scikit-learn · thomasjpfan · Sep 4, 2020 · Sep 3, 2020 · Sep 3, 2020 · Sep 4, 2020
diff --git a/doc/developers/contributing.rst b/doc/developers/contributing.rst
@@ -689,12 +689,12 @@ opposed to how it works "under the hood".
 
 Finally, follow the formatting rules below to make it consistently good:
 
-* Add "See also" in docstrings for related classes/functions.
+* Add "See Also" in docstrings for related classes/functions.
 
-* "See also" in docstrings should be one line per reference,
+* "See Also" in docstrings should be one line per reference,
   with a colon and an explanation, for example::
 
-    See also
+    See Also
     --------
     SelectKBest : Select features based on the k highest scores.
     SelectFpr : Select features based on a false positive rate test.

diff --git a/doc/modules/compose.rst b/doc/modules/compose.rst
@@ -148,7 +148,7 @@ or by name::
  * :ref:`sphx_glr_auto_examples_svm_plot_svm_anova.py`
  * :ref:`sphx_glr_auto_examples_compose_plot_compare_reduction.py`
 
-.. topic:: See also:
+.. topic:: See Also:
 
  * :ref:`composite_grid_search`
 
@@ -457,7 +457,7 @@ to specify the column as a list of strings (``['city']``).
 
 Apart from a scalar or a single item list, the column selection can be specified
 as a list of multiple items, an integer array, a slice, a boolean mask, or
-with a :func:`~sklearn.compose.make_column_selector`. The 
+with a :func:`~sklearn.compose.make_column_selector`. The
 :func:`~sklearn.compose.make_column_selector` is used to select columns based
 on data type or column name::
 
@@ -542,8 +542,8 @@ many estimators. This visualization is activated by setting the
   >>> # diplays HTML representation in a jupyter context
   >>> column_trans  # doctest: +SKIP
 
-An example of the HTML output can be seen in the 
-**HTML representation of Pipeline** section of 
+An example of the HTML output can be seen in the
+**HTML representation of Pipeline** section of
 :ref:`sphx_glr_auto_examples_compose_plot_column_transformer_mixed_types.py`.
 As an alternative, the HTML can be written to a file using
 :func:`~sklearn.utils.estimator_html_repr`::

diff --git a/sklearn/_config.py b/sklearn/_config.py
@@ -21,8 +21,8 @@ def get_config():
 
     See Also
     --------
-    config_context: Context manager for global scikit-learn configuration
-    set_config: Set global scikit-learn configuration
+    config_context : Context manager for global scikit-learn configuration.
+    set_config : Set global scikit-learn configuration.
     """
     return _global_config.copy()
 
@@ -69,8 +69,8 @@ def set_config(assume_finite=None, working_memory=None,
 
     See Also
     --------
-    config_context: Context manager for global scikit-learn configuration
-    get_config: Retrieve current values of the global configuration
+    config_context : Context manager for global scikit-learn configuration.
+    get_config : Retrieve current values of the global configuration.
     """
     if assume_finite is not None:
         _global_config['assume_finite'] = assume_finite
@@ -138,8 +138,8 @@ def config_context(**new_config):
 
     See Also
     --------
-    set_config: Set global scikit-learn configuration
-    get_config: Retrieve current values of the global configuration
+    set_config : Set global scikit-learn configuration.
+    get_config : Retrieve current values of the global configuration.
     """
     old_config = get_config().copy()
     set_config(**new_config)

diff --git a/sklearn/calibration.py b/sklearn/calibration.py
@@ -374,7 +374,7 @@ class _CalibratedClassifier:
             if None, then classes is extracted from the given target values
             in fit().
 
-    See also
+    See Also
     --------
     CalibratedClassifierCV
 

diff --git a/sklearn/cluster/_agglomerative.py b/sklearn/cluster/_agglomerative.py
@@ -416,9 +416,9 @@ def linkage_tree(X, connectivity=None, n_clusters=None, linkage='complete',
         distances[i] refers to the distance between children[i][0] and
         children[i][1] when they are merged.
 
