DOC what's new, minor doc improvements

doc/modules/grid_search.rst

@@ -78,6 +78,8 @@ model selection:
    linear_model.LassoLarsIC
 
 
+.. _out_of_bag:
+
 Out of Bag Estimates
 --------------------
 
@@ -91,9 +93,12 @@ This estimate comes "for free" as no addictional data is needed and
 can be used for model selection.
 
 This is currently implemented in the following classes:
+
 .. autosummary::
    :toctree: generated/
    :template: class.rst
 
     ensemble.RandomForestClassifier
+    ensemble.RandomForestRegressor
     ensemble.ExtraTreesClassifier
+    ensemble.ExtraTreesRegressor

doc/whats_new.rst

@@ -5,6 +5,13 @@
 0.11
 ====
 
+Changelog
+---------
+
+    - :ref:`out_of_bag` of generalization error for :ref:`ensemble`
+      by `Andreas Müller`_.
+
+
 API changes summary
 -------------------
 

sklearn/ensemble/forest.py

@@ -482,7 +482,7 @@ class RandomForestClassifier(ForestClassifier):
     `oob_score_` : float
         Score of the training dataset obtained using an out-of-bag estimate.
 
-     `oob_decision_function_` : array, shape = [n_samples, n_classes]
+    `oob_decision_function_` : array, shape = [n_samples, n_classes]
         Decision function computed with out-of-bag estimate on the training set.
 
 
@@ -726,7 +726,7 @@ class ExtraTreesClassifier(ForestClassifier):
     `oob_score_` : float
         Score of the training dataset obtained using an out-of-bag estimate.
 
-     `oob_decision_function_` : array, shape = [n_samples, n_classes]
+    `oob_decision_function_` : array, shape = [n_samples, n_classes]
         Decision function computed with out-of-bag estimate on the training set.
 
     Notes