Improved documentation

untom · untom · commit 5965d49b084c · 2015-06-09T18:26:28.000+02:00
diff --git a/doc/modules/preprocessing.rst b/doc/modules/preprocessing.rst
@@ -103,7 +103,7 @@ Scaling features to a range
 
 An alternative standardization is scaling features to
 lie between a given minimum and maximum value, often between zero and one,
-or so that the maximum value of each feature is scaled to unit size.
+or so that the maximum absolute value of each feature is scaled to unit size.
 This can be achieved using :class:`MinMaxScaler` or :class:`MaxAbsScaler`,
 respectively.
 
@@ -150,8 +150,7 @@ full formula is::
 
 :class:`MaxAbsScaler` works in a very similar fashion, but scales data so
 it lies within the range ``[-1, 1]``, and is meant for data
-that is already centered at zero. In particular, this scaler is very well
-suited for sparse data.
+that is already centered at zero or sparse data.
 
 Here is how to use the toy data from the previous example with this scaler::
 
@@ -173,9 +172,9 @@ Here is how to use the toy data from the previous example with this scaler::
   array([ 2.,  1.,  2.])
 
 
-As with :func:`scale`, the ``preprocessing`` module further provides a
-convenience function function :func:`maxabs_scale` if you don't want to use
-the `Transformer` API.
+As with :func:`scale`, the module further provides a
+convenience function function :func:`maxabs_scale` if you don't want to
+create an object.
 
 
 Scaling sparse data
@@ -191,8 +190,8 @@ matrices  as input, as long as ``with_centering=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
 execution by allocating excessive amounts of memory unintentionally.
-:class:`RobustScaler` cannot be `fit`ted to sparse inputs, but you can use the
-`transform` method on sparse inputs.
+:class:`RobustScaler` cannot be fited to sparse inputs, but you can use
+the ``transform`` method on sparse inputs.
 
 Note that the scalers accept both Compressed Sparse Rows and Compressed
 Sparse Columns format (see ``scipy.sparse.csr_matrix`` and
diff --git a/sklearn/preprocessing/data.py b/sklearn/preprocessing/data.py
@@ -441,11 +441,12 @@ def inverse_transform(self, X, copy=None):
 
 
 class MaxAbsScaler(BaseEstimator, TransformerMixin):
-    """Scale each feature to the [-1, 1] range without breaking the sparsity.
+    """Scale each feature by its maximum absolute value.
 
     This estimator scales and translates each feature individually such
     that the maximal absolute value of each feature in the
-    training set will be 1.0.
+    training set will be 1.0. It does not shift/center the data, and
+    thus does not destroy any sparsity.
 
     This scaler can also be applied to sparse CSR or CSC matrices.
 
@@ -501,7 +502,7 @@ def transform(self, X, y=None):
         if sparse.issparse(X):
             if X.shape[0] == 1:
                 inplace_row_scale(X, 1.0 / self.scale_)
-            elif self.axis == 0:
+            else:
                 inplace_column_scale(X, 1.0 / self.scale_)
         else:
             X /= self.scale_
@@ -532,7 +533,7 @@ def inverse_transform(self, X):
 def maxabs_scale(X, axis=0, copy=True):
     """Scale each feature to the [-1, 1] range without breaking the sparsity.
 
-    This estimator scales and translates each feature individually such
+    This estimator scales each feature individually such
     that the maximal absolute value of each feature in the
     training set will be 1.0.
 
diff --git a/sklearn/preprocessing/tests/test_data.py b/sklearn/preprocessing/tests/test_data.py
@@ -573,7 +573,6 @@ def test_maxabs_scaler_zero_variance_features():
          [0., 1., +1.5],
          [0., 0., +0.0]]
 
-    # default params
     scaler = MaxAbsScaler()
     X_trans = scaler.fit_transform(X)
     X_expected = [[0., 1., 1.0 / 3.0],
@@ -595,6 +594,17 @@ def test_maxabs_scaler_zero_variance_features():
 
     assert_array_almost_equal(X_trans_new, X_expected_new, decimal=2)
 
+    # sparse data
+    X_csr = sparse.csr_matrix(X)
+    X_trans = scaler.fit_transform(X_csr)
+    X_expected = [[0., 1., 1.0 / 3.0],
+                  [0., 1., -0.2],
+                  [0., 1., 1.0],
+                  [0., 0., 0.0]]
+    assert_array_almost_equal(X_trans.A, X_expected)
+    X_trans_inv = scaler.inverse_transform(X_trans)
+    assert_array_almost_equal(X, X_trans_inv.A)
+
 
 def test_maxabs_scaler_large_negative_value():
     """Check MaxAbsScaler on toy data with a large negative value"""
