move kmpp public next to kmpp private (#19666)

jeremiedbb · web-flow · commit 579e7de7f38f · 2021-03-12T16:08:36.000+01:00
diff --git a/sklearn/cluster/_kmeans.py b/sklearn/cluster/_kmeans.py
@@ -47,6 +47,99 @@
 ###############################################################################
 # Initialization heuristic
 
+def kmeans_plusplus(X, n_clusters, *, x_squared_norms=None,
+                    random_state=None, n_local_trials=None):
+    """Init n_clusters seeds according to k-means++
+
+    .. versionadded:: 0.24
+
+    Parameters
+    ----------
+    X : {array-like, sparse matrix} of shape (n_samples, n_features)
+        The data to pick seeds from.
+
+    n_clusters : int
+        The number of centroids to initialize
+
+    x_squared_norms : array-like of shape (n_samples,), default=None
+        Squared Euclidean norm of each data point.
+
+    random_state : int or RandomState instance, default=None
+        Determines random number generation for centroid initialization. Pass
+        an int for reproducible output across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    n_local_trials : int, default=None
+        The number of seeding trials for each center (except the first),
+        of which the one reducing inertia the most is greedily chosen.
+        Set to None to make the number of trials depend logarithmically
+        on the number of seeds (2+log(k)).
+
+    Returns
+    -------
+    centers : ndarray of shape (n_clusters, n_features)
+        The inital centers for k-means.
+
+    indices : ndarray of shape (n_clusters,)
+        The index location of the chosen centers in the data array X. For a
+        given index and center, X[index] = center.
+
+    Notes
+    -----
+    Selects initial cluster centers for k-mean clustering in a smart way
+    to speed up convergence. see: Arthur, D. and Vassilvitskii, S.
+    "k-means++: the advantages of careful seeding". ACM-SIAM symposium
+    on Discrete algorithms. 2007
+
+    Examples
+    --------
+
+    >>> from sklearn.cluster import kmeans_plusplus
+    >>> import numpy as np
+    >>> X = np.array([[1, 2], [1, 4], [1, 0],
+    ...               [10, 2], [10, 4], [10, 0]])
+    >>> centers, indices = kmeans_plusplus(X, n_clusters=2, random_state=0)
+    >>> centers
+    array([[10,  4],
+           [ 1,  0]])
+    >>> indices
+    array([4, 2])
+    """
+
+    # Check data
+    check_array(X, accept_sparse='csr',
+                dtype=[np.float64, np.float32])
+
+    if X.shape[0] < n_clusters:
+        raise ValueError(f"n_samples={X.shape[0]} should be >= "
+                         f"n_clusters={n_clusters}.")
+
+    # Check parameters
+    if x_squared_norms is None:
+        x_squared_norms = row_norms(X, squared=True)
+    else:
+        x_squared_norms = check_array(x_squared_norms,
+                                      dtype=X.dtype,
+                                      ensure_2d=False)
+
+    if x_squared_norms.shape[0] != X.shape[0]:
+        raise ValueError(
+            f"The length of x_squared_norms {x_squared_norms.shape[0]} should "
+            f"be equal to the length of n_samples {X.shape[0]}.")
+
+    if n_local_trials is not None and n_local_trials < 1:
+        raise ValueError(
+            f"n_local_trials is set to {n_local_trials} but should be an "
+            f"integer value greater than zero.")
+
+    random_state = check_random_state(random_state)
+
+    # Call private k-means++
+    centers, indices = _kmeans_plusplus(X, n_clusters, x_squared_norms,
+                                        random_state, n_local_trials)
+
+    return centers, indices
+
 
 def _kmeans_plusplus(X, n_clusters, x_squared_norms,
                      random_state, n_local_trials=None):
@@ -1924,97 +2017,3 @@ def _more_tags(self):
                 'zero sample_weight is not equivalent to removing samples',
             }
         }
-
-
-def kmeans_plusplus(X, n_clusters, *, x_squared_norms=None,
-                    random_state=None, n_local_trials=None):
-    """Init n_clusters seeds according to k-means++
-
-    .. versionadded:: 0.24
-
-    Parameters
-    ----------
-    X : {array-like, sparse matrix} of shape (n_samples, n_features)
-        The data to pick seeds from.
-
-    n_clusters : int
-        The number of centroids to initialize
-
-    x_squared_norms : array-like of shape (n_samples,), default=None
-        Squared Euclidean norm of each data point.
-
-    random_state : int or RandomState instance, default=None
-        Determines random number generation for centroid initialization. Pass
-        an int for reproducible output across multiple function calls.
-        See :term:`Glossary <random_state>`.
-
-    n_local_trials : int, default=None
-        The number of seeding trials for each center (except the first),
-        of which the one reducing inertia the most is greedily chosen.
-        Set to None to make the number of trials depend logarithmically
-        on the number of seeds (2+log(k)).
-
-    Returns
-    -------
-    centers : ndarray of shape (n_clusters, n_features)
-        The inital centers for k-means.
-
-    indices : ndarray of shape (n_clusters,)
-        The index location of the chosen centers in the data array X. For a
-        given index and center, X[index] = center.
-
-    Notes
-    -----
-    Selects initial cluster centers for k-mean clustering in a smart way
-    to speed up convergence. see: Arthur, D. and Vassilvitskii, S.
-    "k-means++: the advantages of careful seeding". ACM-SIAM symposium
-    on Discrete algorithms. 2007
-
-    Examples
-    --------
-
-    >>> from sklearn.cluster import kmeans_plusplus
-    >>> import numpy as np
-    >>> X = np.array([[1, 2], [1, 4], [1, 0],
-    ...               [10, 2], [10, 4], [10, 0]])
-    >>> centers, indices = kmeans_plusplus(X, n_clusters=2, random_state=0)
-    >>> centers
-    array([[10,  4],
-           [ 1,  0]])
-    >>> indices
-    array([4, 2])
-    """
-
-    # Check data
-    check_array(X, accept_sparse='csr',
-                dtype=[np.float64, np.float32])
-
-    if X.shape[0] < n_clusters:
-        raise ValueError(f"n_samples={X.shape[0]} should be >= "
-                         f"n_clusters={n_clusters}.")
-
-    # Check parameters
-    if x_squared_norms is None:
-        x_squared_norms = row_norms(X, squared=True)
-    else:
-        x_squared_norms = check_array(x_squared_norms,
-                                      dtype=X.dtype,
-                                      ensure_2d=False)
-
-    if x_squared_norms.shape[0] != X.shape[0]:
-        raise ValueError(
-            f"The length of x_squared_norms {x_squared_norms.shape[0]} should "
-            f"be equal to the length of n_samples {X.shape[0]}.")
-
-    if n_local_trials is not None and n_local_trials < 1:
-        raise ValueError(
-            f"n_local_trials is set to {n_local_trials} but should be an "
-            f"integer value greater than zero.")
-
-    random_state = check_random_state(random_state)
-
-    # Call private k-means++
-    centers, indices = _kmeans_plusplus(X, n_clusters, x_squared_norms,
-                                        random_state, n_local_trials)
-
-    return centers, indices
