DOC Correction: max_depth is effective when max_leaf_nodes is not None (

#7183)

sklearn/ensemble/forest.py

@@ -777,7 +777,6 @@ class RandomForestClassifier(ForestClassifier):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -803,7 +802,6 @@ class RandomForestClassifier(ForestClassifier):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split
@@ -984,7 +982,6 @@ class RandomForestRegressor(ForestRegressor):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -1010,7 +1007,6 @@ class RandomForestRegressor(ForestRegressor):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split
@@ -1151,7 +1147,6 @@ class ExtraTreesClassifier(ForestClassifier):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -1177,7 +1172,6 @@ class ExtraTreesClassifier(ForestClassifier):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split
@@ -1357,7 +1351,6 @@ class ExtraTreesRegressor(ForestRegressor):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -1383,7 +1376,6 @@ class ExtraTreesRegressor(ForestRegressor):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split
@@ -1510,7 +1502,6 @@ class RandomTreesEmbedding(BaseForest):
         The maximum depth of each tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -1536,7 +1527,6 @@ class RandomTreesEmbedding(BaseForest):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split

sklearn/ensemble/gradient_boosting.py

@@ -1296,7 +1296,6 @@ class GradientBoostingClassifier(BaseGradientBoosting, ClassifierMixin):
         depth limits the number of nodes in the tree. Tune this parameter
         for best performance; the best value depends on the interaction
         of the input variables.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     criterion : string, optional (default="friedman_mse")
         The function to measure the quality of a split. Supported criteria
@@ -1359,7 +1358,6 @@ class GradientBoostingClassifier(BaseGradientBoosting, ClassifierMixin):
         Grow trees with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     min_impurity_split : float, optional (default=1e-7)
         Threshold for early stopping in tree growth. A node will split
@@ -1661,7 +1659,6 @@ class GradientBoostingRegressor(BaseGradientBoosting, RegressorMixin):
         depth limits the number of nodes in the tree. Tune this parameter
         for best performance; the best value depends on the interaction
         of the input variables.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     criterion : string, optional (default="friedman_mse")
         The function to measure the quality of a split. Supported criteria

sklearn/tree/_tree.pyx

@@ -285,8 +285,6 @@ cdef class BestFirstTreeBuilder(TreeBuilder):
 
     The best node to expand is given by the node at the frontier that has the
     highest impurity improvement.
-
-    NOTE: this TreeBuilder will ignore ``tree.max_depth`` .
     """
     cdef SIZE_t max_leaf_nodes
 

sklearn/tree/tree.py

@@ -566,7 +566,6 @@ class DecisionTreeClassifier(BaseDecisionTree, ClassifierMixin):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -592,7 +591,6 @@ class DecisionTreeClassifier(BaseDecisionTree, ClassifierMixin):
         Grow a tree with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     class_weight : dict, list of dicts, "balanced" or None, optional (default=None)
         Weights associated with classes in the form ``{class_label: weight}``.
@@ -832,7 +830,6 @@ class DecisionTreeRegressor(BaseDecisionTree, RegressorMixin):
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
         min_samples_split samples.
-        Ignored if ``max_leaf_nodes`` is not None.
 
     min_samples_split : int, float, optional (default=2)
         The minimum number of samples required to split an internal node:
@@ -858,7 +855,6 @@ class DecisionTreeRegressor(BaseDecisionTree, RegressorMixin):
         Grow a tree with ``max_leaf_nodes`` in best-first fashion.
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
-        If not None then ``max_depth`` will be ignored.
 
     random_state : int, RandomState instance or None, optional (default=None)
         If int, random_state is the seed used by the random number generator;