FIX IndexError due to imprecision in KMeans++ (scikit-learn#11756)

Author: jnothman

sklearn/cluster/k_means_.py

@@ -107,6 +107,9 @@ def _k_init(X, n_clusters, x_squared_norms, random_state, n_local_trials=None):
         rand_vals = random_state.random_sample(n_local_trials) * current_pot
         candidate_ids = np.searchsorted(stable_cumsum(closest_dist_sq),
                                         rand_vals)
+        # XXX: numerical imprecision can result in a candidate_id out of range
+        np.clip(candidate_ids, None, closest_dist_sq.size - 1,
+                out=candidate_ids)
 
         # Compute distances to center candidates
         distance_to_candidates = euclidean_distances(