)
             Target values. Will be cast to X's dtype if necessary.
 
+        **fit_params : dict
+            Parameters to pass to the underlying splitter.
+
+            .. versionadded:: 1.4
+                Only available if `enable_metadata_routing=True`,
+                which can be set by using
+                ``sklearn.set_config(enable_metadata_routing=True)``.
+                See :ref:`Metadata Routing User Guide <metadata_routing>` for
+                more details.
+
         Returns
         -------
         self : object
             Returns an instance of self.
         """
+        _raise_for_params(fit_params, self, "fit")
+
         _normalize = _deprecate_normalize(
             self.normalize, estimator_name=self.__class__.__name__
         )
 
         X, y = self._validate_data(X, y, y_numeric=True, ensure_min_features=2)
         X = as_float_array(X, copy=False, force_all_finite=False)
         cv = check_cv(self.cv, classifier=False)
+        if _routing_enabled():
+            routed_params = process_routing(self, "fit", **fit_params)
+        else:
+            # TODO(SLEP6): remove when metadata routing cannot be disabled.
+            routed_params = Bunch()
+            routed_params.splitter = Bunch(split={})
         max_iter = (
             min(max(int(0.1 * X.shape[1]), 5), X.shape[1])
             if not self.max_iter
@@ -1099,7 +1121,7 @@ def fit(self, X, y):
                 _normalize,
                 max_iter,
             )
-            for train, test in cv.split(X)
+            for train, test in cv.split(X, **routed_params.splitter.split)
         )
 
         min_early_stop = min(fold.shape[0] for fold in cv_paths)
@@ -1123,3 +1145,24 @@ def fit(self, X, y):
         self.intercept_ = omp.intercept_
         self.n_iter_ = omp.n_iter_
         return self
+
+    def get_metadata_routing(self):
+        """Get metadata routing of this object.
+
+        Please check :ref:`User Guide <metadata_routing>` on how the routing
+        mechanism works.
+
+        .. versionadded:: 1.4
+
+        Returns
+        -------
+        routing : MetadataRouter
+            A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
+            routing information.
+        """
+
+        router = MetadataRouter(owner=self.__class__.__name__).add(
+            splitter=self.cv,
+            method_mapping=MethodMapping().add(callee="split", caller="fit"),
+        )
+        return router

sklearn/tests/test_metaestimators_metadata_routing.py

@@ -228,6 +228,13 @@ def enable_slep006():
         "y": y,
         "estimator_routing_methods": ["fit"],
     },
+    {
+        "metaestimator": OrthogonalMatchingPursuitCV,
+        "X": X,
+        "y": y,
+        "cv_name": "cv",
+        "cv_routing_methods": ["fit"],
+    },
 ]
 """List containing all metaestimators to be tested and their settings
 
@@ -277,7 +284,6 @@ def enable_slep006():
     LassoLarsCV(),
     MultiTaskElasticNetCV(),
     MultiTaskLassoCV(),
-    OrthogonalMatchingPursuitCV(),
     RANSACRegressor(),
     RFE(ConsumingClassifier()),
     RFECV(ConsumingClassifier()),