3434from ..utils .seq_dataset import ArrayDataset , CSRDataset
3535
3636
37- ###
38- ### TODO: intercept for all models
39- ### We should define a common function to center data instead of
40- ### repeating the same code inside each fit method.
37+ # TODO: intercept for all models
4138
42- ### TODO: bayesian_ridge_regression and bayesian_regression_ard
43- ### should be squashed into its respective objects.
39+ # TODO: bayesian_ridge_regression and bayesian_regression_ard
40+ # should be squashed into its respective objects.
4441
4542SPARSE_INTERCEPT_DECAY = 0.01
4643# For sparse data intercept updates are scaled by this decay factor to avoid
@@ -69,12 +66,9 @@ def make_dataset(X, y, sample_weight, random_state=None):
6966 return dataset , intercept_decay
7067
7168
72- def sparse_center_data (X , y , fit_intercept , normalize = False ):
73- """
74- Compute information needed to center data to have mean zero along
75- axis 0. Be aware that X will not be centered since it would break
76- the sparsity, but will be normalized if asked so.
77- """
69+ # TODO: this reproduces the behavior prior 0.17
70+ # Must be remove in 0.19
71+ def _sparse_center_data (X , y , fit_intercept , normalize = None ):
7872 if fit_intercept :
7973 # we might require not to change the csr matrix sometimes
8074 # store a copy if normalize is True.
@@ -106,15 +100,96 @@ def sparse_center_data(X, y, fit_intercept, normalize=False):
106100 return X , y , X_mean , y_mean , X_std
107101
108102
109- def center_data (X , y , fit_intercept , normalize = False , copy = True ,
110- sample_weight = None ):
103+ def sparse_center_data (X , y , fit_intercept , standardize = False ,
104+ normalize = None ):
105+ """
106+ Compute information needed to center data to have mean zero along
107+ axis 0. Be aware that X will not be centered since it would break
108+ the sparsity, but will be standardized if asked so.
109+ """
110+ if normalize is not None :
111+ warnings .warn ("The `normalize` parameter is not in use anymore from "
112+ "version 0.17 and will be removed in 0.19. If you want "
113+ "to standardize the data instead, use"
114+ "`standardize=True`" , DeprecationWarning )
115+ return _sparse_center_data (X , y , fit_intercept , normalize )
116+
117+ if fit_intercept :
118+ # we might require not to change the csr matrix sometimes
119+ # store a copy if standardize is True.
120+ # Change dtype to float64 since mean_variance_axis accepts
121+ # it that way.
122+ if sp .isspmatrix (X ) and X .getformat () == 'csr' :
123+ X = sp .csr_matrix (X , copy = standardize , dtype = np .float64 )
124+ else :
125+ X = sp .csc_matrix (X , copy = standardize , dtype = np .float64 )
126+
127+ X_mean , X_var = mean_variance_axis (X , axis = 0 )
128+ if standardize :
129+ # transform variance to std in-place
130+ X_std = np .sqrt (X_var , X_var )
131+ del X_var
132+ X_std [X_std == 0 ] = 1
133+ inplace_column_scale (X , 1. / X_std )
134+ else :
135+ X_std = np .ones (X .shape [1 ])
136+ y_mean = y .mean (axis = 0 )
137+ y = y - y_mean
138+ else :
139+ X_mean = np .zeros (X .shape [1 ])
140+ X_std = np .ones (X .shape [1 ])
141+ y_mean = 0. if y .ndim == 1 else np .zeros (y .shape [1 ], dtype = X .dtype )
142+
143+ return X , y , X_mean , y_mean , X_std
144+
145+
146+ # TODO: this reproduces the behavior prior 0.17
147+ # Must be remove in 0.19
148+ def _center_data (X , y , fit_intercept , normalize = False , copy = True ,
149+ sample_weight = None ):
150+
151+ X = as_float_array (X , copy )
152+ if fit_intercept :
153+ if isinstance (sample_weight , numbers .Number ):
154+ sample_weight = None
155+ if sp .issparse (X ):
156+ X_mean = np .zeros (X .shape [1 ])
157+ X_std = np .ones (X .shape [1 ])
158+ else :
159+ X_mean = np .average (X , axis = 0 , weights = sample_weight )
160+ X -= X_mean
161+ if normalize :
162+ # XXX: currently scaled to variance=n_samples
163+ X_std = np .sqrt (np .sum (X ** 2 , axis = 0 ))
164+ X_std [X_std == 0 ] = 1
165+ X /= X_std
166+ else :
167+ X_std = np .ones (X .shape [1 ])
168+ y_mean = np .average (y , axis = 0 , weights = sample_weight )
169+ y = y - y_mean
170+ else :
171+ X_mean = np .zeros (X .shape [1 ])
172+ X_std = np .ones (X .shape [1 ])
173+ y_mean = 0. if y .ndim == 1 else np .zeros (y .shape [1 ], dtype = X .dtype )
174+ return X , y , X_mean , y_mean , X_std
175+
176+
177+ def center_data (X , y , fit_intercept , standardize = False , normalize = None ,
178+ copy = True , sample_weight = None ):
111179 """
112180 Centers data to have mean zero along axis 0. This is here because
113181 nearly all linear models will want their data to be centered.
