scikit-learn · tzano · Feb 19, 2017 · Feb 19, 2017 · Feb 19, 2017 · Feb 19, 2017
diff --git a/doc/whats_new.rst b/doc/whats_new.rst
@@ -256,6 +256,11 @@ API changes summary
       :func:`sklearn.model_selection.cross_val_predict`.
       :issue:`2879` by :user:`Stephen Hoover <stephen-hoover>`.
 
+    - Deprecate the ``y`` parameter in :meth:`transform`.
+      The method  should not accept ``y`` parameter, as it's used at the prediction time.
+      :issue:`8174` by :user:`Tahar Zanouda <tzano>`.
+
+
 .. _changes_0_18_1:
 
 Version 0.18.1

diff --git a/sklearn/cluster/birch.py b/sklearn/cluster/birch.py
@@ -12,6 +12,7 @@
 from ..metrics.pairwise import euclidean_distances
 from ..base import TransformerMixin, ClusterMixin, BaseEstimator
 from ..externals.six.moves import xrange
+from ..externals.six import string_types
 from ..utils import check_array
 from ..utils.extmath import row_norms, safe_sparse_dot
 from ..utils.validation import check_is_fitted
@@ -569,7 +570,7 @@ def predict(self, X):
         reduced_distance += self._subcluster_norms
         return self.subcluster_labels_[np.argmin(reduced_distance, axis=1)]
 
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """
         Transform X into subcluster centroids dimension.
 
@@ -580,12 +581,20 @@ def transform(self, X, y=None):
         ----------
         X : {array-like, sparse matrix}, shape (n_samples, n_features)
             Input data.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         X_trans : {array-like, sparse matrix}, shape (n_samples, n_clusters)
             Transformed data.
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, 'subcluster_centers_')
         return euclidean_distances(X, self.subcluster_centers_)
 

diff --git a/sklearn/cluster/k_means_.py b/sklearn/cluster/k_means_.py
@@ -911,7 +911,7 @@ def fit_transform(self, X, y=None):
         X = self._check_fit_data(X)
         return self.fit(X)._transform(X)
 
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """Transform X to a cluster-distance space.
 
         In the new space, each dimension is the distance to the cluster
@@ -922,12 +922,20 @@ def transform(self, X, y=None):
         ----------
         X : {array-like, sparse matrix}, shape = [n_samples, n_features]
             New data to transform.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         X_new : array, shape [n_samples, k]
             X transformed in the new space.
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, 'cluster_centers_')
 
         X = self._check_test_data(X)

diff --git a/sklearn/decomposition/base.py b/sklearn/decomposition/base.py
@@ -8,6 +8,7 @@
 #
 # License: BSD 3 clause
 
+import warnings
 import numpy as np
 from scipy import linalg
 
@@ -16,6 +17,7 @@
 from ..utils.extmath import fast_dot
 from ..utils.validation import check_is_fitted
 from ..externals import six
+from ..externals.six import string_types
 from abc import ABCMeta, abstractmethod
 
 
@@ -97,8 +99,7 @@ def fit(X, y=None):
             Returns the instance itself.
         """
 
-
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """Apply dimensionality reduction to X.
 
         X is projected on the first principal components previously extracted
@@ -109,6 +110,9 @@ def transform(self, X, y=None):
         X : array-like, shape (n_samples, n_features)
             New data, where n_samples is the number of samples
             and n_features is the number of features.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
@@ -125,6 +129,11 @@ def transform(self, X, y=None):
         IncrementalPCA(batch_size=3, copy=True, n_components=2, whiten=False)
         >>> ipca.transform(X) # doctest: +SKIP
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, ['mean_', 'components_'], all_or_any=all)
 
         X = check_array(X)

diff --git a/sklearn/decomposition/dict_learning.py b/sklearn/decomposition/dict_learning.py
@@ -7,6 +7,7 @@
 import time
 import sys
 import itertools
+import warnings
 
 from math import sqrt, ceil
 
@@ -17,6 +18,7 @@
 from ..base import BaseEstimator, TransformerMixin
 from ..externals.joblib import Parallel, delayed, cpu_count
 from ..externals.six.moves import zip
+from ..externals.six import string_types
 from ..utils import (check_array, check_random_state, gen_even_slices,
                      gen_batches, _get_n_jobs)
 from ..utils.extmath import randomized_svd, row_norms
@@ -791,7 +793,7 @@ def _set_sparse_coding_params(self, n_components,
         self.split_sign = split_sign
         self.n_jobs = n_jobs
 
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """Encode the data as a sparse combination of the dictionary atoms.
 
         Coding method is determined by the object parameter
@@ -802,13 +804,21 @@ def transform(self, X, y=None):
         X : array of shape (n_samples, n_features)
             Test data to be transformed, must have the same number of
             features as the data used to train the model.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         X_new : array, shape (n_samples, n_components)
             Transformed data
 
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, 'components_')
 
         # XXX : kwargs is not documented

diff --git a/sklearn/decomposition/fastica_.py b/sklearn/decomposition/fastica_.py
@@ -8,13 +8,16 @@
 # Authors: Pierre Lafaye de Micheaux, Stefan van der Walt, Gael Varoquaux,
 #          Bertrand Thirion, Alexandre Gramfort, Denis A. Engemann
 # License: BSD 3 clause
+
 import warnings
+
 import numpy as np
 from scipy import linalg
 
 from ..base import BaseEstimator, TransformerMixin
 from ..externals import six
 from ..externals.six import moves
+from ..externals.six import string_types
 from ..utils import check_array, as_float_array, check_random_state
 from ..utils.extmath import fast_dot
 from ..utils.validation import check_is_fitted
@@ -523,22 +526,29 @@ def fit(self, X, y=None):
         self._fit(X, compute_sources=False)
         return self
 
-    def transform(self, X, y=None, copy=True):
+    def transform(self, X, y='deprecated', copy=True):
         """Recover the sources from X (apply the unmixing matrix).
 
