Merge pull request #276 from spotify/angular-holes

fix issue with holes in the index and angular distance
spotify · Feb 5, 2018 · 505a747 · 505a747
2 parents 9c5370d + 420a3d7
commit 505a747
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/src/annoylib.h b/src/annoylib.h
@@ -218,6 +218,9 @@ inline void two_means(const vector<Node*>& nodes, int f, Random& random, bool co
     T di = ic * Distance::distance(p, nodes[k], f),
       dj = jc * Distance::distance(q, nodes[k], f);
     T norm = cosine ? get_norm(nodes[k]->v, f) : 1.0;
+    if (!(norm > T(0))) {
+      continue;
+    }
     if (di < dj) {
       for (int z = 0; z < f; z++)
 	p->v[z] = (p->v[z] * ic + nodes[k]->v[z] / norm) / (ic + 1);

diff --git a/test/accuracy_test.py b/test/accuracy_test.py
@@ -75,5 +75,8 @@ def _test_index(self, dataset, exp_accuracy):
     def test_glove_25(self):
         self._test_index('glove-25-angular', 69.00)
 
+    def test_nytimes_16(self):
+        self._test_index('nytimes-16-angular', 80.00)
+
     def test_fashion_mnist(self):
         self._test_index('fashion-mnist-784-euclidean', 90.00)