BUG: fix ward tests

Author: GaelVaroquaux

sklearn/cluster/hierarchical.py

@@ -72,9 +72,13 @@ def ward_tree(X, connectivity=None, n_components=None, copy=True,
         X = np.reshape(X, (-1, 1))
 
     if connectivity is None:
+        if n_clusters is not None:
+            raise ValueError('Early stopping is implemented only for '
+                             'structured Ward clustering (i.e. with '
+                             'explicit connectivity.')
         out = hierarchy.ward(X)
         children_ = out[:, :2].astype(np.int)
-        return children_, 1, n_samples
+        return children_, 1, n_samples, None
 
     # Compute the number of nodes
     if n_components is None:
@@ -331,6 +335,8 @@ def fit(self, X):
 
         n_samples = len(X)
         compute_full_tree = self.compute_full_tree
+        if self.connectivity is None:
+            compute_full_tree = None
         if compute_full_tree == 'auto':
             # Early stopping is likely to give a speed up only for
             # a large number of clusters. The actual threshold

sklearn/cluster/tests/test_hierarchical.py

@@ -21,7 +21,7 @@ def test_structured_ward_tree():
     mask = np.ones([10, 10], dtype=np.bool)
     X = rnd.randn(50, 100)
     connectivity = grid_to_graph(*mask.shape)
-    children, n_components, n_leaves = ward_tree(X.T, connectivity)
+    children, n_components, n_leaves, parent = ward_tree(X.T, connectivity)
     n_nodes = 2 * X.shape[1] - 1
     assert_true(len(children) + n_leaves == n_nodes)
 
@@ -32,7 +32,7 @@ def test_unstructured_ward_tree():
     """
     rnd = np.random.RandomState(0)
     X = rnd.randn(50, 100)
-    children, n_nodes, n_leaves = ward_tree(X.T)
+    children, n_nodes, n_leaves, parent = ward_tree(X.T)
     n_nodes = 2 * X.shape[1] - 1
     assert_true(len(children) + n_leaves == n_nodes)
 
@@ -45,7 +45,7 @@ def test_height_ward_tree():
     mask = np.ones([10, 10], dtype=np.bool)
     X = rnd.randn(50, 100)
     connectivity = grid_to_graph(*mask.shape)
-    children, n_nodes, n_leaves = ward_tree(X.T, connectivity)
+    children, n_nodes, n_leaves, parent = ward_tree(X.T, connectivity)
     n_nodes = 2 * X.shape[1] - 1
     assert_true(len(children) + n_leaves == n_nodes)
 
@@ -109,7 +109,7 @@ def test_scikit_vs_scipy():
         out = hierarchy.ward(X)
 
         children_ = out[:, :2].astype(np.int)
-        children, _, n_leaves = ward_tree(X, connectivity)
+        children, _, n_leaves, _ = ward_tree(X, connectivity)
 
         cut = _hc_cut(k, children, n_leaves)
         cut_ = _hc_cut(k, children_, n_leaves)