standardize the use of copy as a parameter of transform() method

Perrine Letellier · Perrine Letellier · commit 5bfb9f776633 · 2015-10-21T17:57:01.000+02:00
diff --git a/sklearn/preprocessing/data.py b/sklearn/preprocessing/data.py
@@ -332,7 +332,7 @@ def partial_fit(self, X, y=None):
         self.data_range_ = data_range
         return self
 
-    def transform(self, X):
+    def transform(self, X, copy=None):
         """Scaling features of X according to feature_range.
 
         Parameters
@@ -341,16 +341,16 @@ def transform(self, X):
             Input data that will be transformed.
         """
         check_is_fitted(self, 'scale_')
-
-        X = check_array(X, copy=self.copy, ensure_2d=False, dtype=FLOAT_DTYPES)
+        copy = copy if copy is not None else self.copy
+        X = check_array(X, copy=copy, ensure_2d=False, dtype=FLOAT_DTYPES)
         if X.ndim == 1:
             warnings.warn(DEPRECATION_MSG_1D, DeprecationWarning)
 
         X *= self.scale_
         X += self.min_
         return X
 
-    def inverse_transform(self, X):
+    def inverse_transform(self, X, copy=None):
         """Undo the scaling of X according to feature_range.
 
         Parameters
@@ -359,8 +359,8 @@ def inverse_transform(self, X):
             Input data that will be transformed. It cannot be sparse.
         """
         check_is_fitted(self, 'scale_')
-
-        X = check_array(X, copy=self.copy, ensure_2d=False, dtype=FLOAT_DTYPES)
+        copy = copy if copy is not None else self.copy
+        X = check_array(X, copy=copy, ensure_2d=False, dtype=FLOAT_DTYPES)
         if X.ndim == 1:
             warnings.warn(DEPRECATION_MSG_1D, DeprecationWarning)
 
@@ -772,7 +772,7 @@ def partial_fit(self, X, y=None):
         self.scale_ = _handle_zeros_in_scale(max_abs)
         return self
 
-    def transform(self, X, y=None):
+    def transform(self, X, y=None, copy=None):
         """Scale the data
 
         Parameters
@@ -781,7 +781,8 @@ def transform(self, X, y=None):
             The data that should be scaled.
         """
         check_is_fitted(self, 'scale_')
-        X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
+        copy = copy if copy is not None else self.copy
+        X = check_array(X, accept_sparse=('csr', 'csc'), copy=copy,
                         ensure_2d=False, estimator=self, dtype=FLOAT_DTYPES)
 
         if X.ndim == 1:
@@ -796,7 +797,7 @@ def transform(self, X, y=None):
             X /= self.scale_
         return X
 
-    def inverse_transform(self, X):
+    def inverse_transform(self, X, copy=None):
         """Scale back the data to the original representation
 
         Parameters
@@ -805,6 +806,7 @@ def inverse_transform(self, X):
             The data that should be transformed back.
         """
         check_is_fitted(self, 'scale_')
+        copy = copy if copy is not None else self.copy
         X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
                         ensure_2d=False, estimator=self, dtype=FLOAT_DTYPES)
         if X.ndim == 1:
@@ -934,9 +936,9 @@ def __init__(self, with_centering=True, with_scaling=True, copy=True):
         self.with_scaling = with_scaling
         self.copy = copy
 
-    def _check_array(self, X, copy):
+    def _check_array(self, X, copy=False):
         """Makes sure centering is not enabled for sparse matrices."""
-        X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
+        X = check_array(X, accept_sparse=('csr', 'csc'), copy=copy,
                         ensure_2d=False, estimator=self, dtype=FLOAT_DTYPES)
 
         if X.ndim == 1:
@@ -972,7 +974,7 @@ def fit(self, X, y=None):
             self.scale_ = _handle_zeros_in_scale(self.scale_, copy=False)
         return self
 
-    def transform(self, X, y=None):
+    def transform(self, X, y=None, copy=None):
         """Center and scale the data
 
         Parameters
@@ -984,7 +986,8 @@ def transform(self, X, y=None):
             check_is_fitted(self, 'center_')
         if self.with_scaling:
             check_is_fitted(self, 'scale_')
-        X = self._check_array(X, self.copy)
+        copy = copy if copy is not None else self.copy
+        X = self._check_array(X, copy)
         if X.ndim == 1:
             warnings.warn(DEPRECATION_MSG_1D, DeprecationWarning)
 
@@ -1001,7 +1004,7 @@ def transform(self, X, y=None):
                 X /= self.scale_
         return X
 
-    def inverse_transform(self, X):
+    def inverse_transform(self, X, copy=None):
         """Scale back the data to the original representation
 
         Parameters
@@ -1013,7 +1016,8 @@ def inverse_transform(self, X):
             check_is_fitted(self, 'center_')
         if self.with_scaling:
             check_is_fitted(self, 'scale_')
-        X = self._check_array(X, self.copy)
+        copy = copy if copy is not None else self.copy
+        X = self._check_array(X, copy)
         if X.ndim == 1:
             warnings.warn(DEPRECATION_MSG_1D, DeprecationWarning)
 
diff --git a/sklearn/preprocessing/imputation.py b/sklearn/preprocessing/imputation.py
@@ -299,7 +299,7 @@ def _dense_fit(self, X, strategy, missing_values, axis):
 
             return most_frequent
 
-    def transform(self, X):
+    def transform(self, X, copy=None):
         """Impute all missing values in X.
 
         Parameters
@@ -311,7 +311,8 @@ def transform(self, X):
             check_is_fitted(self, 'statistics_')
 
         # Copy just once
-        X = as_float_array(X, copy=self.copy, force_all_finite=False)
+        copy = copy if copy is not None else self.copy
+        X = as_float_array(X, copy=copy, force_all_finite=False)
 
         # Since two different arrays can be provided in fit(X) and
         # transform(X), the imputation data need to be recomputed
