ENH rename Scaler to StandardScaler everywhere

Author: amueller

doc/developers/utilities.rst

@@ -144,7 +144,7 @@ efficiently process ``scipy.sparse`` data.
 - :func:`sparsefuncs.inplace_csr_column_scale`: can be used to multiply the
   columns of a CSR matrix by a constant scale (one scale per column).
   Used for scaling features to unit standard deviation in
-  :class:`sklearn.preprocessing.Scaler`.
+  :class:`sklearn.preprocessing.StandardScaler`.
 
 
 Graph Routines

doc/modules/classes.rst

@@ -836,12 +836,13 @@ Pairwise metrics
    :toctree: generated/
    :template: class.rst
 
-   preprocessing.Scaler
-   preprocessing.Normalizer
    preprocessing.Binarizer
+   preprocessing.KernelCenterer
    preprocessing.LabelBinarizer
    preprocessing.LabelEncoder
-   preprocessing.KernelCenterer
+   preprocessing.MinMaxScaler
+   preprocessing.Normalizer
+   preprocessing.StandardScaler
 
 .. autosummary::
    :toctree: generated/

doc/modules/manifold.rst

@@ -427,7 +427,7 @@ Tips on practical use
 
 * Make sure the same scale is used over all features. Because manifold
   learning methods are based on a nearest-neighbor search, the algorithm
-  may perform poorly otherwise.  See :ref:`Scaler <preprocessing_scaler>`
+  may perform poorly otherwise.  See :ref:`StandardScaler <preprocessing_scaler>`
   for convenient ways of scaling heterogeneous data.
 
 * The reconstruction error computed by each routine can be used to choose

doc/modules/preprocessing.rst

@@ -64,15 +64,15 @@ Scaled data has zero mean and unit variance::
 ..    >>> print_options = np.set_printoptions(print_options)
 
 The ``preprocessing`` module further provides a utility class
-:class:`Scaler` that implements the ``Transformer`` API to compute
+:class:`StandardScaler` that implements the ``Transformer`` API to compute
 the mean and standard deviation on a training set so as to be
 able to later reapply the same transformation on the testing set.
 This class is hence suitable for use in the early steps of a
 :class:`sklearn.pipeline.Pipeline`::
 
-  >>> scaler = preprocessing.Scaler().fit(X)
+  >>> scaler = preprocessing.StandardScaler().fit(X)
   >>> scaler
-  Scaler(copy=True, with_mean=True, with_std=True)
+  StandardScaler(copy=True, with_mean=True, with_std=True)
 
   >>> scaler.mean_                                      # doctest: +ELLIPSIS
   array([ 1. ...,  0. ...,  0.33...])
@@ -94,7 +94,7 @@ same way it did on the training set::
 
 It is possible to disable either centering or scaling by either
 passing ``with_mean=False`` or ``with_std=False`` to the constructor
-of :class:`Scaler`.
+of :class:`StandardScaler`.
 
 
 .. topic:: References:
@@ -115,7 +115,7 @@ of :class:`Scaler`.
 
 .. topic:: Sparse input
 
-  :func:`scale` and :class:`Scaler` accept ``scipy.sparse`` matrices
+  :func:`scale` and :class:`StandardScaler` accept ``scipy.sparse`` matrices
   as input **only when with_mean=False is explicitly passed to the
   constructor**. Otherwise a ``ValueError`` will be raised as
   silently centering would break the sparsity and would often crash the
@@ -132,7 +132,7 @@ of :class:`Scaler`.
 
 .. topic:: Scaling target variables in regression
 
-    :func:`scale` and :class:`Scaler` work out-of-the-box with 1d arrays.
+    :func:`scale` and :class:`StandardScaler` work out-of-the-box with 1d arrays.
     This is very useful for scaling the target / response variables used
     for regression.
 
@@ -243,7 +243,7 @@ It is possible to adjust the threshold of the binarizer::
          [ 1.,  0.,  0.],
          [ 0.,  0.,  0.]])
 
