DOC improve RandomForest docstring by explicitely stating the splitte…

…r strategy used (scikit-learn#27746)

doc/modules/ensemble.rst

@@ -885,9 +885,9 @@ from a sample drawn with replacement (i.e., a bootstrap sample) from the
 training set.
 
 Furthermore, when splitting each node during the construction of a tree, the
-best split is found either from all input features or a random subset of size
-``max_features``. (See the :ref:`parameter tuning guidelines
-<random_forest_parameters>` for more details).
+best split is found through an exhaustive search of the features values of 
+either all input features or a random subset of size ``max_features``. 
+(See the :ref:`parameter tuning guidelines <random_forest_parameters>` for more details.)
 
 The purpose of these two sources of randomness is to decrease the variance of
 the forest estimator. Indeed, individual decision trees typically exhibit high

sklearn/ensemble/_forest.py

@@ -1177,6 +1177,8 @@ class RandomForestClassifier(ForestClassifier):
     A random forest is a meta estimator that fits a number of decision tree
     classifiers on various sub-samples of the dataset and uses averaging to
     improve the predictive accuracy and control over-fitting.
+    Trees in the forest use the best split strategy, i.e. equivalent to passing
+    `splitter="best"` to the underlying :class:`~sklearn.tree.DecisionTreeRegressor`.
     The sub-sample size is controlled with the `max_samples` parameter if
     `bootstrap=True` (default), otherwise the whole dataset is used to build
     each tree.
@@ -1565,9 +1567,11 @@ class RandomForestRegressor(ForestRegressor):
     """
     A random forest regressor.
 
-    A random forest is a meta estimator that fits a number of decision
-    tree regressors on various sub-samples of the dataset and uses averaging
-    to improve the predictive accuracy and control over-fitting.
+    A random forest is a meta estimator that fits a number of decision tree
+    regressors on various sub-samples of the dataset and uses averaging to
+    improve the predictive accuracy and control over-fitting.
+    Trees in the forest use the best split strategy, i.e. equivalent to passing
+    `splitter="best"` to the underlying :class:`~sklearn.tree.DecisionTreeRegressor`.
     The sub-sample size is controlled with the `max_samples` parameter if
     `bootstrap=True` (default), otherwise the whole dataset is used to build
     each tree.