scikit-learn · jrbourbeau · Nov 2, 2018
diff --git a/sklearn/calibration.py b/sklearn/calibration.py
@@ -83,8 +83,8 @@ class CalibratedClassifierCV(BaseEstimator, ClassifierMixin):
 
     Attributes
     ----------
-    classes_ : array, shape (n_classes)
-        The class labels.
+    classes_ : array, shape = (n_classes,)
+        Class labels.
 
     calibrated_classifiers_ : list (len() equal to cv or 1 if cv == "prefit")
         The list of calibrated classifiers, one for each crossvalidation fold,

diff --git a/sklearn/discriminant_analysis.py b/sklearn/discriminant_analysis.py
@@ -594,6 +594,9 @@ class QuadraticDiscriminantAnalysis(BaseEstimator, ClassifierMixin):
         of the Gaussian distributions along its principal axes, i.e. the
         variance in the rotated coordinate system.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis

diff --git a/sklearn/ensemble/gradient_boosting.py b/sklearn/ensemble/gradient_boosting.py
@@ -1905,6 +1905,9 @@ class GradientBoostingClassifier(BaseGradientBoosting, ClassifierMixin):
         The collection of fitted sub-estimators. ``loss_.K`` is 1 for binary
         classification, otherwise n_classes.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Notes
     -----
     The features are always randomly permuted at each split. Therefore,

diff --git a/sklearn/linear_model/logistic.py b/sklearn/linear_model/logistic.py
@@ -1167,6 +1167,9 @@ class LogisticRegression(BaseEstimator, LinearClassifierMixin,
             In SciPy <= 1.0.0 the number of lbfgs iterations may exceed
             ``max_iter``. ``n_iter_`` will now report at most ``max_iter``.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.datasets import load_iris
@@ -1638,6 +1641,9 @@ class LogisticRegressionCV(LogisticRegression, BaseEstimator,
         Actual number of iterations for all classes, folds and Cs.
         In the binary or multinomial cases, the first dimension is equal to 1.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.datasets import load_iris

diff --git a/sklearn/linear_model/passive_aggressive.py b/sklearn/linear_model/passive_aggressive.py
@@ -133,6 +133,9 @@ class PassiveAggressiveClassifier(BaseSGDClassifier):
         The actual number of iterations to reach the stopping criterion.
         For multiclass fits, it is the maximum over every binary fit.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.linear_model import PassiveAggressiveClassifier

diff --git a/sklearn/linear_model/perceptron.py b/sklearn/linear_model/perceptron.py
@@ -117,6 +117,9 @@ class Perceptron(BaseSGDClassifier):
         The actual number of iterations to reach the stopping criterion.
         For multiclass fits, it is the maximum over every binary fit.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Notes
     -----
 

diff --git a/sklearn/linear_model/ridge.py b/sklearn/linear_model/ridge.py
@@ -775,6 +775,9 @@ class RidgeClassifier(LinearClassifierMixin, _BaseRidge):
         Independent term in decision function. Set to 0.0 if
         ``fit_intercept = False``.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     n_iter_ : array or None, shape (n_targets,)
         Actual number of iterations for each target. Available only for
         sag and lsqr solvers. Other solvers will return None.
@@ -1358,6 +1361,9 @@ class RidgeClassifierCV(LinearClassifierMixin, _BaseRidgeCV):
         Independent term in decision function. Set to 0.0 if
         ``fit_intercept = False``.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     alpha_ : float
         Estimated regularization parameter
 

diff --git a/sklearn/linear_model/stochastic_gradient.py b/sklearn/linear_model/stochastic_gradient.py
@@ -938,6 +938,9 @@ class SGDClassifier(BaseSGDClassifier):
     intercept_ : array, shape (1,) if n_classes == 2 else (n_classes,)
         Constants in decision function.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     n_iter_ : int
         The actual number of iterations to reach the stopping criterion.
         For multiclass fits, it is the maximum over every binary fit.

diff --git a/sklearn/naive_bayes.py b/sklearn/naive_bayes.py
@@ -143,6 +143,9 @@ class GaussianNB(BaseNB):
     epsilon_ : float
         absolute additive value to variances
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> import numpy as np
@@ -676,6 +679,9 @@ class MultinomialNB(BaseDiscreteNB):
         during fitting. This value is weighted by the sample weight when
         provided.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> import numpy as np
@@ -777,6 +783,9 @@ class ComplementNB(BaseDiscreteNB):
         Number of samples encountered for each feature during fitting. This
         value is weighted by the sample weight when provided.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> import numpy as np
@@ -878,6 +887,9 @@ class BernoulliNB(BaseDiscreteNB):
         during fitting. This value is weighted by the sample weight when
         provided.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> import numpy as np

diff --git a/sklearn/neighbors/classification.py b/sklearn/neighbors/classification.py
@@ -82,6 +82,11 @@ class KNeighborsClassifier(NeighborsBase, KNeighborsMixin,
         for more details.
         Doesn't affect :meth:`fit` method.
 
