Fix empty clusters not correctly relocated when using sample_weight(#13486)

jeremiedbb · NicolasHug · commit e405505877c8 · 2019-04-12T08:54:17.000-04:00
diff --git a/doc/whats_new/v0.21.rst b/doc/whats_new/v0.21.rst
@@ -90,6 +90,10 @@ Support for Python 3.4 and below has been officially dropped.
   ``n_connected_components_``.
   :issue:`13427` by :user:`Stephane Couvreur <scouvreur>`.
 
+- |Fix| Fixed a bug in :class:`KMeans` where empty clusters weren't correctly
+  relocated when using sample weights. :issue:`13486`
+  by :user:`Jérémie du Boisberranger <jeremiedbb>`.
+
 :mod:`sklearn.datasets`
 .......................
 
diff --git a/sklearn/cluster/_k_means.pyx b/sklearn/cluster/_k_means.pyx
@@ -309,7 +309,7 @@ def _centers_dense(np.ndarray[floating, ndim=2] X,
         for i, cluster_id in enumerate(empty_clusters):
             # XXX two relocated clusters could be close to each other
             far_index = far_from_centers[i]
-            new_center = X[far_index]
+            new_center = X[far_index] * sample_weight[far_index]
             centers[cluster_id] = new_center
             weight_in_cluster[cluster_id] = sample_weight[far_index]
 
diff --git a/sklearn/cluster/tests/test_k_means.py b/sklearn/cluster/tests/test_k_means.py
@@ -9,6 +9,7 @@
 from sklearn.utils.testing import assert_equal
 from sklearn.utils.testing import assert_array_equal
 from sklearn.utils.testing import assert_array_almost_equal
+from sklearn.utils.testing import assert_allclose
 from sklearn.utils.testing import assert_almost_equal
 from sklearn.utils.testing import assert_raises
 from sklearn.utils.testing import assert_raises_regex
@@ -922,3 +923,17 @@ def test_iter_attribute():
     estimator = KMeans(algorithm="elkan", max_iter=1)
     estimator.fit(np.random.rand(10, 10))
     assert estimator.n_iter_ == 1
+
+
+def test_k_means_empty_cluster_relocated():
+    # check that empty clusters are correctly relocated when using sample
+    # weights (#13486)
+    X = np.array([[-1], [1]])
+    sample_weight = [1.9, 0.1]
+    init = np.array([[-1], [10]])
+
+    km = KMeans(n_clusters=2, init=init, n_init=1)
+    km.fit(X, sample_weight=sample_weight)
+
+    assert len(set(km.labels_)) == 2
+    assert_allclose(km.cluster_centers_, [[-1], [1]])