-    See also
+    See Also
     --------
-    ward_tree : hierarchical clustering with ward linkage
+    ward_tree : Hierarchical clustering with ward linkage.
     """
     X = np.asarray(X)
     if X.ndim == 1:

diff --git a/sklearn/cluster/_birch.py b/sklearn/cluster/_birch.py
@@ -394,9 +394,7 @@ class Birch(ClusterMixin, TransformerMixin, BaseEstimator):
 
     See Also
     --------
-
-    MiniBatchKMeans
-        Alternative  implementation that does incremental updates
+    MiniBatchKMeans : Alternative implementation that does incremental updates
         of the centers' positions using mini-batches.
 
     Notes

diff --git a/sklearn/cluster/_dbscan.py b/sklearn/cluster/_dbscan.py
@@ -97,13 +97,11 @@ def dbscan(X, eps=0.5, *, min_samples=5, metric='minkowski',
     labels : ndarray of shape (n_samples,)
         Cluster labels for each point.  Noisy samples are given the label -1.
 
-    See also
+    See Also
     --------
-    DBSCAN
-        An estimator interface for this clustering algorithm.
-    OPTICS
-        A similar estimator interface clustering at multiple values of eps. Our
-        implementation is optimized for memory usage.
+    DBSCAN : An estimator interface for this clustering algorithm.
+    OPTICS : A similar estimator interface clustering at multiple values of
+        eps. Our implementation is optimized for memory usage.
 
     Notes
     -----
@@ -232,10 +230,9 @@ class DBSCAN(ClusterMixin, BaseEstimator):
     >>> clustering
     DBSCAN(eps=3, min_samples=2)
 
-    See also
+    See Also
     --------
-    OPTICS
-        A similar clustering at multiple values of eps. Our implementation
+    OPTICS : A similar clustering at multiple values of eps. Our implementation
         is optimized for memory usage.
 
     Notes

diff --git a/sklearn/cluster/_kmeans.py b/sklearn/cluster/_kmeans.py
@@ -714,12 +714,10 @@ class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
     n_iter_ : int
         Number of iterations run.
 
-    See also
+    See Also
     --------
-
-    MiniBatchKMeans
-        Alternative online implementation that does incremental updates
-        of the centers positions using mini-batches.
+    MiniBatchKMeans : Alternative online implementation that does incremental
+        updates of the centers positions using mini-batches.
         For large scale learning (say n_samples > 10k) MiniBatchKMeans is
         probably much faster than the default batch implementation.
 
@@ -1497,8 +1495,7 @@ class MiniBatchKMeans(KMeans):
 
     See Also
     --------
-    KMeans
-        The classic implementation of the clustering method based on the
+    KMeans : The classic implementation of the clustering method based on the
         Lloyd's algorithm. It consumes the whole set of input data at each
         iteration.
 

diff --git a/sklearn/cluster/_optics.py b/sklearn/cluster/_optics.py
@@ -179,8 +179,7 @@ class OPTICS(ClusterMixin, BaseEstimator):
 
     See Also
     --------
-    DBSCAN
-        A similar clustering for a specified neighborhood radius (eps).
+    DBSCAN : A similar clustering for a specified neighborhood radius (eps).
         Our implementation is optimized for runtime.
 
     References

diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -145,12 +145,12 @@ class ColumnTransformer(TransformerMixin, _BaseComposition):
     in the `passthrough` keyword. Those columns specified with `passthrough`
     are added at the right to the output of the transformers.
 
-    See also
+    See Also
     --------
-    sklearn.compose.make_column_transformer : convenience function for
+    make_column_transformer : Convenience function for
         combining the outputs of multiple transformer objects applied to
         column subsets of the original feature space.
-    sklearn.compose.make_column_selector : convenience function for selecting
+    make_column_selector : Convenience function for selecting
         columns based on datatype or the columns name with a regex pattern.
 