+    Attributes
+    ----------
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> X = [[0], [1], [2], [3]]
@@ -296,6 +301,11 @@ class RadiusNeighborsClassifier(NeighborsBase, RadiusNeighborsMixin,
         ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
         for more details.
 
+    Attributes
+    ----------
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> X = [[0], [1], [2], [3]]

diff --git a/sklearn/neighbors/nearest_centroid.py b/sklearn/neighbors/nearest_centroid.py
@@ -48,6 +48,9 @@ class NearestCentroid(BaseEstimator, ClassifierMixin):
     centroids_ : array-like, shape = [n_classes, n_features]
         Centroid of each class
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.neighbors.nearest_centroid import NearestCentroid

diff --git a/sklearn/semi_supervised/label_propagation.py b/sklearn/semi_supervised/label_propagation.py
@@ -340,7 +340,7 @@ class LabelPropagation(BaseLabelPropagation):
     X_ : array, shape = [n_samples, n_features]
         Input array.
 
-    classes_ : array, shape = [n_classes]
+    classes_ : array, shape = (n_classes,)
         The distinct labels used in classifying instances.
 
     label_distributions_ : array, shape = [n_samples, n_classes]
@@ -454,7 +454,7 @@ class LabelSpreading(BaseLabelPropagation):
     X_ : array, shape = [n_samples, n_features]
         Input array.
 
-    classes_ : array, shape = [n_classes]
+    classes_ : array, shape = (n_classes,)
         The distinct labels used in classifying instances.
 
     label_distributions_ : array, shape = [n_samples, n_classes]

diff --git a/sklearn/svm/classes.py b/sklearn/svm/classes.py
@@ -111,6 +111,9 @@ class LinearSVC(BaseEstimator, LinearClassifierMixin,
     intercept_ : array, shape = [1] if n_classes == 2 else [n_classes]
         Constants in decision function.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> from sklearn.svm import LinearSVC
@@ -556,6 +559,9 @@ class SVC(BaseSVC):
     fit_status_ : int
         0 if correctly fitted, 1 otherwise (will raise warning)
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     probA_ : array, shape = [n_class * (n_class-1) / 2]
     probB_ : array, shape = [n_class * (n_class-1) / 2]
         If probability=True, the parameters learned in Platt scaling to
@@ -737,6 +743,9 @@ class NuSVC(BaseSVC):
     intercept_ : array, shape = [n_class * (n_class-1) / 2]
         Constants in decision function.
 
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     Examples
     --------
     >>> import numpy as np

diff --git a/sklearn/tests/test_docstring_parameters.py b/sklearn/tests/test_docstring_parameters.py
@@ -17,6 +17,7 @@
 from sklearn.utils.testing import check_docstring_parameters
 from sklearn.utils.testing import _get_func_name
 from sklearn.utils.testing import ignore_warnings
+from sklearn.utils.testing import all_estimators
 from sklearn.utils.deprecation import _is_deprecated
 
 import pytest
@@ -144,3 +145,15 @@ def test_tabs():
         assert '\t' not in source, ('"%s" has tabs, please remove them ',
                                     'or add it to theignore list'
                                     % modname)
+
+
+@pytest.mark.parametrize('name, Classifier',
+                         all_estimators(type_filter='classifier'))
+def test_classifier_docstring_attributes(name, Classifier):
+    pytest.importorskip('numpydoc')
+    from numpydoc import docscrape
+
+    doc = docscrape.ClassDoc(Classifier)
+    attributes = doc['Attributes']
+    assert attributes
+    assert any(['classes_' in att[0] for att in attributes])
diff --git a/sklearn/tree/tree.py b/sklearn/tree/tree.py
@@ -1291,6 +1291,11 @@ class ExtraTreeClassifier(DecisionTreeClassifier):
         Note that these weights will be multiplied with sample_weight (passed
         through the fit method) if sample_weight is specified.
 
+    Attributes
+    ----------
+    classes_ : array, shape = (n_classes,)
+        Class labels.
+
     See also
     --------
     ExtraTreeRegressor, sklearn.ensemble.ExtraTreesClassifier,