[MRG] Error for cosine affinity when zero vectors present (#7943)

mthorrell · GaelVaroquaux · commit 3d997697fdd1 · 2019-06-21T11:05:20.000-04:00
* cosine affinity cannot be used when X contains zero vectors

* fixed issue with tabs spaces

* changed to np.any and created a test for this new ValueError

* use assert_raise_message and flipped order of if conditions

* fixed 0 row calculation
diff --git a/sklearn/cluster/hierarchical.py b/sklearn/cluster/hierarchical.py
@@ -432,6 +432,10 @@ def linkage_tree(X, connectivity=None, n_clusters=None, linkage='complete',
             'Unknown linkage option, linkage should be one '
             'of %s, but %s was given' % (linkage_choices.keys(), linkage))
 
+    if affinity == 'cosine' and np.any(~np.any(X, axis=1)):
+        raise ValueError(
+            'Cosine affinity cannot be used when X contains zero vectors')
+
     if connectivity is None:
         from scipy.cluster import hierarchy  # imports PIL
 
diff --git a/sklearn/cluster/tests/test_hierarchical.py b/sklearn/cluster/tests/test_hierarchical.py
@@ -128,6 +128,15 @@ def test_agglomerative_clustering_wrong_arg_memory():
     assert_raises(ValueError, clustering.fit, X)
 
 
+def test_zero_cosine_linkage_tree():
+    # Check that zero vectors in X produce an error when
+    # 'cosine' affinity is used
+    X = np.array([[0, 1],
+                  [0, 0]])
+    msg = 'Cosine affinity cannot be used when X contains zero vectors'
+    assert_raise_message(ValueError, msg, linkage_tree, X, affinity='cosine')
+
+
 def test_agglomerative_clustering():
     # Check that we obtain the correct number of clusters with
     # agglomerative clustering.
