def template_clustering(path_sample,
eps,
minpts,
amount_clusters=None,
visualize=True,
ccore=False):
sample = read_sample(path_sample)
optics_instance = optics(sample, eps, minpts, amount_clusters, ccore)
(ticks, _) = timedcall(optics_instance.process)
print("Sample: ", path_sample, "\t\tExecution time: ", ticks, "\n")
if (visualize is True):
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker='x')
visualizer.show()
ordering = optics_instance.get_ordering()
analyser = ordering_analyser(ordering)
ordering_visualizer.show_ordering_diagram(analyser, amount_clusters)
def templateClusteringResults(path, radius, neighbors, amount_clusters,
expected_length_clusters, ccore):
sample = read_sample(path)
optics_instance = optics(sample, radius, neighbors, amount_clusters,
ccore)
optics_instance.process()
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
assert sum([len(cluster)
for cluster in clusters]) + len(noise) == len(sample)
assert len(clusters) == len(expected_length_clusters)
assert sum([len(cluster)
for cluster in clusters]) == sum(expected_length_clusters)
assert sorted([len(cluster) for cluster in clusters
]) == sorted(expected_length_clusters)
if (amount_clusters is not None):
analyser = ordering_analyser(optics_instance.get_ordering())
assert len(analyser) > 0
amount_clusters, borders = analyser.extract_cluster_amount(
optics_instance.get_radius())
assert amount_clusters == len(expected_length_clusters)
assert len(borders) == amount_clusters - 1
def templateClusteringResultsSpecificData(data_type, path, radius, neighbors, amount_clusters, expected_length_clusters, ccore):
sample = read_sample(path);
if data_type == 'distance_matrix':
input_data = calculate_distance_matrix(sample);
else:
input_data = sample;
optics_instance = optics(input_data, radius, neighbors, amount_clusters, ccore, data_type=data_type);
optics_instance.process();
clusters = optics_instance.get_clusters();
noise = optics_instance.get_noise();
assert sum([len(cluster) for cluster in clusters]) + len(noise) == len(sample);
assert len(clusters) == len(expected_length_clusters);
assert sum([len(cluster) for cluster in clusters]) == sum(expected_length_clusters);
assert sorted([len(cluster) for cluster in clusters]) == sorted(expected_length_clusters);
if (amount_clusters is not None):
analyser = ordering_analyser(optics_instance.get_ordering());
assert len(analyser) > 0;
amount_clusters, borders = analyser.extract_cluster_amount(optics_instance.get_radius());
assert amount_clusters == len(expected_length_clusters);
assert len(borders) == amount_clusters - 1;
def testClusteringOrderVisualizer(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE4);
optics_instance = optics(sample, 6.0, 3, 5);
optics_instance.process();
analyser = ordering_analyser(optics_instance.get_ordering());
ordering_visualizer.show_ordering_diagram(analyser);
def testClusteringOrderVisualizer(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE4);
optics_instance = optics(sample, 6.0, 3, 5);
optics_instance.process();
analyser = ordering_analyser(optics_instance.get_ordering());
ordering_visualizer.show_ordering_diagram(analyser, 5);
def testClusterOrderingOneClusterExtraction(self):
analyser = ordering_analyser([5.0, 5.0, 5.0, 5.0, 5.0, 5.0])
amount_clusters, borders = analyser.extract_cluster_amount(6.5)
assert 1 == amount_clusters
assert 0 == len(borders)
amount_clusters, borders = analyser.extract_cluster_amount(4.5)
assert 0 == amount_clusters
assert 0 == len(borders)
def testClusterOrderingOneClusterExtraction(self):
analyser = ordering_analyser([5.0, 5.0, 5.0, 5.0, 5.0, 5.0]);
amount_clusters, borders = analyser.extract_cluster_amount(6.5);
assert 1 == amount_clusters;
assert 0 == len(borders);
amount_clusters, borders = analyser.extract_cluster_amount(4.5);
assert 0 == amount_clusters;
assert 0 == len(borders);
def templateClusteringResultsSpecificData(data_type, path, radius,
neighbors, amount_clusters,
expected_length_clusters, ccore):
sample = read_sample(path)
if data_type == 'distance_matrix':
input_data = calculate_distance_matrix(sample)
else:
input_data = sample
optics_instance = optics(input_data,
radius,
neighbors,
amount_clusters,
ccore,
data_type=data_type)
optics_instance.process()
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
optics_objects = optics_instance.get_optics_objects()
object_indexes = set([obj.index_object for obj in optics_objects])
assertion.eq(len(optics_objects), len(object_indexes))
