DOC Make explicit that groups required *Group* splitter (scikit-learn#14235)

glemaitre · jnothman · commit 3e14f616ec33 · 2019-07-23T13:06:03.000+10:00
diff --git a/sklearn/feature_selection/rfe.py b/sklearn/feature_selection/rfe.py
@@ -469,7 +469,8 @@ def fit(self, X, y, groups=None):
 
         groups : array-like, shape = [n_samples], optional
             Group labels for the samples used while splitting the dataset into
-            train/test set.
+            train/test set. Only used in conjunction with a "Group" `cv`
+            instance (e.g., `GroupKFold`).
         """
         X, y = check_X_y(X, y, "csr")
 
diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
@@ -630,7 +630,8 @@ def fit(self, X, y=None, groups=None, **fit_params):
 
         groups : array-like, with shape (n_samples,), optional
             Group labels for the samples used while splitting the dataset into
-            train/test set.
+            train/test set. Only used in conjunction with a "Group" `cv`
+            instance (e.g., `GroupKFold`).
 
         **fit_params : dict of string -> object
             Parameters passed to the ``fit`` method of the estimator
diff --git a/sklearn/model_selection/_validation.py b/sklearn/model_selection/_validation.py
@@ -60,7 +60,8 @@ def cross_validate(estimator, X, y=None, groups=None, scoring=None, cv='warn',
 
     groups : array-like, with shape (n_samples,), optional
         Group labels for the samples used while splitting the dataset into
-        train/test set.
+        train/test set. Only used in conjunction with a "Group" `cv` instance
+        (e.g., `GroupKFold`).
 
     scoring : string, callable, list/tuple, dict or None, default: None
         A single string (see :ref:`scoring_parameter`) or a callable
@@ -294,7 +295,8 @@ def cross_val_score(estimator, X, y=None, groups=None, scoring=None, cv='warn',
 
     groups : array-like, with shape (n_samples,), optional
         Group labels for the samples used while splitting the dataset into
-        train/test set.
+        train/test set. Only used in conjunction with a "Group" `cv` instance
+        (e.g., `GroupKFold`).
 
     scoring : string, callable or None, optional, default: None
         A string (see model evaluation documentation) or
@@ -674,7 +676,8 @@ def cross_val_predict(estimator, X, y=None, groups=None, cv='warn',
 
     groups : array-like, with shape (n_samples,), optional
         Group labels for the samples used while splitting the dataset into
-        train/test set.
+        train/test set. Only used in conjunction with a "Group" `cv` instance
+        (e.g., `GroupKFold`).
 
     cv : int, cross-validation generator or an iterable, optional
         Determines the cross-validation splitting strategy.
@@ -1107,7 +1110,8 @@ def learning_curve(estimator, X, y, groups=None,
 
     groups : array-like, with shape (n_samples,), optional
         Group labels for the samples used while splitting the dataset into
-        train/test set.
+        train/test set. Only used in conjunction with a "Group" `cv` instance
+        (e.g., `GroupKFold`).
 
     train_sizes : array-like, shape (n_ticks,), dtype float or int
         Relative or absolute numbers of training examples that will be used to
@@ -1368,7 +1372,8 @@ def validation_curve(estimator, X, y, param_name, param_range, groups=None,
 
     groups : array-like, with shape (n_samples,), optional
         Group labels for the samples used while splitting the dataset into
-        train/test set.
+        train/test set. Only used in conjunction with a "Group" `cv` instance
+        (e.g., `GroupKFold`).
 
     cv : int, cross-validation generator or an iterable, optional
         Determines the cross-validation splitting strategy.
