DOC numpydoc validation for VotingClassifier (scikit-learn#15497)

Author: go-bears

maint_tools/test_docstrings.py

@@ -39,6 +39,15 @@
     "SGDClassifier.score",
     "SGDClassifier.sparsify",
     "SGDClassifier.densify",
+    "VotingClassifier.fit",
+    "VotingClassifier.transform",
+    "VotingClassifier.predict",
+    "VotingClassifier.score",
+    "VotingClassifier.predict_proba",
+    "VotingClassifier.set_params",
+    "VotingClassifier.get_params",
+    "VotingClassifier.named_estimators",
+    "VotingClassifier$",
 ]
 
 

sklearn/base.py

@@ -1,4 +1,8 @@
-"""Base classes for all estimators."""
+"""
+Base classes for all estimators.
+
+Used for VotingClassifier
+"""
 
 # Author: Gael Varoquaux <[email protected]>
 # License: BSD 3 clause
@@ -334,6 +338,7 @@ def _get_tags(self):
 
 class ClassifierMixin:
     """Mixin class for all classifiers in scikit-learn."""
+
     _estimator_type = "classifier"
 
     def score(self, X, y, sample_weight=None):

sklearn/ensemble/_base.py

@@ -1,6 +1,4 @@
-"""
-Base class for ensemble-based estimators.
-"""
+"""Base class for ensemble-based estimators."""
 
 # Authors: Gilles Louppe
 # License: BSD 3 clause
@@ -42,14 +40,13 @@ def _parallel_fit_estimator(estimator, X, y, sample_weight=None):
 
 
 def _set_random_states(estimator, random_state=None):
-    """Sets fixed random_state parameters for an estimator
+    """Set fixed random_state parameters for an estimator.
 
     Finds all parameters ending ``random_state`` and sets them to integers
     derived from ``random_state``.
 
     Parameters
     ----------
-
     estimator : estimator supporting get/set_params
         Estimator with potential randomness managed by random_state
         parameters.
@@ -106,6 +103,7 @@ class BaseEnsemble(MetaEstimatorMixin, BaseEstimator, metaclass=ABCMeta):
     estimators_ : list of estimators
         The collection of fitted base estimators.
     """
+
     # overwrite _required_parameters from MetaEstimatorMixin
     _required_parameters = []
 
@@ -122,8 +120,10 @@ def __init__(self, base_estimator, n_estimators=10,
         # self.estimators_ needs to be filled by the derived classes in fit.
 
     def _validate_estimator(self, default=None):
-        """Check the estimator and the n_estimator attribute, set the
-        `base_estimator_` attribute."""
+        """Check the estimator and the n_estimator attribute.
+
+        Sets the base_estimator_` attributes.
+        """
         if not isinstance(self.n_estimators, numbers.Integral):
             raise ValueError("n_estimators must be an integer, "
                              "got {0}.".format(type(self.n_estimators)))
@@ -159,15 +159,15 @@ def _make_estimator(self, append=True, random_state=None):
         return estimator
 
     def __len__(self):
-        """Returns the number of estimators in the ensemble."""
+        """Return the number of estimators in the ensemble."""
         return len(self.estimators_)
 
     def __getitem__(self, index):
-        """Returns the index'th estimator in the ensemble."""
+        """Return the index'th estimator in the ensemble."""
         return self.estimators_[index]
 
     def __iter__(self):
-        """Returns iterator over estimators in the ensemble."""
+        """Return iterator over estimators in the ensemble."""
         return iter(self.estimators_)
 
 
@@ -204,6 +204,7 @@ class _BaseHeterogeneousEnsemble(MetaEstimatorMixin, _BaseComposition,
         training data. If an estimator has been set to `'drop'`, it will not
         appear in `estimators_`.
     """
+
     _required_parameters = ['estimators']
 
     @property

sklearn/ensemble/_voting.py

@@ -41,21 +41,19 @@ class _BaseVoting(TransformerMixin, _BaseHeterogeneousEnsemble):
 
     @property
     def _weights_not_none(self):
-        """Get the weights of not `None` estimators"""
+        """Get the weights of not `None` estimators."""
         if self.weights is None:
             return None
         return [w for est, w in zip(self.estimators, self.weights)
                 if est[1] not in (None, 'drop')]
 
     def _predict(self, X):
-        """Collect results from clf.predict calls. """
+        """Collect results from clf.predict calls."""
         return np.asarray([est.predict(X) for est in self.estimators_]).T
 
     @abstractmethod
     def fit(self, X, y, sample_weight=None):
-        """
-        common fit operations.
-        """
+        """Get common fit operations."""
         names, clfs = self._validate_estimators()
 
         if (self.weights is not None and
@@ -90,7 +88,7 @@ class VotingClassifier(ClassifierMixin, _BaseVoting):
 
     Parameters
     ----------
-    estimators : list of (string, estimator) tuples
+    estimators : list of (str, estimator) tuples
         Invoking the ``fit`` method on the ``VotingClassifier`` will fit clones
         of those original estimators that will be stored in the class attribute
         ``self.estimators_``. An estimator can be set to ``'drop'``
@@ -138,6 +136,10 @@ class VotingClassifier(ClassifierMixin, _BaseVoting):
     classes_ : array-like, shape (n_predictions,)
         The classes labels.
 
+    See Also
+    --------
+    VotingRegressor: Prediction voting regressor.
+
     Examples
     --------
     >>> import numpy as np
@@ -172,10 +174,6 @@ class VotingClassifier(ClassifierMixin, _BaseVoting):
     [1 1 1 2 2 2]
     >>> print(eclf3.transform(X).shape)
     (6, 6)
-
-    See also
-    --------
-    VotingRegressor: Prediction voting regressor.
     """
 
     def __init__(self, estimators, voting='hard', weights=None, n_jobs=None,
@@ -187,7 +185,7 @@ def __init__(self, estimators, voting='hard', weights=None, n_jobs=None,
         self.flatten_transform = flatten_transform
 
     def fit(self, X, y, sample_weight=None):
-        """ Fit the estimators.
+        """Fit the estimators.
 
         Parameters
         ----------
@@ -206,6 +204,7 @@ def fit(self, X, y, sample_weight=None):
         Returns
         -------
         self : object
+
         """
         check_classification_targets(y)
         if isinstance(y, np.ndarray) and len(y.shape) > 1 and y.shape[1] > 1:
@@ -223,7 +222,7 @@ def fit(self, X, y, sample_weight=None):
         return super().fit(X, transformed_y, sample_weight)
 
     def predict(self, X):
-        """ Predict class labels for X.
+        """Predict class labels for X.
 
         Parameters
         ----------
@@ -235,7 +234,6 @@ def predict(self, X):
         maj : array-like, shape (n_samples,)
             Predicted class labels.
         """
-
         check_is_fitted(self)
         if self.voting == 'soft':
             maj = np.argmax(self.predict_proba(X), axis=1)
@@ -252,11 +250,11 @@ def predict(self, X):
         return maj
 
     def _collect_probas(self, X):
-        """Collect results from clf.predict calls. """
+        """Collect results from clf.predict calls."""
         return np.asarray([clf.predict_proba(X) for clf in self.estimators_])
 
     def _predict_proba(self, X):
-        """Predict class probabilities for X in 'soft' voting """
+        """Predict class probabilities for X in 'soft' voting."""
         check_is_fitted(self)
         avg = np.average(self._collect_probas(X), axis=0,
                          weights=self._weights_not_none)