for obj in optics_objects:
if obj.core_distance is not None:
assertion.ge(obj.core_distance, 0)
if obj.reachability_distance is not None:
assertion.ge(obj.reachability_distance, 0)
assert sum([len(cluster)
for cluster in clusters]) + len(noise) == len(sample)
assert len(clusters) == len(expected_length_clusters)
assert sum([len(cluster)
for cluster in clusters]) == sum(expected_length_clusters)
assert sorted([len(cluster) for cluster in clusters
]) == sorted(expected_length_clusters)
if amount_clusters is not None:
analyser = ordering_analyser(optics_instance.get_ordering())
assert len(analyser) > 0
amount_clusters, borders = analyser.extract_cluster_amount(
optics_instance.get_radius())
assert amount_clusters == len(expected_length_clusters)
assert len(borders) == amount_clusters - 1
def analyze(sample, radius, neighbors):
# Run cluster analysis where connectivity radius is bigger than real
# Create OPTICS algorithm for cluster analysis
optics_instance = optics(sample, radius, neighbors)
# Run cluster analysis
optics_instance.process()
# Obtain results of clustering
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
# Obtain reachability-distances
ordering = ordering_analyser(optics_instance.get_ordering())
return ordering, clusters, noise
def analyze(sample, radius, neighbors): # Run cluster analysis where connectivity radius is bigger than real # Create OPTICS algorithm for cluster analysis optics_instance = optics(sample, radius, neighbors) # Run cluster analysis optics_instance.process() # Obtain results of clustering clusters = optics_instance.get_clusters() noise = optics_instance.get_noise() # Obtain reachability-distances ordering = ordering_analyser(optics_instance.get_ordering()) return ordering, clusters, noise
def optics_temp(self, point_list):
# data = np.array( point_list)
sample = point_list
start = time.time()
optics_instance = optics(sample, 0.5, 6, ccore=True)
optics_instance.process()
clusters = optics_instance.get_clusters()
end = time.time()
print("imte", end - start)
noise = optics_instance.get_noise()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker='x')
visualizer.show()
ordering = optics_instance.get_ordering()
analyser = ordering_analyser(ordering)
ordering_visualizer.show_ordering_diagram(analyser, amount_clusters)
def templateClusteringResultsSpecificData(data_type, path, radius, neighbors, amount_clusters, expected_length_clusters, ccore):
sample = read_sample(path)
if data_type == 'distance_matrix':
input_data = calculate_distance_matrix(sample)
else:
input_data = sample
optics_instance = optics(input_data, radius, neighbors, amount_clusters, ccore, data_type=data_type)
optics_instance.process()
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
optics_objects = optics_instance.get_optics_objects()
object_indexes = set( [ obj.index_object for obj in optics_objects ] )
assertion.eq(len(optics_objects), len(object_indexes))
for obj in optics_objects:
if obj.core_distance is not None:
assertion.ge(obj.core_distance, 0)
if obj.reachability_distance is not None:
assertion.ge(obj.reachability_distance, 0)
assert sum([len(cluster) for cluster in clusters]) + len(noise) == len(sample)
assert len(clusters) == len(expected_length_clusters)
assert sum([len(cluster) for cluster in clusters]) == sum(expected_length_clusters)
assert sorted([len(cluster) for cluster in clusters]) == sorted(expected_length_clusters)
if amount_clusters is not None:
analyser = ordering_analyser(optics_instance.get_ordering())
assert len(analyser) > 0
amount_clusters, borders = analyser.extract_cluster_amount(optics_instance.get_radius())
assert amount_clusters == len(expected_length_clusters)
assert len(borders) == amount_clusters - 1
def testImpossibleClusterOrderingAllocationGeterogeneous(self):
analyser = ordering_analyser(
[5.0, 5.0, 5.0, 5.0, 6.0, 8.0, 6.0, 5.0, 5.0, 5.0])
amount_clusters, borders = analyser.calculate_connvectivity_radius(3)
assert None == amount_clusters
assert 0 == len(borders)
def testImpossibleClusterOrderingAllocationGeterogeneous(self):
analyser = ordering_analyser([5.0, 5.0, 5.0, 5.0, 6.0, 8.0, 6.0, 5.0, 5.0, 5.0]);
amount_clusters, borders = analyser.calculate_connvectivity_radius(3);
assert None == amount_clusters;
assert 0 == len(borders);
def testImpossibleClusterOrderingAllocationHomogeneous(self):
analyser = ordering_analyser(
[5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0, 5.0])
assert None == analyser.calculate_connvectivity_radius(2)
