DOC add missing attributes in several modules (#15521)

pwalchessen · soccergirl34 · glemaitre · web-flow · commit 89b80a6c67ad · 2020-06-18T11:18:23.000+02:00
Co-authored-by: Patricia Walchessen &lt;pwalchessen@gmail.com&gt;
Co-authored-by: Guillaume Lemaitre &lt;g.lemaitre58@gmail.com&gt;
diff --git a/sklearn/feature_selection/_rfe.py b/sklearn/feature_selection/_rfe.py
@@ -52,7 +52,7 @@ class RFE(SelectorMixin, MetaEstimatorMixin, BaseEstimator):
 
     Parameters
     ----------
-    estimator : object
+    estimator : estimator instance
         A supervised learning estimator with a ``fit`` method that provides
         information about feature importance
         (e.g. `coef_`, `feature_importances_`).
@@ -89,19 +89,22 @@ class RFE(SelectorMixin, MetaEstimatorMixin, BaseEstimator):
 
     Attributes
     ----------
+    classes_ : ndarray of shape (n_classes,)
+        Unique class labels.
+
+    estimator_ : estimator instance
+        The fitted estimator used to select features.
+
     n_features_ : int
         The number of selected features.
 
-    support_ : array of shape [n_features]
-        The mask of selected features.
-
-    ranking_ : array of shape [n_features]
+    ranking_ : ndarray of shape (n_features,)
         The feature ranking, such that ``ranking_[i]`` corresponds to the
         ranking position of the i-th feature. Selected (i.e., estimated
         best) features are assigned rank 1.
 
-    estimator_ : object
-        The external estimator fit on the reduced dataset.
+    support_ : ndarray of shape (n_features,)
+        The mask of selected features.
 
     Examples
     --------
@@ -363,7 +366,7 @@ class RFECV(RFE):
 
     Parameters
     ----------
-    estimator : object
+    estimator : estimator instance
         A supervised learning estimator with a ``fit`` method that provides
         information about feature importance either through a ``coef_``
         attribute or through a ``feature_importances_`` attribute.
@@ -439,26 +442,29 @@ class RFECV(RFE):
 
     Attributes
     ----------
+    classes_ : ndarray of shape (n_classes,)
+        Unique class labels.
+
+    estimator_ : estimator instance
+        The fitted estimator used to select features.
+
+    grid_scores_ : ndarray of shape (n_subsets_of_features)
+        The cross-validation scores such that
+        ``grid_scores_[i]`` corresponds to
+        the CV score of the i-th subset of features.
+
     n_features_ : int
         The number of selected features with cross-validation.
 
-    support_ : array of shape [n_features]
-        The mask of selected features.
-
-    ranking_ : array of shape [n_features]
+    ranking_ : narray of shape (n_features,)
         The feature ranking, such that `ranking_[i]`
         corresponds to the ranking
         position of the i-th feature.
         Selected (i.e., estimated best)
         features are assigned rank 1.
 
-    grid_scores_ : array of shape [n_subsets_of_features]
-        The cross-validation scores such that
-        ``grid_scores_[i]`` corresponds to
-        the CV score of the i-th subset of features.
-
-    estimator_ : object
-        The external estimator fit on the reduced dataset.
+    support_ : ndarray of shape (n_features,)
+        The mask of selected features.
 
     Notes
     -----
diff --git a/sklearn/linear_model/_perceptron.py b/sklearn/linear_model/_perceptron.py
@@ -97,20 +97,24 @@ class Perceptron(BaseSGDClassifier):
 
     Attributes
     ----------
-    coef_ : ndarray of shape = [1, n_features] if n_classes == 2 else \
-        [n_classes, n_features]
+    classes_ : ndarray of shape (n_classes,)
+        The unique classes labels.
+
+    coef_ : ndarray of shape (1, n_features) if n_classes == 2 else \
+            (n_classes, n_features)
         Weights assigned to the features.
 
-    intercept_ : ndarray of shape = [1] if n_classes == 2 else [n_classes]
+    intercept_ : ndarray of shape (1,) if n_classes == 2 else (n_classes,)
         Constants in decision function.
 
+    loss_function_ : concrete LossFunction
+        The function that determines the loss, or difference between the
+        output of the algorithm and the target values.
+
     n_iter_ : int
         The actual number of iterations to reach the stopping criterion.
         For multiclass fits, it is the maximum over every binary fit.
 
