verifies fit_predict is available on last step of pipeline

sklearn/pipeline.py

@@ -145,25 +145,6 @@ def fit(self, X, y=None, **fit_params):
         self.steps[-1][-1].fit(Xt, y, **fit_params)
         return self
 
-    def fit_predict(self, X, y=None, **fit_params):
-        """Exposes fit_predict on pipelines.
-
-        Fit all the transforms one after the other and transform the
-        data, then run fit_predict of the final estimator on the transformed
-        data.
-
-        Parameters
-        ----------
-        X : iterable
-            Training data. Must fulfill input requirements of first step of
-            the pipeline.
-        y : iterable, default=None
-            Training targets. Must fulfill label requirements for all steps
-            of the pipeline.
-        """
-        Xt, fit_params = self._pre_transform(X, y, **fit_params)
-        return self.steps[-1][-1].fit_predict(Xt, y, **fit_params)
-
     def fit_transform(self, X, y=None, **fit_params):
         """Fit all the transforms one after the other and transform the
         data, then use fit_transform on transformed data using the final
@@ -202,6 +183,26 @@ def predict(self, X):
             Xt = transform.transform(Xt)
         return self.steps[-1][-1].predict(Xt)
 
+    @if_delegate_has_method(delegate='_final_estimator')
+    def fit_predict(self, X, y=None, **fit_params):
+        """Exposes fit_predict on pipelines.
+
+        Fit all the transforms one after the other and transform the
+        data, then run fit_predict of the final estimator on the transformed
+        data.
+
+        Parameters
+        ----------
+        X : iterable
+            Training data. Must fulfill input requirements of first step of
+            the pipeline.
+        y : iterable, default=None
+            Training targets. Must fulfill label requirements for all steps
+            of the pipeline.
+        """
+        Xt, fit_params = self._pre_transform(X, y, **fit_params)
+        return self.steps[-1][-1].fit_predict(Xt, y, **fit_params)
+
     @if_delegate_has_method(delegate='_final_estimator')
     def predict_proba(self, X):
         """Applies transforms to the data, and the predict_proba method of the

sklearn/tests/test_pipeline.py

@@ -5,7 +5,7 @@
 from scipy import sparse
 
 from sklearn.externals.six.moves import zip
-from sklearn.utils.testing import assert_raises
+from sklearn.utils.testing import assert_raises, assert_raises_regex
 from sklearn.utils.testing import assert_equal
 from sklearn.utils.testing import assert_false
 from sklearn.utils.testing import assert_true
@@ -222,6 +222,19 @@ def test_fit_predict_on_pipeline():
     assert_array_almost_equal(pipeline_pred, separate_pred)
 
 
+def test_fit_predict_on_pipeline_without_fit_predict():
+    # tests that applying fit_predict on pipeline where final step does not
+    # have fit_predict implemented raises AttributeError
+    iris = load_iris()
+    scaler = StandardScaler()
+    pca = PCA()
+    pipe = Pipeline([('scaler', scaler), ('pca', pca)])
+
+    assert_raises_regex(AttributeError,
+                        "'PCA' object has no attribute 'fit_predict'",
+                        lambda: pipe.fit_predict(iris.data))
+
+
 def test_feature_union():
     # basic sanity check for feature union
     iris = load_iris()