def test_kmeans(self):
table = Orange.data.Table('iris')
cr = ClusteringEvaluation(table, learners=[KMeans(n_clusters=2),
KMeans(n_clusters=3),
KMeans(n_clusters=5)], k=3)
expected = [0.68081362, 0.55259194, 0.48851755]
np.testing.assert_almost_equal(Silhouette(cr), expected, decimal=2)
expected = [0.51936073, 0.74837231, 0.59178896]
np.testing.assert_almost_equal(AdjustedMutualInfoScore(cr),
expected, decimal=2)
def test_deprecated_silhouette(self):
with warnings.catch_warnings(record=True) as w:
KMeans(compute_silhouette_score=True)
assert len(w) == 1
assert issubclass(w[-1].category, DeprecationWarning)
with warnings.catch_warnings(record=True) as w:
KMeans(compute_silhouette_score=False)
assert len(w) == 1
assert issubclass(w[-1].category, DeprecationWarning)
def test_kmeans(self):
kmeans = KMeans(n_clusters=2)
c = kmeans(self.iris)
X = self.iris.X[:20]
p = c(X)
# First 20 iris belong to one cluster
assert len(set(p.ravel())) == 1
def test_kmeans_parameters(self):
kmeans = KMeans(n_clusters=10,
max_iter=10,
random_state=42,
tol=0.001,
init='random')
c = kmeans(self.iris)
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))
def test_kmeans_parameters(self):
kmeans = KMeans(n_clusters=10,
max_iter=10,
random_state=42,
tol=0.001,
init='random',
compute_silhouette_score=True)
c = kmeans(self.iris)
def test_kmeans(self):
table = Orange.data.Table('iris')
kmeans = KMeans(n_clusters=2)
c = kmeans(table)
X = table.X[:20]
p = c(X)
# First 20 iris belong to one cluster
assert len(set(p.ravel())) == 1
def test_kmeans(self):
table = Orange.data.Table('iris')
cr = ClusteringEvaluation(k=3)(table, learners=[KMeans(n_clusters=2),
KMeans(n_clusters=3),
KMeans(n_clusters=5)])
expected = [0.68081362, 0.55259194, 0.48851755]
np.testing.assert_almost_equal(Silhouette(cr), expected, decimal=2)
expected = [0.65383807, 0.75511917, 0.68721092]
np.testing.assert_almost_equal(AdjustedMutualInfoScore(cr),
expected, decimal=2)
self.assertIsNone(cr.models)
cr = ClusteringEvaluation(k=3, store_models=True)(
table, learners=[KMeans(n_clusters=2)])
self.assertEqual(cr.models.shape, (3, 1))
self.assertTrue(all(isinstance(m, KMeansModel)
for m in cr.models.flatten()))
def test_kmeans_parameters(self):
table = Orange.data.Table('iris')
kmeans = KMeans(n_clusters=10,
max_iter=10,
random_state=42,
tol=0.001,
init='random')
c = kmeans(table)
def test_kmeans_parameters(self):
kmeans = KMeans(n_clusters=10,
max_iter=10,
random_state=42,
tol=0.001,
init='random')
c = kmeans(self.iris)
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
def test_predict_table(self):
kmeans = KMeans()
c = kmeans(self.iris)
table = self.iris[:20]
p = c(table)
def test_predict_numpy(self):
table = Orange.data.Table('iris')
kmeans = KMeans()
c = kmeans(table)
X = table.X[::20]
p = c(X)
def test_predict_table(self):
table = Orange.data.Table('iris')
kmeans = KMeans()
c = kmeans(table)
table = table[:20]
p = c(table)
def test_predict_single_instance(self):
table = Orange.data.Table('iris')
kmeans = KMeans()
c = kmeans(table)
inst = table[0]
p = c(inst)
class TestKMeans(unittest.TestCase):
def setUp(self):
self.kmeans = KMeans(n_clusters=2)
self.iris = Orange.data.Table('iris')
def test_kmeans(self):
c = self.kmeans(self.iris)
# First 20 iris belong to one cluster
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
self.assertEqual(1, len(set(c[:20].ravel())))
def test_kmeans_parameters(self):
kmeans = KMeans(n_clusters=10,
max_iter=10,
random_state=42,
tol=0.001,
init='random')
c = kmeans(self.iris)
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