         Parameters
         ----------
         X : array-like, shape (n_samples, n_features)
             Data to transform, where n_samples is the number of samples
             and n_features is the number of features.
-
         copy : bool (optional)
             If False, data passed to fit are overwritten. Defaults to True.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         X_new : array-like, shape (n_samples, n_components)
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, 'mixing_')
 
         X = check_array(X, copy=copy, dtype=FLOAT_DTYPES)

diff --git a/sklearn/decomposition/pca.py b/sklearn/decomposition/pca.py
@@ -12,6 +12,8 @@
 
 from math import log, sqrt
 
+import warnings
+
 import numpy as np
 from scipy import linalg
 from scipy.special import gammaln
@@ -28,6 +30,7 @@
 from ..utils.extmath import stable_cumsum
 from ..utils.validation import check_is_fitted
 from ..utils.arpack import svds
+from ..externals.six import string_types
 
 
 def _assess_dimension_(spectrum, rank, n_samples, n_features):
@@ -719,7 +722,7 @@ def _fit(self, X):
 
         return X
 
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """Apply dimensionality reduction on X.
 
         X is projected on the first principal components previous extracted
@@ -730,12 +733,20 @@ def transform(self, X, y=None):
         X : array-like, shape (n_samples, n_features)
             New data, where n_samples in the number of samples
             and n_features is the number of features.
+        y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         X_new : array-like, shape (n_samples, n_components)
 
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         check_is_fitted(self, 'mean_')
 
         X = check_array(X)

diff --git a/sklearn/decomposition/tests/test_pca.py b/sklearn/decomposition/tests/test_pca.py
@@ -574,6 +574,24 @@ def fit_deprecated(X):
     assert_array_almost_equal(Y, Y_pca)
 
 
+def test_deprecation_transform():
+    depr_message = "The parameter y on transform() is deprecated"
+
+    # PCA on iris data
+    X = iris.data
+
+    pca = PCA(n_components=2)
+    X_r = pca.fit(X)
+
+    # Tests that deprecated Y parameter throws warning
+    assert_warns_message(DeprecationWarning, depr_message, X_r.transform,
+                         X, y=1)
+    assert_warns_message(DeprecationWarning, depr_message, X_r.transform,
+                         X, y=[1])
+    assert_warns_message(DeprecationWarning, depr_message, X_r.transform,
+                         X, y=None)
+
+
 def test_pca_spase_input():
 
     X = np.random.RandomState(0).rand(5, 4)

diff --git a/sklearn/feature_extraction/dict_vectorizer.py b/sklearn/feature_extraction/dict_vectorizer.py
@@ -6,12 +6,15 @@
 from collections import Mapping
 from operator import itemgetter
 
+import warnings
+
 import numpy as np
 import scipy.sparse as sp
 
 from ..base import BaseEstimator, TransformerMixin
 from ..externals import six
 from ..externals.six.moves import xrange
+from ..externals.six import string_types
 from ..utils import check_array, tosequence
 from ..utils.fixes import frombuffer_empty
 
@@ -271,7 +274,7 @@ def inverse_transform(self, X, dict_type=dict):
 
         return dicts
 
-    def transform(self, X, y=None):
+    def transform(self, X, y='deprecated'):
         """Transform feature->value dicts to array or sparse matrix.
 
         Named features not encountered during fit or fit_transform will be
@@ -283,12 +286,18 @@ def transform(self, X, y=None):
             Dict(s) or Mapping(s) from feature names (arbitrary Python
             objects) to feature values (strings or convertible to dtype).
         y : (ignored)
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
 
         Returns
         -------
         Xa : {array, sparse matrix}
             Feature vectors; always 2-d.
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
         if self.sparse:
             return self._transform(X, fitting=False)
 

diff --git a/sklearn/feature_extraction/hashing.py b/sklearn/feature_extraction/hashing.py
@@ -1,13 +1,16 @@
 # Author: Lars Buitinck
 # License: BSD 3 clause
 
+import warnings
+
 import numbers
 
 import numpy as np
 import scipy.sparse as sp
 
 from . import _hashing
 from ..base import BaseEstimator, TransformerMixin
+from ..externals.six import string_types
 
 
 def _iteritems(d):
@@ -114,7 +117,7 @@ def fit(self, X=None, y=None):
         self._validate_params(self.n_features, self.input_type)
         return self
 
-    def transform(self, raw_X, y=None):
+    def transform(self, raw_X, y='deprecated'):
         """Transform a sequence of instances to a scipy.sparse matrix.
 
         Parameters
@@ -126,13 +129,19 @@ def transform(self, raw_X, y=None):
             raw_X need not support the len function, so it can be the result
             of a generator; n_samples is determined on the fly.
         y : (ignored)
-
+            .. deprecated:: 0.19
+               This parameter will be removed in 0.21.
         Returns
         -------
         X : scipy.sparse matrix, shape = (n_samples, self.n_features)
             Feature matrix, for use with estimators or further transformers.
 
         """
+        if not isinstance(y, string_types) or y != 'deprecated':
+            warnings.warn("The parameter y on transform() is "
+                          "deprecated since 0.19 and will be removed in 0.21",
+                          DeprecationWarning)
+
         raw_X = iter(raw_X)
         if self.input_type == "dict":
             raw_X = (_iteritems(d) for d in raw_X)