     Examples
@@ -772,9 +772,9 @@ def make_column_transformer(*transformers,
     -------
     ct : ColumnTransformer
 
-    See also
+    See Also
     --------
-    sklearn.compose.ColumnTransformer : Class that allows combining the
+    ColumnTransformer : Class that allows combining the
         outputs of multiple transformer objects used on column subsets
         of the data into a single feature space.
 
@@ -838,9 +838,9 @@ class make_column_selector:
         Callable for column selection to be used by a
         :class:`ColumnTransformer`.
 
-    See also
+    See Also
     --------
-    sklearn.compose.ColumnTransformer : Class that allows combining the
+    ColumnTransformer : Class that allows combining the
         outputs of multiple transformer objects used on column subsets
         of the data into a single feature space.
 

diff --git a/sklearn/cross_decomposition/_pls.py b/sklearn/cross_decomposition/_pls.py
@@ -632,7 +632,7 @@ class PLSCanonical(_PLS):
     PLSCanonical()
     >>> X_c, Y_c = plsca.transform(X, Y)
 
-    See also
+    See Also
     --------
     CCA
     PLSSVD
@@ -742,7 +742,7 @@ class CCA(_UnstableArchMixin, _PLS):
     CCA(n_components=1)
     >>> X_c, Y_c = cca.transform(X, Y)
 
-    See also
+    See Also
     --------
     PLSCanonical
     PLSSVD
@@ -824,7 +824,7 @@ class PLSSVD(TransformerMixin, BaseEstimator):
     >>> X_c.shape, Y_c.shape
     ((4, 2), (4, 2))
 
-    See also
+    See Also
     --------
     PLSCanonical
     CCA

diff --git a/sklearn/datasets/_samples_generator.py b/sklearn/datasets/_samples_generator.py
@@ -150,10 +150,10 @@ def make_classification(n_samples=100, n_features=20, *, n_informative=2,
     .. [1] I. Guyon, "Design of experiments for the NIPS 2003 variable
            selection benchmark", 2003.
 
-    See also
+    See Also
     --------
-    make_blobs: simplified variant
-    make_multilabel_classification: unrelated generator for multilabel tasks
+    make_blobs : Simplified variant.
+    make_multilabel_classification : Unrelated generator for multilabel tasks.
     """
     generator = check_random_state(random_state)
 
@@ -461,9 +461,9 @@ def make_hastie_10_2(n_samples=12000, *, random_state=None):
     .. [1] T. Hastie, R. Tibshirani and J. Friedman, "Elements of Statistical
            Learning Ed. 2", Springer, 2009.
 
-    See also
+    See Also
     --------
-    make_gaussian_quantiles: a generalization of this dataset approach
+    make_gaussian_quantiles : A generalization of this dataset approach.
     """
     rs = check_random_state(random_state)
 
@@ -816,9 +816,9 @@ def make_blobs(n_samples=100, n_features=2, *, centers=None, cluster_std=1.0,
     >>> y
     array([0, 1, 2, 0, 2, 2, 2, 1, 1, 0])
 
-    See also
+    See Also
     --------
-    make_classification: a more intricate variant
+    make_classification : A more intricate variant.
     """
     generator = check_random_state(random_state)
 
@@ -1301,7 +1301,7 @@ def make_spd_matrix(n_dim, *, random_state=None):
     X : ndarray of shape (n_dim, n_dim)
         The random symmetric, positive-definite matrix.
 
-    See also
+    See Also
     --------
     make_sparse_spd_matrix
     """
@@ -1357,7 +1357,7 @@ def make_sparse_spd_matrix(dim=1, *, alpha=0.95, norm_diag=False,
     Thus alpha does not translate directly into the filling fraction of
     the matrix itself.
 
-    See also
+    See Also
     --------
     make_spd_matrix
     """
@@ -1633,7 +1633,7 @@ def make_biclusters(shape, n_clusters, *, noise=0.0, minval=10,
         of the seventh ACM SIGKDD international conference on Knowledge
         discovery and data mining (pp. 269-274). ACM.
 
