Clustering: Fixed tests

Author: PrimozGodec

Orange/tests/test_clustering_dbscan.py

@@ -28,4 +28,4 @@ def test_predict_numpy(self):
         dbscan = DBSCAN()
         c = dbscan(self.iris)
         X = self.iris.X[::20]
-        p = c(X)
+        p = c.predict(X)

Orange/tests/test_clustering_kmeans.py

@@ -18,7 +18,7 @@ def setUpClass(cls):
     def test_kmeans(self):
         kmeans = KMeans(n_clusters=2)
         c = kmeans(self.iris)
-        X = self.iris.X[:20]
+        X = self.iris[:20]
         p = c(X)
         # First 20 iris belong to one cluster
         assert len(set(p.ravel())) == 1
@@ -28,16 +28,9 @@ def test_kmeans_parameters(self):
                         max_iter=10,
                         random_state=42,
                         tol=0.001,
-                        init='random',
-                        compute_silhouette_score=True)
+                        init='random')
         c = kmeans(self.iris)
 
-    def test_predict_single_instance(self):
-        kmeans = KMeans()
-        c = kmeans(self.iris)
-        inst = self.iris[0]
-        p = c(inst)
-
     def test_predict_table(self):
         kmeans = KMeans()
         c = kmeans(self.iris)
@@ -48,18 +41,10 @@ def test_predict_numpy(self):
         kmeans = KMeans()
         c = kmeans(self.iris)
         X = self.iris.X[::20]
-        p = c(X)
+        p = c.predict(X)
 
     def test_predict_sparse(self):
         kmeans = KMeans()
         c = kmeans(self.iris)
-        X = csc_matrix(self.iris.X[::20])
-        p = c(X)
-
-    def test_silhouette_sparse(self):
-        """Test if silhouette gets calculated for sparse data"""
-        kmeans = KMeans(compute_silhouette_score=True)
-        sparse_iris = self.iris.copy()
-        sparse_iris.X = csc_matrix(sparse_iris.X)
-        c = kmeans(sparse_iris)
-        self.assertFalse(np.isnan(c.silhouette))
+        self.iris.X = csc_matrix(self.iris.X[::20])
+        p = c(self.iris)

Orange/tests/test_louvain.py

@@ -5,22 +5,17 @@
 import numpy as np
 
 from Orange.data import Table
-from Orange.clustering.louvain import Louvain
+from Orange.clustering.louvain import Louvain, LouvainModel
 
 
-class TestSVMLearner(unittest.TestCase):
+class TestLouvain(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
         cls.data = Table('iris')
         cls.louvain = Louvain()
 
     def test_orange_table(self):
-        self.assertIsNone(self.louvain.fit(self.data))
-        clusters = self.louvain.fit_predict(self.data)
-        self.assertIn(type(clusters), [list, np.ndarray])
-
-    def test_np_array(self):
-        data_np = self.data.X
-        self.assertIsNone(self.louvain.fit(data_np))
-        clusters = self.louvain.fit_predict(data_np)
+        louvain_model = self.louvain(self.data)
+        self.assertEqual(type(louvain_model), LouvainModel)
+        clusters = louvain_model(self.data)
         self.assertIn(type(clusters), [list, np.ndarray])

Orange/widgets/unsupervised/tests/test_owkmeans.py

@@ -5,6 +5,7 @@
 import numpy as np
 from AnyQt.QtCore import Qt
 from AnyQt.QtWidgets import QRadioButton
+from sklearn.metrics import silhouette_score
 
 import Orange.clustering
 from Orange.data import Table, Domain
@@ -199,24 +200,22 @@ def test_data_on_output(self):
 
     @patch("Orange.clustering.kmeans.KMeansModel.__call__")
     def test_centroids_on_output(self, km_call):
-        ret = km_call.return_value = Mock()
-        ret.X = np.array([0] * 50 + [1] * 100)
-        ret.silhouette_samples = np.arange(150) / 150
+        km_call.return_value = np.array([0] * 50 + [1] * 100).flatten()
 
         widget = self.widget
         widget.optimize_k = False
         widget.k = 4
         self.send_signal(widget.Inputs.data, self.iris)
         self.commit_and_wait()
 
-        widget.clusterings[4].silhouette_samples = np.arange(150) / 150
+        widget.samples_scores = lambda x: np.arctan(
+            np.arange(150) / 150) / np.pi + 0.5
         widget.send_data()
         out = self.get_output(widget.Outputs.centroids)
-        np.testing.assert_almost_equal(
-            out.metas,
-            [[0, np.mean(np.arctan(np.arange(50) / 150)) / np.pi + 0.5],
+        np.testing.assert_array_almost_equal(
+            np.array([[0, np.mean(np.arctan(np.arange(50) / 150)) / np.pi + 0.5],
              [1, np.mean(np.arctan(np.arange(50, 150) / 150)) / np.pi + 0.5],
-             [2, 0], [3, 0]])
+             [2, 0], [3, 0]]), out.metas.astype(float))
         self.assertEqual(out.name, "iris centroids")
 
     def test_centroids_domain_on_output(self):
@@ -262,12 +261,14 @@ def test_optimization_fails(self):
         self.KMeansFail.fail_on = {3, 5, 7}
         model = widget.table_view.model()
 
-        with patch.object(model, "set_scores", wraps=model.set_scores) as set_scores:
+        with patch.object(
+                model, "set_scores", wraps=model.set_scores) as set_scores:
             self.send_signal(self.widget.Inputs.data, self.iris, wait=5000)
             scores, start_k = set_scores.call_args[0]
             self.assertEqual(
                 scores,
-                [km if isinstance(km, str) else km.silhouette
+                [km if isinstance(km, str) else silhouette_score(
+                    self.iris.X, km(self.iris))
                  for km in (widget.clusterings[k] for k in range(3, 9))]
             )
             self.assertEqual(start_k, 3)
@@ -312,15 +313,14 @@ def test_run_fails(self):
         self.assertIsNotNone(self.get_output(self.widget.Outputs.annotated_data))
 
     def test_select_best_row(self):
-        class Cluster:
-            def __init__(self, n):
-                self.silhouette = n
-
         widget = self.widget
         widget.k_from, widget.k_to = 2, 6
-        widget.clusterings = {k: Cluster(5 - (k - 4) ** 2) for k in range(2, 7)}
+        widget.optimize_k = True
+        self.send_signal(self.widget.Inputs.data, Table("housing"), wait=5000)
+        self.commit_and_wait()
         widget.update_results()
-        self.assertEqual(widget.selected_row(), 2)
+        # for housing dataset best selection is 3 clusters, so row no. 1
+        self.assertEqual(widget.selected_row(), 1)
 
         widget.clusterings = {k: "error" for k in range(2, 7)}
         widget.update_results()
@@ -394,7 +394,9 @@ def test_silhouette_column(self):
         # Avoid randomness in the test
         random = np.random.RandomState(0)  # pylint: disable=no-member
         table = Table(random.rand(110, 2))
-        with patch("Orange.clustering.kmeans.SILHOUETTE_MAX_SAMPLES", 100):
+        with patch(
+                "Orange.widgets.unsupervised.owkmeans.SILHOUETTE_MAX_SAMPLES",
+                100):
             self.send_signal(self.widget.Inputs.data, table)
             outtable = self.get_output(widget.Outputs.annotated_data)
             outtable = outtable.get_column_view("Silhouette")[0]