-As for the :class:`Scaler` and :class:`Normalizer` classes, the
+As for the :class:`StandardScaler` and :class:`Normalizer` classes, the
 preprocessing module provides a companion function :func:`binarize`
 to be used when the transformer API is not necessary.
 

doc/modules/sgd.rst

@@ -229,10 +229,10 @@ Tips on Practical Use
     attribute on the input vector X to [0,1] or [-1,+1], or standardize
     it to have mean 0 and variance 1. Note that the *same* scaling
     must be applied to the test vector to obtain meaningful
-    results. This can be easily done using :class:`Scaler`::
+    results. This can be easily done using :class:`StandardScaler`::
 
-      from sklearn.preprocessing import Scaler
-      scaler = Scaler()
+      from sklearn.preprocessing import StandardScaler
+      scaler = StandardScaler()
       scaler.fit(X_train)  # Don't cheat - fit only on training data
       X_train = scaler.transform(X_train)
       X_test = scaler.transform(X_test)  # apply same transformation to test data

examples/cluster/plot_cluster_comparison.py

@@ -30,7 +30,7 @@
 from sklearn import cluster, datasets
 from sklearn.metrics import euclidean_distances
 from sklearn.neighbors import kneighbors_graph
-from sklearn.preprocessing import Scaler
+from sklearn.preprocessing import StandardScaler
 
 np.random.seed(0)
 
@@ -55,7 +55,7 @@
                 no_structure]):
     X, y = dataset
     # normalize dataset for easier parameter selection
-    X = Scaler().fit_transform(X)
+    X = StandardScaler().fit_transform(X)
 
     # estimate bandwidth for mean shift
     bandwidth = cluster.estimate_bandwidth(X, quantile=0.3)

examples/linear_model/plot_logistic_l1_l2_sparsity.py

@@ -25,12 +25,12 @@
 
 from sklearn.linear_model import LogisticRegression
 from sklearn import datasets
-from sklearn.preprocessing import Scaler
+from sklearn.preprocessing import StandardScaler
 
 digits = datasets.load_digits()
 
 X, y = digits.data, digits.target
-X = Scaler().fit_transform(X)
+X = StandardScaler().fit_transform(X)
 
 # classify small against large digits
 y = (y > 4).astype(np.int)

examples/linear_model/plot_sparse_recovery.py

@@ -50,7 +50,7 @@
 from sklearn.linear_model import RandomizedLasso, lasso_stability_path, \
                                  LassoLarsCV
 from sklearn.feature_selection import f_regression
-from sklearn.preprocessing import Scaler
+from sklearn.preprocessing import StandardScaler
 from sklearn.metrics import auc, precision_recall_curve
 from sklearn.ensemble import ExtraTreesRegressor
 from sklearn.utils.extmath import pinvh
@@ -97,7 +97,7 @@ def mutual_incoherence(X_relevant, X_irelevant):
     # Keep [Wainwright2006] (26c) constant
     X[:n_relevant_features] /= np.abs(
             linalg.svdvals(X[:n_relevant_features])).max()
-    X = Scaler().fit_transform(X.copy())
+    X = StandardScaler().fit_transform(X.copy())
 
     # The output variable
     y = np.dot(X, coef)

examples/svm/plot_rbf_parameters.py

@@ -25,7 +25,7 @@
 import pylab as pl
 
 from sklearn.svm import SVC
-from sklearn.preprocessing import Scaler
+from sklearn.preprocessing import StandardScaler
 from sklearn.datasets import load_iris
 from sklearn.cross_validation import StratifiedKFold
 from sklearn.grid_search import GridSearchCV
@@ -49,7 +49,7 @@
 # instead of fitting the transformation on the training set and
 # just applying it on the test set.
 
-scaler = Scaler()
+scaler = StandardScaler()
 
 X = scaler.fit_transform(X)
 X_2d = scaler.fit_transform(X_2d)

sklearn/cluster/_k_means.pyx

@@ -243,7 +243,7 @@ def csr_row_norm_l2(X, squared=True):
     """Get L2 norm of each row in CSR matrix X.
 
     TODO: refactor me in the sklearn.utils.sparsefuncs module once the CSR
-    sklearn.preprocessing.Scaler has been refactored as well.
+    sklearn.preprocessing.StandardScaler has been refactored as well.
     """
     cdef:
         unsigned int n_samples = X.shape[0]