[MRG+1] Don't modify steps in {Pipeline,FeatureUnion}.__init__ (#9716)

amueller · jnothman · commit a65a9e53af48 · 2017-09-13T09:20:51.000+10:00
diff --git a/sklearn/pipeline.py b/sklearn/pipeline.py
@@ -110,8 +110,7 @@ class Pipeline(_BaseComposition):
     # BaseEstimator interface
 
     def __init__(self, steps, memory=None):
-        # shallow copy of steps
-        self.steps = list(steps)
+        self.steps = steps
         self._validate_steps()
         self.memory = memory
 
@@ -184,6 +183,8 @@ def _final_estimator(self):
     # Estimator interface
 
     def _fit(self, X, y=None, **fit_params):
+        # shallow copy of steps - this should really be steps_
+        self.steps = list(self.steps)
         self._validate_steps()
         # Setup the memory
         memory = check_memory(self.memory)
@@ -613,7 +614,7 @@ class FeatureUnion(_BaseComposition, TransformerMixin):
 
     """
     def __init__(self, transformer_list, n_jobs=1, transformer_weights=None):
-        self.transformer_list = list(transformer_list)
+        self.transformer_list = transformer_list
         self.n_jobs = n_jobs
         self.transformer_weights = transformer_weights
         self._validate_transformers()
@@ -704,6 +705,7 @@ def fit(self, X, y=None):
         self : FeatureUnion
             This estimator
         """
+        self.transformer_list = list(self.transformer_list)
         self._validate_transformers()
         transformers = Parallel(n_jobs=self.n_jobs)(
             delayed(_fit_one_transformer)(trans, X, y)
diff --git a/sklearn/tests/test_pipeline.py b/sklearn/tests/test_pipeline.py
@@ -19,6 +19,7 @@
 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
+from sklearn.utils.testing import assert_no_warnings
 
 from sklearn.base import clone, BaseEstimator
 from sklearn.pipeline import Pipeline, FeatureUnion, make_pipeline, make_union
@@ -187,7 +188,7 @@ def test_pipeline_init():
     assert_raises(ValueError, pipe.set_params, anova__C=0.1)
 
     # Test clone
-    pipe2 = clone(pipe)
+    pipe2 = assert_no_warnings(clone, pipe)
     assert_false(pipe.named_steps['svc'] is pipe2.named_steps['svc'])
 
     # Check that apart from estimators, the parameters are the same
@@ -421,6 +422,10 @@ def test_feature_union():
     X_sp_transformed = fs.fit_transform(X_sp, y)
     assert_array_almost_equal(X_transformed, X_sp_transformed.toarray())
 
+    # Test clone
+    fs2 = assert_no_warnings(clone, fs)
+    assert_false(fs.transformer_list[0][1] is fs2.transformer_list[0][1])
+
     # test setting parameters
     fs.set_params(select__k=2)
     assert_equal(fs.fit_transform(X, y).shape, (X.shape[0], 4))