114182
115183 If sample_weight is not None, then the weighted mean of X and y
116184 is zero, and not the mean itself
117185 """
186+ if normalize is not None :
187+ warnings .warn ("The `normalize` parameter is not in use anymore from "
188+ "version 0.17 and will be removed in 0.19. If you want "
189+ "to standardize the data instead, use"
190+ "`standardize=True`" , DeprecationWarning )
191+ return _center_data (X , y , fit_intercept , normalize , copy , sample_weight )
192+
118193 X = as_float_array (X , copy )
119194 if fit_intercept :
120195 if isinstance (sample_weight , numbers .Number ):
@@ -125,9 +200,8 @@ def center_data(X, y, fit_intercept, normalize=False, copy=True,
125200 else :
126201 X_mean = np .average (X , axis = 0 , weights = sample_weight )
127202 X -= X_mean
128- if normalize :
129- # XXX: currently scaled to variance=n_samples
130- X_std = np .sqrt (np .sum (X ** 2 , axis = 0 ))
203+ if standardize :
204+ X_std = np .sqrt (np .mean (X ** 2 , axis = 0 ))
131205 X_std [X_std == 0 ] = 1
132206 X /= X_std
133207 else :
@@ -356,8 +430,8 @@ class LinearRegression(LinearModel, RegressorMixin):
356430 to false, no intercept will be used in calculations
357431 (e.g. data is expected to be already centered).
358432
359- normalize : boolean, optional, default False
360- If True, the regressors X will be normalized before regression.
433+ standardize : boolean, optional, default False
434+ If True, the regressors X will be standardized before regression.
361435
362436 copy_X : boolean, optional, default True
363437 If True, X will be copied; else, it may be overwritten.
@@ -385,13 +459,26 @@ class LinearRegression(LinearModel, RegressorMixin):
385459
386460 """
387461
388- def __init__ (self , fit_intercept = True , normalize = False , copy_X = True ,
389- n_jobs = 1 ):
462+ def __init__ (self , fit_intercept = True , standardize = False , normalize = None ,
463+ copy_X = True , n_jobs = 1 ):
464+ if normalize is not None :
465+ warnings .warn ("The `normalize` parameter is not in use anymore "
466+ "from version 0.17 and will be removed in 0.19. If "
467+ "you want the data to be standardized instead, use "
468+ "`standardize=True`" , DeprecationWarning )
390469 self .fit_intercept = fit_intercept
391- self .normalize = normalize
470+ self .standardize = standardize
392471 self .copy_X = copy_X
393472 self .n_jobs = n_jobs
394473
474+ @property
475+ @deprecated ("The `normalize` attribute is not in use anymore "
476+ "from version 0.17 and will be removed in 0.19. If "
477+ "you want the data to be standardized instead, use "
478+ "`standardize=True`" )
479+ def normalize (self ):
480+ return None
481+
395482 def fit (self , X , y , sample_weight = None ):
396483 """
397484 Fit linear model.
@@ -416,11 +503,13 @@ def fit(self, X, y, sample_weight=None):
416503 X , y = check_X_y (X , y , accept_sparse = ['csr' , 'csc' , 'coo' ],
417504 y_numeric = True , multi_output = True )
418505
419- if ((sample_weight is not None ) and np .atleast_1d (sample_weight ).ndim > 1 ):
506+ if ((sample_weight is not None ) and
507+ np .atleast_1d (sample_weight ).ndim > 1 ):
420508 sample_weight = column_or_1d (sample_weight , warn = True )
421509
422510 X , y , X_mean , y_mean , X_std = self ._center_data (
423
F438
- X , y , self .fit_intercept , self .normalize , self .copy_X ,
511+ X , y , fit_intercept = self .fit_intercept ,
512+ standardize = self .standardize , copy = self .copy_X ,
424513 sample_weight = sample_weight )
425514
426515 if sample_weight is not None :
@@ -450,24 +539,25 @@ def fit(self, X, y, sample_weight=None):
450539 return self
451540
452541
453- def _pre_fit (X , y , Xy , precompute , normalize , fit_intercept , copy ):
542+ def _pre_fit (X , y , Xy , precompute , standardize , fit_intercept , copy ):
454543 """Aux function used at beginning of fit in linear models"""
455544 n_samples , n_features = X .shape
456545
457546 if sparse .isspmatrix (X ):
458547 precompute = False
459548 X , y , X_mean , y_mean , X_std = sparse_center_data (
460- X , y , fit_intercept , normalize )
549+ X , y , fit_intercept = fit_intercept , standardize = standardize )
461550 else :
462551 # copy was done in fit if necessary
463552 X , y , X_mean , y_mean , X_std = center_data (
464- X , y , fit_intercept , normalize , copy = copy )
553+ X , y , fit_intercept = fit_intercept , standardize = standardize ,
554+ copy = copy )
465555 if hasattr (precompute , '__array__' ) and (
466- fit_intercept and not np .allclose (X_mean , np .zeros (n_features ))
467- or normalize and not np .allclose (X_std , np .ones (n_features ))):
556+ fit_intercept and not np .allclose (X_mean , np .zeros (n_features )) or
557+ standardize and not np .allclose (X_std , np .ones (n_features ))):
468558 warnings .warn ("Gram matrix was provided but X was centered"
469559 " to fit intercept, "
470- "or X was normalized : recomputing Gram matrix." ,
560+ "or X was standardized : recomputing Gram matrix." ,
471561 UserWarning )
472562 # recompute Gram
473563 precompute = 'auto'
0 commit comments