DOC Various documentation improvements (scikit-learn#21764)

Co-authored-by: Guillaume Lemaitre <[email protected]>

Author: mandjevant

sklearn/kernel_ridge.py

@@ -52,7 +52,7 @@ class KernelRidge(MultiOutputMixin, RegressorMixin, BaseEstimator):
         Kernel mapping used internally. This parameter is directly passed to
         :class:`~sklearn.metrics.pairwise.pairwise_kernel`.
         If `kernel` is a string, it must be one of the metrics
-        in `pairwise.PAIRWISE_KERNEL_FUNCTIONS`.
+        in `pairwise.PAIRWISE_KERNEL_FUNCTIONS` or "precomputed".
         If `kernel` is "precomputed", X is assumed to be a kernel matrix.
         Alternatively, if `kernel` is a callable function, it is called on
         each pair of instances (rows) and the resulting value recorded. The

sklearn/mixture/_gaussian_mixture.py

@@ -473,14 +473,10 @@ class GaussianMixture(BaseMixture):
         String describing the type of covariance parameters to use.
         Must be one of:
 
-        'full'
-            each component has its own general covariance matrix
-        'tied'
-            all components share the same general covariance matrix
-        'diag'
-            each component has its own diagonal covariance matrix
-        'spherical'
-            each component has its own single variance
+        - 'full': each component has its own general covariance matrix.
+        - 'tied': all components share the same general covariance matrix.
+        - 'diag': each component has its own diagonal covariance matrix.
+        - 'spherical': each component has its own single variance.
 
     tol : float, default=1e-3
         The convergence threshold. EM iterations will stop when the

sklearn/multiclass.py

@@ -932,7 +932,7 @@ class OutputCodeClassifier(MetaEstimatorMixin, ClassifierMixin, BaseEstimator):
         An estimator object implementing :term:`fit` and one of
         :term:`decision_function` or :term:`predict_proba`.
 
-    code_size : float
+    code_size : float, default=1.5
         Percentage of the number of classes to be used to create the code book.
         A number between 0 and 1 will require fewer classifiers than
         one-vs-the-rest. A number greater than 1 will require more classifiers

sklearn/neighbors/_nearest_centroid.py

@@ -30,7 +30,7 @@ class NearestCentroid(ClassifierMixin, BaseEstimator):
 
     Parameters
     ----------
-    metric : str or callable
+    metric : str or callable, default="euclidian"
         The metric to use when calculating distance between instances in a
         feature array. If metric is a string or callable, it must be one of
         the options allowed by

sklearn/preprocessing/_discretization.py

@@ -37,27 +37,21 @@ class KBinsDiscretizer(TransformerMixin, BaseEstimator):
     encode : {'onehot', 'onehot-dense', 'ordinal'}, default='onehot'
         Method used to encode the transformed result.
 
-        onehot
-            Encode the transformed result with one-hot encoding
-            and return a sparse matrix. Ignored features are always
-            stacked to the right.
-        onehot-dense
-            Encode the transformed result with one-hot encoding
-            and return a dense array. Ignored features are always
-            stacked to the right.
-        ordinal
-            Return the bin identifier encoded as an integer value.
+        - 'onehot': Encode the transformed result with one-hot encoding
+          and return a sparse matrix. Ignored features are always
+          stacked to the right.
+        - 'onehot-dense': Encode the transformed result with one-hot encoding
+          and return a dense array. Ignored features are always
+          stacked to the right.
+        - 'ordinal': Return the bin identifier encoded as an integer value.
 
     strategy : {'uniform', 'quantile', 'kmeans'}, default='quantile'
         Strategy used to define the widths of the bins.
 
-        uniform
-            All bins in each feature have identical widths.
-        quantile
-            All bins in each feature have the same number of points.
-        kmeans
-            Values in each bin have the same nearest center of a 1D k-means
-            cluster.
+        - 'uniform': All bins in each feature have identical widths.
+        - 'quantile': All bins in each feature have the same number of points.
+        - 'kmeans': Values in each bin have the same nearest center of a 1D
+          k-means cluster.
 
     dtype : {np.float32, np.float64}, default=None
         The desired data-type for the output. If None, output dtype is