-    See also
+    See Also
     --------
     make_checkerboard
     """
@@ -1725,7 +1725,7 @@ def make_checkerboard(shape, n_clusters, *, noise=0.0, minval=10,
         Spectral biclustering of microarray data: coclustering genes
         and conditions. Genome research, 13(4), 703-716.
 
-    See also
+    See Also
     --------
     make_biclusters
     """

diff --git a/sklearn/datasets/_svmlight_format_io.py b/sklearn/datasets/_svmlight_format_io.py
@@ -132,11 +132,10 @@ def load_svmlight_file(f, *, n_features=None, dtype=np.float64,
        query_id for each sample. Only returned when query_id is set to
        True.
 
-    See also
+    See Also
     --------
-    load_svmlight_files: similar function for loading multiple files in this
-                         format, enforcing the same number of features/columns
-                         on all of them.
+    load_svmlight_files : Similar function for loading multiple files in this
+        format, enforcing the same number of features/columns on all of them.
 
     Examples
     --------
@@ -287,7 +286,7 @@ def load_svmlight_files(files, *, n_features=None, dtype=np.float64,
     number of features (X_train.shape[1] == X_test.shape[1]). This may not
     be the case if you load the files individually with load_svmlight_file.
 
-    See also
+    See Also
     --------
     load_svmlight_file
     """

diff --git a/sklearn/decomposition/_dict_learning.py b/sklearn/decomposition/_dict_learning.py
@@ -1285,7 +1285,7 @@ class DictionaryLearning(_BaseSparseCoding, BaseEstimator):
     J. Mairal, F. Bach, J. Ponce, G. Sapiro, 2009: Online dictionary learning
     for sparse coding (https://www.di.ens.fr/sierra/pdfs/icml09.pdf)
 
-    See also
+    See Also
     --------
     SparseCoder
     MiniBatchDictionaryLearning
@@ -1525,7 +1525,7 @@ class MiniBatchDictionaryLearning(_BaseSparseCoding, BaseEstimator):
     J. Mairal, F. Bach, J. Ponce, G. Sapiro, 2009: Online dictionary learning
     for sparse coding (https://www.di.ens.fr/sierra/pdfs/icml09.pdf)
 
-    See also
+    See Also
     --------
     SparseCoder
     DictionaryLearning

diff --git a/sklearn/decomposition/_factor_analysis.py b/sklearn/decomposition/_factor_analysis.py
@@ -138,7 +138,7 @@ class FactorAnalysis(TransformerMixin, BaseEstimator):
     .. Christopher M. Bishop: Pattern Recognition and Machine Learning,
         Chapter 12.2.4
 
-    See also
+    See Also
     --------
     PCA: Principal component analysis is also a latent linear variable model
         which however assumes equal noise variance for each feature.

diff --git a/sklearn/decomposition/_incremental_pca.py b/sklearn/decomposition/_incremental_pca.py
@@ -157,7 +157,7 @@ class IncrementalPCA(_BasePCA):
     G. Golub and C. Van Loan. Matrix Computations, Third Edition, Chapter 5,
     Section 5.4.4, pp. 252-253.
 
-    See also
+    See Also
     --------
     PCA
     KernelPCA

diff --git a/sklearn/decomposition/_sparse_pca.py b/sklearn/decomposition/_sparse_pca.py
@@ -103,7 +103,7 @@ class SparsePCA(TransformerMixin, BaseEstimator):
     >>> np.mean(transformer.components_ == 0)
     0.9666...
 
-    See also
+    See Also
     --------
     PCA
     MiniBatchSparsePCA
@@ -296,7 +296,7 @@ class MiniBatchSparsePCA(SparsePCA):
     >>> np.mean(transformer.components_ == 0)
     0.94
 
-    See also
+    See Also
     --------
     PCA
     SparsePCA