def clustering(self, sample_path, answer_path, amount, ccore):
attempts = 10
failures = ""
for _ in range(attempts):
data = read_sample(sample_path)
gmeans_instance = gmeans(data, amount, ccore).process()
reader = answer_reader(answer_path)
expected_length_clusters = sorted(reader.get_cluster_lengths())
clusters = gmeans_instance.get_clusters()
centers = gmeans_instance.get_centers()
wce = gmeans_instance.get_total_wce()
self.assertEqual(len(expected_length_clusters), len(centers))
if len(clusters) > 1:
self.assertGreater(wce, 0.0)
else:
self.assertGreaterEqual(wce, 0.0)
unique_indexes = set()
for cluster in clusters:
for index_point in cluster:
unique_indexes.add(index_point)
if len(data) != len(unique_indexes):
failures += "1. %d != %d\n" % (len(data), len(unique_indexes))
continue
expected_total_length = sum(expected_length_clusters)
actual_total_length = sum([len(cluster) for cluster in clusters])
if expected_total_length != actual_total_length:
failures += "2. %d != %d\n" % (expected_total_length,
actual_total_length)
continue
actual_length_clusters = sorted(
[len(cluster) for cluster in clusters])
if expected_length_clusters != actual_length_clusters:
failures += "3. %s != %s\n" % (str(expected_length_clusters),
str(actual_length_clusters))
continue
return
self.fail("Expected result is not obtained during %d attempts: %s\n" %
(attempts, failures))
def template_clustering(sample_path, k_init=1, ccore=True, **kwargs):
sample = read_sample(sample_path)
gmeans_instance = gmeans(sample, k_init, ccore, repeat=5).process()
clusters = gmeans_instance.get_clusters()
centers = gmeans_instance.get_centers()
visualize = kwargs.get('visualize', True)
if visualize:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(centers, None, marker='*', markersize=10)
visualizer.show()
return sample, clusters
def template_predict(self, path, amount, points, ccore):
metric = distance_metric(type_metric.EUCLIDEAN)
sample = read_sample(path)
gmeans_instance = gmeans(sample, amount, ccore).process()
centers = gmeans_instance.get_centers()
closest_clusters = gmeans_instance.predict(points)
self.assertEqual(len(points), len(closest_clusters))
for i in range(len(points)):
cluster_index = closest_clusters[i]
distance = metric(centers[cluster_index], points[i])
for center_index in range(len(centers)):
if center_index != cluster_index:
other_distance = metric(centers[center_index], points[i])
self.assertLessEqual(distance, other_distance)
def clustering(self, sample_path, answer, amount, ccore, **kwargs):
attempts = 10
failures = ""
k_max = kwargs.get('k_max', -1)
random_state = kwargs.get('random_state', None)
data = read_sample(sample_path)
if isinstance(answer, str):
reader = answer_reader(answer)
expected_length_clusters = sorted(reader.get_cluster_lengths())
amount_clusters = len(expected_length_clusters)
elif isinstance(answer, int):
expected_length_clusters = None
amount_clusters = answer
else:
expected_length_clusters = answer
amount_clusters = len(answer)
for _ in range(attempts):
gmeans_instance = gmeans(data,
amount,
ccore,
k_max=k_max,
random_state=random_state).process()
clusters = gmeans_instance.get_clusters()
centers = gmeans_instance.get_centers()
wce = gmeans_instance.get_total_wce()
self.assertEqual(amount_clusters, len(centers))
if len(clusters) > 1:
self.assertGreater(wce, 0.0)
else:
self.assertGreaterEqual(wce, 0.0)
if len(clusters) != amount_clusters:
failures += "1. %d != %d\n" % (len(clusters), amount_clusters)
continue
unique_indexes = set()
for cluster in clusters:
for index_point in cluster:
unique_indexes.add(index_point)
if len(data) != len(unique_indexes):
failures += "2. %d != %d\n" % (len(data), len(unique_indexes))
continue
if expected_length_clusters is None:
return
expected_total_length = sum(expected_length_clusters)
actual_total_length = sum([len(cluster) for cluster in clusters])
if expected_total_length != actual_total_length:
failures += "3. %d != %d\n" % (expected_total_length,
actual_total_length)
continue
actual_length_clusters = sorted(
[len(cluster) for cluster in clusters])
if expected_length_clusters != actual_length_clusters:
failures += "4. %s != %s\n" % (str(expected_length_clusters),
str(actual_length_clusters))
continue
return
self.fail("Expected result is not obtained during %d attempts: %s\n" %
(attempts, failures))
def test_predict_without_process(self):
self.assertEqual([], gmeans([[0], [1]]).predict([0]))
