MRG: Speed up euclidean_distances with Cython

sklearn/cluster/k_means_.py

@@ -94,7 +94,7 @@ def _k_init(X, n_clusters, n_local_trials=None, random_state=None,
     if x_squared_norms is None:
         x_squared_norms = _squared_norms(X)
     closest_dist_sq = euclidean_distances(
-        centers[0], X, Y_norm_squared=x_squared_norms, squared=True)
+        centers[0], X, Y_norm_precomputed=x_squared_norms, squared=True)
     current_pot = closest_dist_sq.sum()
 
     # Pick the remaining n_clusters-1 points
@@ -106,7 +106,8 @@ def _k_init(X, n_clusters, n_local_trials=None, random_state=None,
 
         # Compute distances to center candidates
         distance_to_candidates = euclidean_distances(
-            X[candidate_ids], X, Y_norm_squared=x_squared_norms, squared=True)
+            X[candidate_ids], X, Y_norm_precomputed=x_squared_norms,
+            squared=True)
 
         # Decide which candidate is the best
         best_candidate = None
@@ -415,7 +416,8 @@ def _squared_norms(X):
 def _labels_inertia_precompute_dense(X, x_squared_norms, centers):
     n_samples = X.shape[0]
     k = centers.shape[0]
-    distances = euclidean_distances(centers, X, x_squared_norms,
+    distances = euclidean_distances(centers, X,
+                                    Y_norm_precomputed=x_squared_norms,
                                     squared=True)
     labels = np.empty(n_samples, dtype=np.int)
     labels.fill(-1)

sklearn/manifold/mds.py

@@ -87,9 +87,10 @@ def _smacof_single(similarities, metric=True, n_components=2, init=None,
         X = init
 
     old_stress = None
+    dis = np.empty((n_samples, n_samples), dtype=np.float64)
     for it in range(max_iter):
         # Compute distance and monotonic regression
-        dis = euclidean_distances(X)
+        euclidean_distances(X, out=dis)
 
         if metric:
             disparities = similarities
@@ -120,16 +121,16 @@ def _smacof_single(similarities, metric=True, n_components=2, init=None,
         B[np.arange(len(B)), np.arange(len(B))] += ratio.sum(axis=1)
         X = 1. / n_samples * np.dot(B, X)
 
-        dis = np.sqrt((X ** 2).sum(axis=1)).sum()
+        dis_sum = np.sqrt((X ** 2).sum(axis=1)).sum()
         if verbose == 2:
             print 'it: %d, stress %s' % (it, stress)
         if old_stress is not None:
-            if(old_stress - stress / dis) < eps:
+            if(old_stress - stress / dis_sum) < eps:
                 if verbose:
                     print 'breaking at iteration %d with stress %s' % (it,
                                                                        stress)
                 break
-        old_stress = stress / dis
+        old_stress = stress / dis_sum
 
     return X, stress