[MRG] Added docstring checks for ensemble module (scikit-learn#11418)

* Added docstring checks for ensemble module

Author: NicolasHug

sklearn/ensemble/forest.py

@@ -374,11 +374,12 @@ def feature_importances_(self):
         return sum(all_importances) / len(self.estimators_)
 
 
-# This is a utility function for joblib's Parallel. It can't go locally in
-# ForestClassifier or ForestRegressor, because joblib complains that it cannot
-# pickle it when placed there.
+def _accumulate_prediction(predict, X, out, lock):
+    """This is a utility function for joblib's Parallel.
 
-def accumulate_prediction(predict, X, out, lock):
+    It can't go locally in ForestClassifier or ForestRegressor, because joblib
+    complains that it cannot pickle it when placed there.
+    """
     prediction = predict(X, check_input=False)
     with lock:
         if len(out) == 1:
@@ -584,7 +585,8 @@ class in a leaf.
                      for j in np.atleast_1d(self.n_classes_)]
         lock = threading.Lock()
         Parallel(n_jobs=n_jobs, verbose=self.verbose, backend="threading")(
-            delayed(accumulate_prediction)(e.predict_proba, X, all_proba, lock)
+            delayed(_accumulate_prediction)(e.predict_proba, X, all_proba,
+                                            lock)
             for e in self.estimators_)
 
         for proba in all_proba:
@@ -691,7 +693,7 @@ def predict(self, X):
         # Parallel loop
         lock = threading.Lock()
         Parallel(n_jobs=n_jobs, verbose=self.verbose, backend="threading")(
-            delayed(accumulate_prediction)(e.predict, X, [y_hat], lock)
+            delayed(_accumulate_prediction)(e.predict, X, [y_hat], lock)
             for e in self.estimators_)
 
         y_hat /= len(self.estimators_)
@@ -763,22 +765,6 @@ class RandomForestClassifier(ForestClassifier):
         "gini" for the Gini impurity and "entropy" for the information gain.
         Note: this parameter is tree-specific.
 
-    max_features : int, float, string or None, optional (default="auto")
-        The number of features to consider when looking for the best split:
-
-        - If int, then consider `max_features` features at each split.
-        - If float, then `max_features` is a fraction and
-          `int(max_features * n_features)` features are considered at each
-          split.
-        - If "auto", then `max_features=sqrt(n_features)`.
-        - If "sqrt", then `max_features=sqrt(n_features)` (same as "auto").
-        - If "log2", then `max_features=log2(n_features)`.
-        - If None, then `max_features=n_features`.
-
-        Note: the search for a split does not stop until at least one
-        valid partition of the node samples is found, even if it requires to
-        effectively inspect more than ``max_features`` features.
-
     max_depth : integer or None, optional (default=None)
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
@@ -811,20 +797,27 @@ class RandomForestClassifier(ForestClassifier):
         the input samples) required to be at a leaf node. Samples have
         equal weight when sample_weight is not provided.
 
+    max_features : int, float, string or None, optional (default="auto")
+        The number of features to consider when looking for the best split:
+
+        - If int, then consider `max_features` features at each split.
+        - If float, then `max_features` is a fraction and
+          `int(max_features * n_features)` features are considered at each
+          split.
+        - If "auto", then `max_features=sqrt(n_features)`.
+        - If "sqrt", then `max_features=sqrt(n_features)` (same as "auto").
+        - If "log2", then `max_features=log2(n_features)`.
+        - If None, then `max_features=n_features`.
+
+        Note: the search for a split does not stop until at least one
+        valid partition of the node samples is found, even if it requires to
+        effectively inspect more than ``max_features`` features.
+
     max_leaf_nodes : int or None, optional (default=None)
         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.
 
-    min_impurity_split : float,
-        Threshold for early stopping in tree growth. A node will split
-        if its impurity is above the threshold, otherwise it is a leaf.
-
-        .. deprecated:: 0.19
-           ``min_impurity_split`` has been deprecated in favor of
-           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
-           Use ``min_impurity_decrease`` instead.
-
     min_impurity_decrease : float, optional (default=0.)
         A node will be split if this split induces a decrease of the impurity
         greater than or equal to this value.
@@ -843,6 +836,15 @@ class RandomForestClassifier(ForestClassifier):
 
         .. versionadded:: 0.19
 
+    min_impurity_split : float,
+        Threshold for early stopping in tree growth. A node will split
+        if its impurity is above the threshold, otherwise it is a leaf.
+
+        .. deprecated:: 0.19
+           ``min_impurity_split`` has been deprecated in favor of
+           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
+           Use ``min_impurity_decrease`` instead.
+
     bootstrap : boolean, optional (default=True)
         Whether bootstrap samples are used when building trees.
 
@@ -1041,22 +1043,6 @@ class RandomForestRegressor(ForestRegressor):
         .. versionadded:: 0.18
            Mean Absolute Error (MAE) criterion.
 
