[MRG + 1] enable metric = 'cosine' for tsne computation

sklearn/manifold/t_sne.py

@@ -711,10 +711,7 @@ def _fit(self, X, skip_num_points=0):
                 print("[t-SNE] Computing {} nearest neighbors...".format(k))
 
             # Find the nearest neighbors for every point
-            neighbors_method = 'ball_tree'
-            if (self.metric == 'precomputed'):
-                neighbors_method = 'brute'
-            knn = NearestNeighbors(algorithm=neighbors_method, n_neighbors=k,
+            knn = NearestNeighbors(algorithm='auto', n_neighbors=k,
                                    metric=self.metric)
             t0 = time()
             knn.fit(X)

sklearn/manifold/tests/test_t_sne.py

@@ -30,6 +30,8 @@
 from scipy.spatial.distance import pdist
 from scipy.spatial.distance import squareform
 from sklearn.metrics.pairwise import pairwise_distances
+from sklearn.metrics.pairwise import manhattan_distances
+from sklearn.metrics.pairwise import cosine_distances
 
 
 x = np.linspace(0, 1, 10)
@@ -764,3 +766,21 @@ def test_bh_match_exact():
     assert n_iter['exact'] == n_iter['barnes_hut']
     assert_array_almost_equal(X_embeddeds['exact'], X_embeddeds['barnes_hut'],
                               decimal=3)
+
+
+def test_tsne_with_different_distance_metrics():
+    """Make sure that TSNE works for different distance metrics"""
+    random_state = check_random_state(0)
+    n_components_original = 3
+    n_components_embedding = 2
+    X = random_state.randn(50, n_components_original).astype(np.float32)
+    metrics = ['manhattan', 'cosine']
+    dist_funcs = [manhattan_distances, cosine_distances]
+    for metric, dist_func in zip(metrics, dist_funcs):
+        tsne_1 = TSNE(metric=metric, n_components=n_components_embedding,
+                      random_state=0).fit_transform(X)
+        tsne_2 = TSNE(metric='precomputed',
+                      n_components=n_components_embedding,
+                      random_state=0).fit_transform(dist_func(X))
+        t = trustworthiness(tsne_1, tsne_2, n_neighbors=1)
+        assert_greater(t, 0.9)