DOC Ensures that MLPClassifier passes numpydoc validation (#20444)

jmloyola · glemaitre · web-flow · commit adb7ced696b3 · 2021-07-06T11:06:23.000+02:00
Co-authored-by: Guillaume Lemaitre &lt;g.lemaitre58@gmail.com&gt;
diff --git a/maint_tools/test_docstrings.py b/maint_tools/test_docstrings.py
@@ -86,7 +86,6 @@
     "LocalOutlierFactor",
     "LocallyLinearEmbedding",
     "MDS",
-    "MLPClassifier",
     "MLPRegressor",
     "MaxAbsScaler",
     "MeanShift",
diff --git a/sklearn/neural_network/_multilayer_perceptron.py b/sklearn/neural_network/_multilayer_perceptron.py
@@ -742,7 +742,8 @@ def fit(self, X, y):
 
         Returns
         -------
-        self : returns a trained MLP model.
+        self : object
+            Returns a trained MLP model.
         """
         return self._fit(X, y, incremental=False)
 
@@ -825,7 +826,7 @@ class MLPClassifier(ClassifierMixin, BaseMultilayerPerceptron):
     batch_size : int, default='auto'
         Size of minibatches for stochastic optimizers.
         If the solver is 'lbfgs', the classifier will not use minibatch.
-        When set to "auto", `batch_size=min(200, n_samples)`
+        When set to "auto", `batch_size=min(200, n_samples)`.
 
     learning_rate : {'constant', 'invscaling', 'adaptive'}, default='constant'
         Learning rate schedule for weight updates.
@@ -904,27 +905,27 @@ class MLPClassifier(ClassifierMixin, BaseMultilayerPerceptron):
         If early stopping is False, then the training stops when the training
         loss does not improve by more than tol for n_iter_no_change consecutive
         passes over the training set.
-        Only effective when solver='sgd' or 'adam'
+        Only effective when solver='sgd' or 'adam'.
 
     validation_fraction : float, default=0.1
         The proportion of training data to set aside as validation set for
         early stopping. Must be between 0 and 1.
-        Only used if early_stopping is True
+        Only used if early_stopping is True.
 
     beta_1 : float, default=0.9
         Exponential decay rate for estimates of first moment vector in adam,
-        should be in [0, 1). Only used when solver='adam'
+        should be in [0, 1). Only used when solver='adam'.
 
     beta_2 : float, default=0.999
         Exponential decay rate for estimates of second moment vector in adam,
-        should be in [0, 1). Only used when solver='adam'
+        should be in [0, 1). Only used when solver='adam'.
 
     epsilon : float, default=1e-8
-        Value for numerical stability in adam. Only used when solver='adam'
+        Value for numerical stability in adam. Only used when solver='adam'.
 
     n_iter_no_change : int, default=10
         Maximum number of epochs to not meet ``tol`` improvement.
-        Only effective when solver='sgd' or 'adam'
+        Only effective when solver='sgd' or 'adam'.
 
         .. versionadded:: 0.20
 
@@ -979,21 +980,10 @@ class MLPClassifier(ClassifierMixin, BaseMultilayerPerceptron):
     out_activation_ : str
         Name of the output activation function.
 
-    Examples
+    See Also
     --------
-    >>> from sklearn.neural_network import MLPClassifier
-    >>> from sklearn.datasets import make_classification
-    >>> from sklearn.model_selection import train_test_split
-    >>> X, y = make_classification(n_samples=100, random_state=1)
-    >>> X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y,
-    ...                                                     random_state=1)
-    >>> clf = MLPClassifier(random_state=1, max_iter=300).fit(X_train, y_train)
-    >>> clf.predict_proba(X_test[:1])
-    array([[0.038..., 0.961...]])
-    >>> clf.predict(X_test[:5, :])
-    array([1, 0, 1, 0, 1])
-    >>> clf.score(X_test, y_test)
-    0.8...
+    MLPRegressor : Multi-layer Perceptron regressor.
+    BernoulliRBM : Bernoulli Restricted Boltzmann Machine (RBM).
 
     Notes
     -----
@@ -1023,6 +1013,22 @@ class MLPClassifier(ClassifierMixin, BaseMultilayerPerceptron):
 
     Kingma, Diederik, and Jimmy Ba. "Adam: A method for stochastic
         optimization." arXiv preprint arXiv:1412.6980 (2014).
+
+    Examples
+    --------
+    >>> from sklearn.neural_network import MLPClassifier
+    >>> from sklearn.datasets import make_classification
+    >>> from sklearn.model_selection import train_test_split
+    >>> X, y = make_classification(n_samples=100, random_state=1)
+    >>> X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y,
+    ...                                                     random_state=1)
+    >>> clf = MLPClassifier(random_state=1, max_iter=300).fit(X_train, y_train)
+    >>> clf.predict_proba(X_test[:1])
+    array([[0.038..., 0.961...]])
+    >>> clf.predict(X_test[:5, :])
+    array([1, 0, 1, 0, 1])
+    >>> clf.score(X_test, y_test)
+    0.8...
     """
 
     def __init__(
@@ -1134,7 +1140,7 @@ def _validate_input(self, X, y, incremental, reset):
         return X, y
 
     def predict(self, X):
-        """Predict using the multi-layer perceptron classifier
+        """Predict using the multi-layer perceptron classifier.
 
         Parameters
         ----------
@@ -1211,7 +1217,7 @@ def predict_log_proba(self, X):
         log_y_prob : ndarray of shape (n_samples, n_classes)
             The predicted log-probability of the sample for each class
             in the model, where classes are ordered as they are in
-            `self.classes_`. Equivalent to log(predict_proba(X))
+            `self.classes_`. Equivalent to `log(predict_proba(X))`.
         """
         y_prob = self.predict_proba(X)
         return np.log(y_prob, out=y_prob)
