DOC fix some whats_new/0.22 links and other cleanups (#15059)

doc/whats_new/v0.22.rst

@@ -56,15 +56,15 @@ Changelog
 :mod:`sklearn.base`
 ...................
 
-- |API| From version 0.24 :meth:`BaseEstimator.get_params` will raise an
+- |API| From version 0.24 :meth:`base.BaseEstimator.get_params` will raise an
   AttributeError rather than return None for parameters that are in the
   estimator's constructor but not stored as attributes on the instance.
   :pr:`14464` by `Joel Nothman`_.
 
 :mod:`sklearn.calibration`
 ..........................
 
-- |Fix| Fixed a bug that made `calibration.CalibratedClassifierCV` fail when
+- |Fix| Fixed a bug that made :class:`calibration.CalibratedClassifierCV` fail when
   given a `sample_weight` parameter of type `list` (in the case where
   `sample_weights` are not supported by the wrapped estimator). :pr:`13575`
   by :user:`William de Vazelhes <wdevazelhes>`.
@@ -76,6 +76,15 @@ Changelog
   neighbors graph as input. :issue:`10482` by `Tom Dupre la Tour`_ and
   :user:`Kumar Ashutosh <thechargedneutron>`.
 
+- |Enhancement| :class:`cluster.SpectralClustering` now accepts a ``n_components``
+  parameter. This parameter extends `SpectralClustering` class functionality to
+  match :meth:`cluster.spectral_clustering`.
+  :pr:`13726` by :user:`Shuzhe Xiao <fdas3213>`.
+
+- |Fix| Fixed a bug where :class:`cluster.KMeans` produced inconsistent results
+  between `n_jobs=1` and `n_jobs>1` due to the handling of the random state.
+  :pr:`9288` by :user:`Bryan Yang <bryanyang0528>`.
+
 :mod:`sklearn.compose`
 ......................
 
@@ -88,18 +97,6 @@ Changelog
   pass `**fit_params` to the underlying regressor.
   :pr:`14890` by :user:`Miguel Cabrera <mfcabrera>`.
 
-:mod:`sklearn.cluster`
-......................
-
-- |Enhancement| :class:`cluster.SpectralClustering` now accepts a ``n_components``
-  parameter. This parameter extends `SpectralClustering` class functionality to
-  match `spectral_clustering`.
-  :pr:`13726` by :user:`Shuzhe Xiao <fdas3213>`.
-
-- |Fix| Fixed a bug where :class:`cluster.KMeans` produced inconsistent results
-  between `n_jobs=1` and `n_jobs>1` due to the handling of the random state.
-  :pr:`9288` by :user:`Bryan Yang <bryanyang0528>`.
-
 :mod:`sklearn.cross_decomposition`
 ..................................
 
@@ -119,7 +116,7 @@ Changelog
   . :pr:`14259` by :user:`Sourav Singh <souravsingh>`.
 
 - |Enhancement| :func:`datasets.make_classification` now accepts array-like
-   `weights` parameter, i.e. list or numpy.array, instead of list only.
+  `weights` parameter, i.e. list or numpy.array, instead of list only.
   :pr:`14764` by :user:`Cat Chenal <CatChenal>`.
 
 - |Fix| Fixed a bug in :func:`datasets.fetch_openml`, which failed to load
@@ -131,7 +128,8 @@ Changelog
 
 - |Enhancement| :func:`decomposition.dict_learning()` and
   :func:`decomposition.dict_learning_online()` now accept `method_max_iter` and
-  pass it to `sparse_encode`. :issue:`12650` by `Adrin Jalali`_.
+  pass it to :meth:`decomposition.sparse_encode`.
+  :issue:`12650` by `Adrin Jalali`_.
 
 - |Enhancement| :class:`decomposition.SparseCoder`,
   :class:`decomposition.DictionaryLearning`, and
@@ -146,8 +144,8 @@ Changelog
   :pr:`13960` by :user:`Scott Gigante <scottgigante>`.
 
 - |Fix| :func:`decomposition.sparse_encode()` now passes the `max_iter` to the
-  underlying `LassoLars` when `algorithm='lasso_lars'`. :issue:`12650` by
-  `Adrin Jalali`_.
+  underlying :class:`linear_model.LassoLars` when `algorithm='lasso_lars'`.
+  :issue:`12650` by `Adrin Jalali`_.
 
