EHN Add function score_samples to Pipeline (#13806)

doc/whats_new/v0.22.rst

@@ -55,6 +55,12 @@ Changelog
   of the maximization procedure in :term:`fit`.
   :pr:`13618` by :user:`Yoshihiro Uchida <c56pony>`.
 
+:mod:`sklearn.pipeline`
+.......................
+
+- |Enhancement| :class:`pipeline.Pipeline` now supports :term:`score_samples` if
+  the final estimator does.
+  :pr:`13806` by :user:`Anaël Beaugnon <ab-anssi>`.
 
 :mod:`sklearn.svm`
 ..................

sklearn/pipeline.py

@@ -486,6 +486,25 @@ def decision_function(self, X):
             Xt = transform.transform(Xt)
         return self.steps[-1][-1].decision_function(Xt)
 
+    @if_delegate_has_method(delegate='_final_estimator')
+    def score_samples(self, X):
+        """Apply transforms, and score_samples of the final estimator.
+
+        Parameters
+        ----------
+        X : iterable
+            Data to predict on. Must fulfill input requirements of first step
+            of the pipeline.
+
+        Returns
+        -------
+        y_score : ndarray, shape (n_samples,)
+        """
+        Xt = X
+        for _, _, transformer in self._iter(with_final=False):
+            Xt = transformer.transform(Xt)
+        return self.steps[-1][-1].score_samples(Xt)
+
     @if_delegate_has_method(delegate='_final_estimator')
     def predict_log_proba(self, X):
         """Apply transforms, and predict_log_proba of the final estimator

sklearn/tests/test_pipeline.py

@@ -16,6 +16,7 @@
 from sklearn.utils.testing import assert_raises_regex
 from sklearn.utils.testing import assert_raise_message
 from sklearn.utils.testing import assert_equal
+from sklearn.utils.testing import assert_allclose
 from sklearn.utils.testing import assert_array_equal
 from sklearn.utils.testing import assert_array_almost_equal
 from sklearn.utils.testing import assert_dict_equal
@@ -24,6 +25,7 @@
 from sklearn.base import clone, BaseEstimator
 from sklearn.pipeline import Pipeline, FeatureUnion, make_pipeline, make_union
 from sklearn.svm import SVC
+from sklearn.neighbors import LocalOutlierFactor
 from sklearn.linear_model import LogisticRegression, Lasso
 from sklearn.linear_model import LinearRegression
 from sklearn.cluster import KMeans
@@ -330,6 +332,36 @@ def test_pipeline_methods_pca_svm():
     pipe.score(X, y)
 
 
+def test_pipeline_score_samples_pca_lof():
+    iris = load_iris()
+    X = iris.data
+    # Test that the score_samples method is implemented on a pipeline.
+    # Test that the score_samples method on pipeline yields same results as
+    # applying transform and score_samples steps separately.
+    pca = PCA(svd_solver='full', n_components='mle', whiten=True)
+    lof = LocalOutlierFactor(novelty=True)
+    pipe = Pipeline([('pca', pca), ('lof', lof)])
+    pipe.fit(X)
+    # Check the shapes
+    assert pipe.score_samples(X).shape == (X.shape[0],)
+    # Check the values
+    lof.fit(pca.fit_transform(X))
+    assert_allclose(pipe.score_samples(X), lof.score_samples(pca.transform(X)))
+
+
+def test_score_samples_on_pipeline_without_score_samples():
+    X = np.array([[1], [2]])
+    y = np.array([1, 2])
+    # Test that a pipeline does not have score_samples method when the final
+    # step of the pipeline does not have score_samples defined.
+    pipe = make_pipeline(LogisticRegression())
+    pipe.fit(X, y)
+    with pytest.raises(AttributeError,
+                       match="'LogisticRegression' object has no attribute "
+                             "'score_samples'"):
+        pipe.score_samples(X)
+
+
 def test_pipeline_methods_preprocessing_svm():
     # Test the various methods of the pipeline (preprocessing + svm).
     iris = load_iris()