-    max_features : int, float, string or None, optional (default="auto")
-        The number of features to consider when looking for the best split:
-
-        - If int, then consider `max_features` features at each split.
-        - If float, then `max_features` is a fraction and
-          `int(max_features * n_features)` features are considered at each
-          split.
-        - If "auto", then `max_features=n_features`.
-        - If "sqrt", then `max_features=sqrt(n_features)`.
-        - If "log2", then `max_features=log2(n_features)`.
-        - If None, then `max_features=n_features`.
-
-        Note: the search for a split does not stop until at least one
-        valid partition of the node samples is found, even if it requires to
-        effectively inspect more than ``max_features`` features.
-
     max_depth : integer or None, optional (default=None)
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
@@ -1089,20 +1075,27 @@ class RandomForestRegressor(ForestRegressor):
         the input samples) required to be at a leaf node. Samples have
         equal weight when sample_weight is not provided.
 
+    max_features : int, float, string or None, optional (default="auto")
+        The number of features to consider when looking for the best split:
+
+        - If int, then consider `max_features` features at each split.
+        - If float, then `max_features` is a fraction and
+          `int(max_features * n_features)` features are considered at each
+          split.
+        - If "auto", then `max_features=n_features`.
+        - If "sqrt", then `max_features=sqrt(n_features)`.
+        - If "log2", then `max_features=log2(n_features)`.
+        - If None, then `max_features=n_features`.
+
+        Note: the search for a split does not stop until at least one
+        valid partition of the node samples is found, even if it requires to
+        effectively inspect more than ``max_features`` features.
+
     max_leaf_nodes : int or None, optional (default=None)
         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.
 
-    min_impurity_split : float,
-        Threshold for early stopping in tree growth. A node will split
-        if its impurity is above the threshold, otherwise it is a leaf.
-
-        .. deprecated:: 0.19
-           ``min_impurity_split`` has been deprecated in favor of
-           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
-           Use ``min_impurity_decrease`` instead.
-
     min_impurity_decrease : float, optional (default=0.)
         A node will be split if this split induces a decrease of the impurity
         greater than or equal to this value.
@@ -1121,6 +1114,15 @@ class RandomForestRegressor(ForestRegressor):
 
         .. versionadded:: 0.19
 
+    min_impurity_split : float,
+        Threshold for early stopping in tree growth. A node will split
+        if its impurity is above the threshold, otherwise it is a leaf.
+
+        .. deprecated:: 0.19
+           ``min_impurity_split`` has been deprecated in favor of
+           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
+           Use ``min_impurity_decrease`` instead.
+
     bootstrap : boolean, optional (default=True)
         Whether bootstrap samples are used when building trees.
 
@@ -1272,22 +1274,6 @@ class ExtraTreesClassifier(ForestClassifier):
         The function to measure the quality of a split. Supported criteria are
         "gini" for the Gini impurity and "entropy" for the information gain.
 
-    max_features : int, float, string or None, optional (default="auto")
-        The number of features to consider when looking for the best split:
-
-        - If int, then consider `max_features` features at each split.
-        - If float, then `max_features` is a fraction and
-          `int(max_features * n_features)` features are considered at each
-          split.
-        - If "auto", then `max_features=sqrt(n_features)`.
-        - If "sqrt", then `max_features=sqrt(n_features)`.
-        - If "log2", then `max_features=log2(n_features)`.
-        - If None, then `max_features=n_features`.
-
-        Note: the search for a split does not stop until at least one
-        valid partition of the node samples is found, even if it requires to
-        effectively inspect more than ``max_features`` features.
-
     max_depth : integer or None, optional (default=None)
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
@@ -1320,20 +1306,27 @@ class ExtraTreesClassifier(ForestClassifier):
         the input samples) required to be at a leaf node. Samples have
         equal weight when sample_weight is not provided.
 
+    max_features : int, float, string or None, optional (default="auto")
+        The number of features to consider when looking for the best split:
+
+        - If int, then consider `max_features` features at each split.
+        - If float, then `max_features` is a fraction and
+          `int(max_features * n_features)` features are considered at each
+          split.
+        - If "auto", then `max_features=sqrt(n_features)`.
+        - If "sqrt", then `max_features=sqrt(n_features)`.
+        - If "log2", then `max_features=log2(n_features)`.
+        - If None, then `max_features=n_features`.
+
+        Note: the search for a split does not stop until at least one
+        valid partition of the node samples is found, even if it requires to
+        effectively inspect more than ``max_features`` features.
+
     max_leaf_nodes : int or None, optional (default=None)
         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.
 