def test_predict_table(self):
c = self.kmeans(self.iris)
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
def test_predict_numpy(self):
c = self.kmeans.fit(self.iris.X)
self.assertEqual(KMeansModel, type(c))
self.assertEqual(np.ndarray, type(c.labels))
self.assertEqual(len(self.iris), len(c.labels))
def test_predict_sparse_csc(self):
self.iris.X = csc_matrix(self.iris.X[::20])
c = self.kmeans(self.iris)
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
def test_predict_spares_csr(self):
self.iris.X = csr_matrix(self.iris.X[::20])
c = self.kmeans(self.iris)
self.assertEqual(np.ndarray, type(c))
self.assertEqual(len(self.iris), len(c))
def test_model(self):
c = self.kmeans.get_model(self.iris)
self.assertEqual(KMeansModel, type(c))
self.assertEqual(len(self.iris), len(c.labels))
c1 = c(self.iris)
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels, c1)
def test_model_np(self):
"""
Test with numpy array as an input in model.
"""
c = self.kmeans.get_model(self.iris)
c1 = c(self.iris.X)
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels, c1)
def test_model_sparse_csc(self):
"""
Test with sparse array as an input in model.
"""
c = self.kmeans.get_model(self.iris)
c1 = c(csc_matrix(self.iris.X))
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels, c1)
def test_model_sparse_csr(self):
"""
Test with sparse array as an input in model.
"""
c = self.kmeans.get_model(self.iris)
c1 = c(csr_matrix(self.iris.X))
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels, c1)
def test_model_instance(self):
"""
Test with instance as an input in model.
"""
c = self.kmeans.get_model(self.iris)
c1 = c(self.iris[0])
# prediction of the model must be same since data are same
self.assertEqual(c1, c.labels[0])
def test_model_list(self):
"""
Test with list as an input in model.
"""
c = self.kmeans.get_model(self.iris)
c1 = c(self.iris.X.tolist())
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels, c1)
# example with a list of only one data item
c1 = c(self.iris.X.tolist()[0])
# prediction of the model must be same since data are same
np.testing.assert_array_almost_equal(c.labels[0], c1)
def test_model_bad_datatype(self):
"""
Check model with data-type that is not supported.
"""
c = self.kmeans.get_model(self.iris)
self.assertRaises(TypeError, c, 10)
def test_model_data_table_domain(self):
"""
Check model with data-type that is not supported.
"""
# ok domain
data = Table(
Domain(
list(self.iris.domain.attributes) + [ContinuousVariable("a")]),
np.concatenate((self.iris.X, np.ones((len(self.iris), 1))),
axis=1))
c = self.kmeans.get_model(self.iris)
res = c(data)
np.testing.assert_array_almost_equal(c.labels, res)
# totally different domain - should fail
self.assertRaises(DomainTransformationError, c, Table("housing"))
def test_deprecated_silhouette(self):
with warnings.catch_warnings(record=True) as w:
KMeans(compute_silhouette_score=True)
assert len(w) == 1
assert issubclass(w[-1].category, DeprecationWarning)
with warnings.catch_warnings(record=True) as w:
KMeans(compute_silhouette_score=False)
assert len(w) == 1
assert issubclass(w[-1].category, DeprecationWarning)
def setUp(self):
self.kmeans = KMeans(n_clusters=2)
self.iris = Orange.data.Table('iris')
def test_predict_sparse(self):
kmeans = KMeans()
c = kmeans(self.iris)
X = csc_matrix(self.iris.X[::20])
p = c(X)
def test_predict_numpy(self):
kmeans = KMeans()
c = kmeans(self.iris)
X = self.iris.X[::20]
p = c(X)
def test_predict_single_instance(self):
kmeans = KMeans()
c = kmeans(self.iris)
inst = self.iris[0]
p = c(inst)