def test_simple(self):
config = Config()
self.assertEqual('kmeans', config['method'])
self.assertEqual({'k': 3, 'seed': 0}, config['parameter'])
self.assertEqual('simple', config['compressor_method'])
self.assertEqual({'bucket_size': 100}, config.get('compressor_parameter'))
self.assertEqual('euclidean', config.get('distance'))
def test_simple(self):
config = Config()
self.assertEqual('kmeans', config['method'])
self.assertEqual({'k': 3, 'seed': 0}, config['parameter'])
self.assertEqual('simple', config['compressor_method'])
self.assertEqual({'bucket_size': 100},
config.get('compressor_parameter'))
self.assertEqual('euclidean', config.get('distance'))
def _test_func_with_legal_and_illegal_config(self, func):
dataset = self._make_stub_dataset()
# test illegal method
config = Config(method='dbscan',
compressor_parameter={"bucket_size": 5})
clustering = self._make_stub_clustering(config, dataset)
self.assertRaises(RuntimeError, lambda: func(clustering, dataset))
clustering.stop()
# test legal method
config = Config(method='kmeans',
compressor_parameter={"bucket_size": 5})
clustering = self._make_stub_clustering(config, dataset)
func(clustering, dataset)
clustering.stop()
def test_get_core_members(self):
dataset = self._make_stub_dataset()
config = Config(method='kmeans',
compressor_parameter={"bucket_size": 5})
clustering = self._make_stub_clustering(config, dataset)
clustering.get_core_members(light=False)
clustering.get_core_members(light=True)
clustering.stop()
def test_method_params(self):
self.assertTrue('k' in Config(method='kmeans')['parameter'])
self.assertTrue('seed' in Config(method='kmeans')['parameter'])
self.assertTrue('k' in Config(method='gmm')['parameter'])
self.assertTrue('seed' in Config(method='gmm')['parameter'])
self.assertTrue('eps' in Config(method='dbscan')['parameter'])
self.assertTrue('min_core_point' in Config(
method='dbscan')['parameter'])
def test_compressor_params(self):
self.assertTrue('bucket_size' in Config(
compressor_method='simple')['compressor_parameter'])
self.assertTrue('bucket_size' in Config(
compressor_method='compressive')['compressor_parameter'])
self.assertTrue('bucket_length' in Config(
compressor_method='compressive')['compressor_parameter'])
self.assertTrue('compressed_bucket_size' in Config(
compressor_method='compressive')['compressor_parameter'])
self.assertTrue('bicriteria_base_size' in Config(
compressor_method='compressive')['compressor_parameter'])
self.assertTrue('forgetting_factor' in Config(
compressor_method='compressive')['compressor_parameter'])
self.assertTrue('seed' in Config(
compressor_method='compressive')['compressor_parameter'])
config = Config(compressor_method='simple',
compressor_parameter={'bucket_size': 10})
self.assertEqual(10, config['compressor_parameter']['bucket_size'])
def test_default(self):
config = Config.default()
self.assertEqual('kmeans', config['method'])
self.assertEqual('simple', config['compressor_method'])
self.assertEqual('euclidean', config['distance'])
def test_compressor_methods(self):
config = Config()
self.assertTrue(isinstance(config.compressor_methods(), list))
def test_distances(self):
config = Config()
self.assertTrue(isinstance(config.distances(), list))
def test_compressor_methods(self): config = Config() self.assertTrue(isinstance(config.compressor_methods(), list))
def test_methods(self):
config = Config()
self.assertTrue(isinstance(config.methods(), list))
def test_methods(self): config = Config() self.assertTrue(isinstance(config.methods(), list))
def test_distances(self): config = Config() self.assertTrue(isinstance(config.distances(), list))
def test_get_revision(self):
clustering = Clustering.run(Config())
self.assertEqual(0, clustering.get_revision())
clustering.stop()
def test_push(self):
clustering = Clustering.run(Config())
dataset = self._make_stub_dataset()
for (idx, row_id, result) in clustering.push(dataset):
self.assertEqual(result, True)
clustering.stop()
def test_embedded(self):
clustering = Clustering.run(Config(), embedded=True)
clustering.stop()
from jubakit.clustering import Clustering, Schema, Dataset, Config
from jubakit.loader.csv import CSVLoader
# Load a CSV file.
loader = CSVLoader('blobs.csv')
# Define a Schema that defines types for each columns of the CSV file.
schema = Schema({
'cluster': Schema.ID,
}, Schema.NUMBER)
# Create a Dataset.
dataset = Dataset(loader, schema)
# Create an Clustering Service.
cfg = Config(method='kmeans')
clustering = Clustering.run(cfg)
# Update the Clustering model.
for (idx, row_id, result) in clustering.push(dataset):
pass
# Get clusters
clusters = clustering.get_core_members(light=False)
# Get centers of each cluster
centers = clustering.get_k_center()
# Calculate SSE: sum of squared errors
sse = 0.0
for cluster, center in zip(clusters, centers):
# Center of clusters
def test_default(self):
config = Config.default()
self.assertEqual('kmeans', config['method'])
self.assertEqual('simple', config['compressor_method'])
self.assertEqual('euclidean', config['distance'])