 :mod:`sklearn.dummy`
 ....................
@@ -224,13 +222,13 @@ Changelog
 
 - |Enhancement| Addition of ``max_samples`` argument allows limiting
   size of bootstrap samples to be less than size of dataset. Added to
-  :class:`ensemble.forest.ForestClassifier`,
-  :class:`ensemble.forest.ForestRegressor`,
-  :class:`ensemble.forest.RandomForestClassifier`,
-  :class:`ensemble.forest.RandomForestRegressor`,
-  :class:`ensemble.forest.ExtraTreesClassifier`,
-  :class:`ensemble.forest.ExtraTreesRegressor`,
-  :class:`ensemble.forest.RandomTreesEmbedding`. :pr:`14682` by
+  :class:`ensemble.ForestClassifier`,
+  :class:`ensemble.ForestRegressor`,
+  :class:`ensemble.RandomForestClassifier`,
+  :class:`ensemble.RandomForestRegressor`,
+  :class:`ensemble.ExtraTreesClassifier`,
+  :class:`ensemble.ExtraTreesRegressor`,
+  :class:`ensemble.RandomTreesEmbedding`. :pr:`14682` by
   :user:`Matt Hancock <notmatthancock>` and
   :pr:`5963` by :user:`Pablo Duboue <DrDub>`.
 
@@ -244,12 +242,12 @@ Changelog
   :class:`feature_extraction.text.TfidfVectorizer`.
   :pr:`14602` by :user:`Gaurav Chawla <getgaurav2>`.
 
-- |Fix| Functions created by build_preprocessor and build_analyzer of
+- |Fix| Functions created by ``build_preprocessor`` and ``build_analyzer`` of
   :class:`feature_extraction.text.VectorizerMixin` can now be pickled.
   :pr:`14430` by :user:`Dillon Niederhut <deniederhut>`.
 
 - |API| Deprecated unused `copy` param for
-  :meth: `feature_extraction.text.TfidfVectorizer.transform` it will be
+  :meth:`feature_extraction.text.TfidfVectorizer.transform` it will be
   removed in v0.24. :pr:`14520` by
   :user:`Guillem G. Subies <guillemgsubies>`.
 
@@ -270,8 +268,8 @@ Changelog
   the kernel attribute is modified, but may result in a performance improvement.
   :pr:`14378` by :user:`Masashi Shibata <c-bata>`.
 
-- |API| From version 0.24 :meth:`Kernel.get_params` will raise an
-  AttributeError rather than return None for parameters that are in the
+- |API| From version 0.24 :meth:`gaussian_process.kernels.Kernel.get_params` will raise an
+  ``AttributeError`` rather than return ``None`` for parameters that are in the
   estimator's constructor but not stored as attributes on the instance.
   :pr:`14464` by `Joel Nothman`_.
 
@@ -406,6 +404,10 @@ Changelog
   precomputed distance matrix contains non-zero diagonal entries.
   :pr:`12258` by :user:`Stephen Tierney <sjtrny>`.
 
+- |API| ``scoring="neg_brier_score"`` should be used instead of
+  ``scoring="brier_score_loss"`` which is now deprecated.
+  :pr:`14898` by :user:`Stefan Matcovici <stefan-matcovici>`.
+
 :mod:`sklearn.model_selection`
 ..............................
 
@@ -490,7 +492,7 @@ Changelog
   performance improvement. :pr:`13987` by `Roman Yurchak`_.
 
 - |Fix| KernelCenterer now throws error when fit on non-square
-  class:`preprocessing.KernelCenterer`
+  :class:`preprocessing.KernelCenterer`
   :pr:`14336` by :user:`Gregory Dexter <gdex1>`.
 
 :mod:`sklearn.svm`
@@ -552,7 +554,7 @@ Changelog
   index array-like across rows and columns. The column indexing can be done on
   NumPy array, SciPy sparse matrix, and Pandas DataFrame. An additional
   refactoring was done.
-  :pr:`14035` and :pr:`14475` by `Guillaume Lemaitre <glemaitre>`.
+  :pr:`14035` and :pr:`14475` by :user:`Guillaume Lemaitre <glemaitre>`.
 
 - |Enhancement| :func:`utils.extmath.safe_sparse_dot` works between 3D+ ndarray
   and sparse matrix.
@@ -562,13 +564,6 @@ Changelog
   NaN to integer.
   :pr:`14872` by `Roman Yurchak`_.
 
-:mod:`sklearn.metrics`
-..................................
-
-- |API| scoring="neg_brier_score" should be used instead of
-  scoring="brier_score_loss" which is now deprecated.
-  :pr:`14898` by :user:`Stefan Matcovici <stefan-matcovici>`.
-
 Miscellaneous
 .............
 
@@ -595,11 +590,11 @@ These changes mostly affect library developers.
   :pr:`13875` by `Trevor Stephens`_.
 
 - `requires_positive_X` estimator tag (for models that require
-  X to be non-negative) is now used by `check_estimator` to make sure
-  a proper error message is raised if X contains some negative entries.
+  X to be non-negative) is now used by :meth:`utils.estimator_checks.check_estimator`
+  to make sure a proper error message is raised if X contains some negative entries.
   :pr:`14680` by :user:`Alex Gramfort <agramfort>`.
 
 - Added check that pairwise estimators raise error on non-square data
   :pr:`14336` by :user:`Gregory Dexter <gdex1>`.
 
-- |Fix| Added check_transformer_data_not_an_array to checks where missing
+- |Fix| Added ``check_transformer_data_not_an_array`` to checks where missing