Merge pull request #4071 from amueller/grid_search_document_best_estimator

jnothman · jnothman · commit cdae4a4ed415 · 2015-01-10T21:56:20.000+11:00
[MRG] Doc best_estimator_ depends on refit=True. Fixes #2976.
diff --git a/examples/model_selection/grid_search_digits.py b/examples/model_selection/grid_search_digits.py
@@ -51,12 +51,12 @@
     print()
 
     clf = GridSearchCV(SVC(C=1), tuned_parameters, cv=5,
-                       scoring='%_weighted' % score)
+                       scoring='%s_weighted' % score)
     clf.fit(X_train, y_train)
 
     print("Best parameters set found on development set:")
     print()
-    print(clf.best_estimator_)
+    print(clf.best_params_)
     print()
     print("Grid scores on development set:")
     print()
diff --git a/sklearn/grid_search.py b/sklearn/grid_search.py
@@ -557,8 +557,8 @@ class GridSearchCV(BaseSearchCV):
     fit_params : dict, optional
         Parameters to pass to the fit method.
 
-    n_jobs : int, optional
-        Number of jobs to run in parallel (default 1).
+    n_jobs : int, default 1
+        Number of jobs to run in parallel.
 
     pre_dispatch : int, or string, optional
         Controls the number of jobs that get dispatched during parallel
@@ -577,17 +577,17 @@ class GridSearchCV(BaseSearchCV):
             - A string, giving an expression as a function of n_jobs,
               as in '2*n_jobs'
 
-    iid : boolean, optional
+    iid : boolean, default=True
         If True, the data is assumed to be identically distributed across
         the folds, and the loss minimized is the total loss per sample,
         and not the mean loss across the folds.
 
-    cv : integer or cross-validation generator, optional
-        If an integer is passed, it is the number of folds (default 3).
+    cv : integer or cross-validation generator, default=3
+        If an integer is passed, it is the number of folds.
         Specific cross-validation objects can be passed, see
         sklearn.cross_validation module for the list of possible objects
 
-    refit : boolean
+    refit : boolean, default=True
         Refit the best estimator with the entire dataset.
         If "False", it is impossible to make predictions using
         this GridSearchCV instance after fitting.
@@ -636,7 +636,7 @@ class GridSearchCV(BaseSearchCV):
     best_estimator_ : estimator
         Estimator that was chosen by the search, i.e. estimator
         which gave highest score (or smallest loss if specified)
-        on the left out data.
+        on the left out data. Not available if refit=False.
 
     best_score_ : float
         Score of best_estimator on the left out data.
@@ -740,8 +740,8 @@ class RandomizedSearchCV(BaseSearchCV):
     fit_params : dict, optional
         Parameters to pass to the fit method.
 
-    n_jobs : int, optional
-        Number of jobs to run in parallel (default 1).
+    n_jobs : int, default=1
+        Number of jobs to run in parallel.
 
     pre_dispatch : int, or string, optional
         Controls the number of jobs that get dispatched during parallel
@@ -760,7 +760,7 @@ class RandomizedSearchCV(BaseSearchCV):
             - A string, giving an expression as a function of n_jobs,
               as in '2*n_jobs'
 
-    iid : boolean, optional
+    iid : boolean, default=True
         If True, the data is assumed to be identically distributed across
         the folds, and the loss minimized is the total loss per sample,
         and not the mean loss across the folds.
@@ -770,7 +770,7 @@ class RandomizedSearchCV(BaseSearchCV):
         Specific cross-validation objects can be passed, see
         sklearn.cross_validation module for the list of possible objects
 
-    refit : boolean
+    refit : boolean, default=True
         Refit the best estimator with the entire dataset.
         If "False", it is impossible to make predictions using
         this RandomizedSearchCV instance after fitting.
@@ -800,7 +800,7 @@ class RandomizedSearchCV(BaseSearchCV):
     best_estimator_ : estimator
         Estimator that was chosen by the search, i.e. estimator
         which gave highest score (or smallest loss if specified)
-        on the left out data.
+        on the left out data. Not available if refit=False.
 
     best_score_ : float
         Score of best_estimator on the left out data.