-    classes_ : ndarray of shape (n_classes,)
-        The unique classes labels.
-
     t_ : int
         Number of weight updates performed during training.
         Same as ``(n_iter_ * n_samples)``.
diff --git a/sklearn/neighbors/_classification.py b/sklearn/neighbors/_classification.py
@@ -104,6 +104,9 @@ class KNeighborsClassifier(NeighborsBase, KNeighborsMixin,
         `p` parameter value if the `effective_metric_` attribute is set to
         'minkowski'.
 
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     outputs_2d_ : bool
         False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit
         otherwise True.
@@ -344,6 +347,13 @@ class RadiusNeighborsClassifier(NeighborsBase, RadiusNeighborsMixin,
         `p` parameter value if the `effective_metric_` attribute is set to
         'minkowski'.
 
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    outlier_label_ : int or array-like of shape (n_class,)
+        Label which is given for outlier samples (samples with no neighbors
+        on given radius).
+
     outputs_2d_ : bool
         False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit
         otherwise True.
@@ -419,7 +429,7 @@ def fit(self, X, y):
 
         elif self.outlier_label == 'most_frequent':
             outlier_label_ = []
-            # iterate over multi-output, get the most frequest label for each
+            # iterate over multi-output, get the most frequent label for each
             # output.
             for k, classes_k in enumerate(classes_):
                 label_count = np.bincount(_y[:, k])
diff --git a/sklearn/neighbors/_graph.py b/sklearn/neighbors/_graph.py
@@ -275,6 +275,22 @@ class KNeighborsTransformer(KNeighborsMixin, UnsupervisedMixin,
         The number of parallel jobs to run for neighbors search.
         If ``-1``, then the number of jobs is set to the number of CPU cores.
 
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     Examples
     --------
     >>> from sklearn.manifold import Isomap
@@ -417,6 +433,22 @@ class RadiusNeighborsTransformer(RadiusNeighborsMixin, UnsupervisedMixin,
         The number of parallel jobs to run for neighbors search.
         If ``-1``, then the number of jobs is set to the number of CPU cores.
 
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     Examples
     --------
     >>> from sklearn.cluster import DBSCAN
diff --git a/sklearn/neighbors/_regression.py b/sklearn/neighbors/_regression.py
@@ -107,6 +107,9 @@ class KNeighborsRegressor(NeighborsBase, KNeighborsMixin,
         `p` parameter value if the `effective_metric_` attribute is set to
         'minkowski'.
 
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     Examples
     --------
     >>> X = [[0], [1], [2], [3]]
@@ -283,6 +286,9 @@ class RadiusNeighborsRegressor(NeighborsBase, RadiusNeighborsMixin,
         `p` parameter value if the `effective_metric_` attribute is set to
         'minkowski'.
 
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     Examples
     --------
     >>> X = [[0], [1], [2], [3]]
diff --git a/sklearn/neighbors/_unsupervised.py b/sklearn/neighbors/_unsupervised.py
@@ -73,22 +73,27 @@ class NearestNeighbors(KNeighborsMixin, RadiusNeighborsMixin,
     effective_metric_params_ : dict
         Parameters for the metric used to compute distances to neighbors.
 
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
     Examples
     --------
-      >>> import numpy as np
-      >>> from sklearn.neighbors import NearestNeighbors
-      >>> samples = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
-
-      >>> neigh = NearestNeighbors(n_neighbors=2, radius=0.4)
-      >>> neigh.fit(samples)
-      NearestNeighbors(...)
-
-      >>> neigh.kneighbors([[0, 0, 1.3]], 2, return_distance=False)
-      array([[2, 0]]...)
-
-      >>> nbrs = neigh.radius_neighbors([[0, 0, 1.3]], 0.4, return_distance=False)
-      >>> np.asarray(nbrs[0][0])
-      array(2)
+    >>> import numpy as np
+    >>> from sklearn.neighbors import NearestNeighbors
+    >>> samples = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
+
+    >>> neigh = NearestNeighbors(n_neighbors=2, radius=0.4)
+    >>> neigh.fit(samples)
+    NearestNeighbors(...)
+
+    >>> neigh.kneighbors([[0, 0, 1.3]], 2, return_distance=False)
+    array([[2, 0]]...)
+
+    >>> nbrs = neigh.radius_neighbors(
+    ...    [[0, 0, 1.3]], 0.4, return_distance=False
+    ... )
+    >>> np.asarray(nbrs[0][0])
+    array(2)
 
     See also
     --------
diff --git a/sklearn/svm/_classes.py b/sklearn/svm/_classes.py
diff --git a/sklearn/tests/test_docstring_parameters.py b/sklearn/tests/test_docstring_parameters.py
