scikit-learn
diff --git a/‎sklearn/cluster/_k_means.py
+14-13 b/‎sklearn/cluster/_k_means.py
+14-13
@@ -654,11 +654,12 @@ class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
     Parameters
     ----------
 
-    n_clusters : int, optional, default: 8
+    n_clusters : int, default=8
         The number of clusters to form as well as the number of
         centroids t
10000
o generate.
 
-    init : {'k-means++', 'random' or an ndarray}
+    init : {'k-means++', 'random'} or ndarray of shape \
+            (n_clusters, n_features), default='k-means++'
         Method for initialization, defaults to 'k-means++':
 
         'k-means++' : selects initial cluster centers for k-mean
@@ -671,19 +672,19 @@ class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
         If an ndarray is passed, it should be of shape (n_clusters, n_features)
         and gives the initial centers.
 
-    n_init : int, default: 10
+    n_init : int, default=10
         Number of time the k-means algorithm will be run with different
         centroid seeds. The final results will be the best output of
         n_init consecutive runs in terms of inertia.
 
-    max_iter : int, default: 300
+    max_iter : int, default=300
         Maximum number of iterations of the k-means algorithm for a
         single run.
 
-    tol : float, default: 1e-4
+    tol : float, default=1e-4
         Relative tolerance with regards to inertia to declare convergence.
 
-    precompute_distances : {'auto', True, False}
+    precompute_distances : 'auto' or bool, default='auto'
         Precompute distances (faster but takes more memory).
 
         'auto' : do not precompute distances if n_samples * n_clusters > 12
@@ -694,15 +695,15 @@ class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
 
         False : never precompute distances.
 
-    verbose : int, default 0
+    verbose : int, default=0
         Verbosity mode.
-    random_state : int, RandomState instance or None (default)
+    random_state : int, RandomState instance, default=None
         Determines random number generation for centroid initialization. Use
         an int to make the randomness deterministic.
         See :term:`Glossary <random_state>`.
 
-    copy_x : bool, optional
+    copy_x : bool, default=True
         When pre-computing distances it is more numerically accurate to center
         the data first.  If copy_x is True (default), then the original data is
         not modified, ensuring X is C-contiguous.  If False, the original data
@@ -711,28 +712,28 @@ class KMeans(TransformerMixin, ClusterMixin, BaseEstimator):
         the data mean, in this case it will also not ensure that data is
         C-contiguous which may cause a significant slowdown.
 
-    n_jobs : int or None, optional (default=None)
+    n_jobs : int, default=None
         The number of jobs to use for the computation. This works by computing
         each of the n_init runs in parallel.
 
         ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
         ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
         for more details.
 
-    algorithm : "auto", "full" or "elkan", default="auto"
+    algorithm : {"auto", "full", "elkan"}, default="auto"
         K-means algorithm to use. The classical EM-style algorithm is "full".
         The "elkan" variation is more efficient by using the triangle
         inequality, but currently doesn't support sparse data. "auto" chooses
         "elkan" for dense data and "full" for sparse data.
 
     Attributes
     ----------
-    cluster_centers_ : array, [n_clusters, n_features]
+    cluster_centers_ : ndarray of shape (n_clusters, n_features)
         Coordinates of cluster centers. If the algorithm stops before fully
         converging (see ``tol`` and ``max_iter``), these will not be
         consistent with ``labels_``.
 
-    labels_ : array, shape (n_samples,)
+    labels_ : ndarray of shape (n_samples,)
         Labels of each point
 
     inertia_ : float