[MRG] FIX Avoid default mutable argument in constructor of AgglomerativeClustering (#8153)

glemaitre · jnothman · commit 0b02125b1393 · 2017-01-05T22:21:31.000+11:00
diff --git a/sklearn/cluster/hierarchical.py b/sklearn/cluster/hierarchical.py
@@ -660,7 +660,7 @@ class AgglomerativeClustering(BaseEstimator, ClusterMixin):
     """
 
     def __init__(self, n_clusters=2, affinity="euclidean",
-                 memory=Memory(cachedir=None, verbose=0),
+                 memory=None,
                  connectivity=None, compute_full_tree='auto',
                  linkage='ward', pooling_func=np.mean):
         self.n_clusters = n_clusters
@@ -685,8 +685,13 @@ def fit(self, X, y=None):
         """
         X = check_array(X, ensure_min_samples=2, estimator=self)
         memory = self.memory
-        if isinstance(memory, six.string_types):
+        if memory is None:
+            memory = Memory(cachedir=None, verbose=0)
+        elif isinstance(memory, six.string_types):
             memory = Memory(cachedir=memory, verbose=0)
+        elif not isinstance(memory, Memory):
+            raise ValueError('`memory` has to be a `str` or a `joblib.Memory`'
+                             ' instance')
 
         if self.n_clusters <= 0:
             raise ValueError("n_clusters should be an integer greater than 0."
diff --git a/sklearn/cluster/tests/test_hierarchical.py b/sklearn/cluster/tests/test_hierarchical.py
@@ -115,6 +115,17 @@ def test_height_linkage_tree():
         assert_true(len(children) + n_leaves == n_nodes)
 
 
+def test_agglomerative_clustering_wrong_arg_memory():
+    # Test either if an error is raised when memory is not
+    # either a str or a joblib.Memory instance
+    rng = np.random.RandomState(0)
+    n_samples = 100
+    X = rng.randn(n_samples, 50)
+    memory = 5
+    clustering = AgglomerativeClustering(memory=memory)
+    assert_raises(ValueError, clustering.fit, X)
+
+
 def test_agglomerative_clustering():
     # Check that we obtain the correct number of clusters with
     # agglomerative clustering.
