DOC remove mention of sequence of sequences in Parameters sections

jnothman · ogrisel · commit 255895d951a4 · 2014-06-05T11:20:36.000+02:00
diff --git a/doc/modules/multiclass.rst b/doc/modules/multiclass.rst
@@ -139,8 +139,8 @@ Multilabel learning
 -------------------
 
 :class:`OneVsRestClassifier` also supports multilabel classification.
-To use this feature, feed the classifier a list of tuples containing
-target labels, like in the example below.
+To use this feature, feed the classifier an indicator matrix, in which cell
+[i, j] indicates the presence of label j in sample i.
 
 
 .. figure:: ../auto_examples/images/plot_multilabel_1.png
diff --git a/sklearn/metrics/metrics.py b/sklearn/metrics/metrics.py
@@ -101,9 +101,9 @@ def _check_clf_targets(y_true, y_pred):
         The type of the true target data, as output by
         ``utils.multiclass.type_of_target``
 
-    y_true : array or indicator matrix or sequence of sequences
+    y_true : array or indicator matrix
 
-    y_pred : array or indicator matrix or sequence of sequences
+    y_pred : array or indicator matrix
     """
     y_true, y_pred = check_arrays(y_true, y_pred, allow_lists=True)
     type_true = type_of_target(y_true)
diff --git a/sklearn/multiclass.py b/sklearn/multiclass.py
@@ -142,9 +142,9 @@ class OneVsRestClassifier(BaseEstimator, ClassifierMixin, MetaEstimatorMixin):
     multiclass classification and is a fair default choice.
 
     This strategy can also be used for multilabel learning, where a classifier
-    is used to predict multiple labels for instance, by fitting on a sequence
-    of sequences of labels (e.g., a list of tuples) rather than a single
-    target vector. For multilabel learning, the number of classes must be at
+    is used to predict multiple labels for instance, by fitting on a 2-d matrix
+    in which cell [i, j] is 1 sample i has label j and 0 otherwise.
+    For multilabel learning, the number of classes must be at
     least three, since otherwise OvR reduces to binary classification.
 
     In the multilabel learning literature, OvR is also known as the binary
@@ -188,9 +188,8 @@ def fit(self, X, y):
         X : {array-like, sparse matrix}, shape = [n_samples, n_features]
             Data.
 
-        y : array-like, shape = [n_samples]
-         or sequence of sequences, len = n_samples
-            Multi-class targets. A sequence of sequences turns on multilabel
+        y : array-like, shape = [n_samples] or [n_samples, n_classes]
+            Multi-class targets. An indicator matrix turns on multilabel
             classification.
 
         Returns
diff --git a/sklearn/preprocessing/label.py b/sklearn/preprocessing/label.py
@@ -248,9 +248,10 @@ def fit(self, y):
 
         Parameters
         ----------
-        y : numpy array of shape (n_samples,) or sequence of sequences
-            Target values. In the multilabel case the nested sequences can
-            have variable lengths.
+        y : numpy array of shape (n_samples,) or (n_samples, n_classes)
+            Target values. The 2-d matrix should only contain 0 and 1,
+            represents multilabel classification, and is returned unchanged
+            by LabelBinarizer.
 
         Returns
         -------
@@ -273,9 +274,10 @@ def transform(self, y):
 
         Parameters
         ----------
-        y : numpy array of shape [n_samples] or sequence of sequences
-            Target values. In the multilabel case the nested sequences can
-            have variable lengths.
+        y : numpy array of shape (n_samples,) or (n_samples, n_classes)
+            Target values. The 2-d matrix should only contain 0 and 1,
+            represents multilabel classification, and is returned unchanged
+            by LabelBinarizer.
 
         Returns
         -------
@@ -315,9 +317,10 @@ def inverse_transform(self, Y, threshold=None):
 
         Returns
         -------
-        y : numpy array of shape [n_samples] or sequence of sequences
-            Target values. In the multilabel case the nested sequences can
-            have variable lengths.
+        y : numpy array of shape (n_samples,) or (n_samples, n_classes)
+            Target values. The 2-d matrix should only contain 0 and 1,
+            represents multilabel classification, and is returned unchanged
+            by LabelBinarizer.
 
         Notes
         -----