-    min_impurity_split : float,
-        Threshold for early stopping in tree growth. A node will split
-        if its impurity is above the threshold, otherwise it is a leaf.
-
-        .. deprecated:: 0.19
-           ``min_impurity_split`` has been deprecated in favor of
-           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
-           Use ``min_impurity_decrease`` instead.
-
     min_impurity_decrease : float, optional (default=0.)
         A node will be split if this split induces a decrease of the impurity
         greater than or equal to this value.
@@ -1352,6 +1345,15 @@ class ExtraTreesClassifier(ForestClassifier):
 
         .. versionadded:: 0.19
 
+    min_impurity_split : float,
+        Threshold for early stopping in tree growth. A node will split
+        if its impurity is above the threshold, otherwise it is a leaf.
+
+        .. deprecated:: 0.19
+           ``min_impurity_split`` has been deprecated in favor of
+           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
+           Use ``min_impurity_decrease`` instead.
+
     bootstrap : boolean, optional (default=False)
         Whether bootstrap samples are used when building trees.
 
@@ -1522,22 +1524,6 @@ class ExtraTreesRegressor(ForestRegressor):
         .. versionadded:: 0.18
            Mean Absolute Error (MAE) criterion.
 
-    max_features : int, float, string or None, optional (default="auto")
-        The number of features to consider when looking for the best split:
-
-        - If int, then consider `max_features` features at each split.
-        - If float, then `max_features` is a fraction and
-          `int(max_features * n_features)` features are considered at each
-          split.
-        - If "auto", then `max_features=n_features`.
-        - If "sqrt", then `max_features=sqrt(n_features)`.
-        - If "log2", then `max_features=log2(n_features)`.
-        - If None, then `max_features=n_features`.
-
-        Note: the search for a split does not stop until at least one
-        valid partition of the node samples is found, even if it requires to
-        effectively inspect more than ``max_features`` features.
-
     max_depth : integer or None, optional (default=None)
         The maximum depth of the tree. If None, then nodes are expanded until
         all leaves are pure or until all leaves contain less than
@@ -1570,20 +1556,27 @@ class ExtraTreesRegressor(ForestRegressor):
         the input samples) required to be at a leaf node. Samples have
         equal weight when sample_weight is not provided.
 
+    max_features : int, float, string or None, optional (default="auto")
+        The number of features to consider when looking for the best split:
+
+        - If int, then consider `max_features` features at each split.
+        - If float, then `max_features` is a fraction and
+          `int(max_features * n_features)` features are considered at each
+          split.
+        - If "auto", then `max_features=n_features`.
+        - If "sqrt", then `max_features=sqrt(n_features)`.
+        - If "log2", then `max_features=log2(n_features)`.
+        - If None, then `max_features=n_features`.
+
+        Note: the search for a split does not stop until at least one
+        valid partition of the node samples is found, even if it requires to
+        effectively inspect more than ``max_features`` features.
+
     max_leaf_nodes : int or None, optional (default=None)
         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.
 
-    min_impurity_split : float,
-        Threshold for early stopping in tree growth. A node will split
-        if its impurity is above the threshold, otherwise it is a leaf.
-
-        .. deprecated:: 0.19
-           ``min_impurity_split`` has been deprecated in favor of
-           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
-           Use ``min_impurity_decrease`` instead.
-
     min_impurity_decrease : float, optional (default=0.)
         A node will be split if this split induces a decrease of the impurity
         greater than or equal to this value.
@@ -1602,6 +1595,15 @@ class ExtraTreesRegressor(ForestRegressor):
 
         .. versionadded:: 0.19
 
+    min_impurity_split : float,
+        Threshold for early stopping in tree growth. A node will split
+        if its impurity is above the threshold, otherwise it is a leaf.
+
+        .. deprecated:: 0.19
+           ``min_impurity_split`` has been deprecated in favor of
+           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
+           Use ``min_impurity_decrease`` instead.
+
     bootstrap : boolean, optional (default=False)
         Whether bootstrap samples are used when building trees.
 
@@ -1765,15 +1767,6 @@ class RandomTreesEmbedding(BaseForest):
         Best nodes are defined as relative reduction in impurity.
         If None then unlimited number of leaf nodes.
 
-    min_impurity_split : float,
-        Threshold for early stopping in tree growth. A node will split
-        if its impurity is above the threshold, otherwise it is a leaf.
-
-        .. deprecated:: 0.19
-           ``min_impurity_split`` has been deprecated in favor of
-           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
-           Use ``min_impurity_decrease`` instead.
-
     min_impurity_decrease : float, optional (default=0.)
         A node will be split if this split induces a decrease of the impurity
         greater than or equal to this value.
@@ -1792,8 +1785,14 @@ class RandomTreesEmbedding(BaseForest):
 
         .. versionadded:: 0.19
 
-    bootstrap : boolean, optional (default=True)
-        Whether bootstrap samples are used when building trees.
+    min_impurity_split : float,
+        Threshold for early stopping in tree growth. A node will split
+        if its impurity is above the threshold, otherwise it is a leaf.
+
+        .. deprecated:: 0.19
+           ``min_impurity_split`` has been deprecated in favor of
+           ``min_impurity_decrease`` in 0.19 and will be removed in 0.21.
+           Use ``min_impurity_decrease`` instead.
 
     sparse_output : bool, optional (default=True)
         Whether or not to return a sparse CSR matrix, as default behavior,