def testVisualize2DAnd3DClusters(self):
sample_2d = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
sample_3d = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA);
visualizer = cluster_visualizer(2, 2);
visualizer.append_clusters([ sample_2d ], None, 0, markersize = 5);
visualizer.append_clusters([ sample_3d ], None, 1, markersize = 30);
visualizer.show();
def testVisualize1DClustersTwoCanvases(self):
sample_simple7 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE7);
sample_simple8 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE8);
# Two canvas visualization
visualizer = cluster_visualizer(2);
visualizer.append_clusters([ sample_simple7 ], None, 0, markersize = 30);
visualizer.append_clusters([ sample_simple8 ], None, 1, markersize = 30);
visualizer.show();
def testVisualize3DClustersTwoCanvases(self):
sample_tetra = read_sample(FCPS_SAMPLES.SAMPLE_TETRA);
sample_hepta = read_sample(FCPS_SAMPLES.SAMPLE_HEPTA);
# Two canvas visualization
visualizer = cluster_visualizer(2);
visualizer.append_clusters([ sample_tetra ], None, 0, markersize = 30);
visualizer.append_clusters([ sample_hepta ], None, 1, markersize = 30);
visualizer.show();
def testVisualizeRectangeRepresentation2x2(self):
sample_simple1 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
sample_simple2 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2);
sample_simple3 = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3);
visualizer = cluster_visualizer(3, 2);
visualizer.append_clusters([ sample_simple1 ], None, 0, markersize = 5);
visualizer.append_clusters([ sample_simple2 ], None, 1, markersize = 5);
visualizer.append_clusters([ sample_simple3 ], None, 2, markersize = 5);
visualizer.show();
def testAllocatedRequestedClustersSampleSimple03(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3)
KmedoidsTestTemplates.templateAllocateRequestedClusterAmount(sample, 2, None, False)
KmedoidsTestTemplates.templateAllocateRequestedClusterAmount(sample, 5, None, False)
KmedoidsTestTemplates.templateAllocateRequestedClusterAmount(sample, 8, None, False)
KmedoidsTestTemplates.templateAllocateRequestedClusterAmount(sample, 10, None, False)
KmedoidsTestTemplates.templateAllocateRequestedClusterAmount(sample, 15, None, False)
def templateClusterAllocation(self, path, cluster_sizes, number_clusters, iterations, maxneighbors):
result_testing = False;
# it's randomized algorithm therefore attempts are required
for attempt in range(0, 5, 1):
sample = read_sample(path);
clarans_instance = clarans(sample, number_clusters, iterations, maxneighbors);
clarans_instance.process();
clusters = clarans_instance.get_clusters();
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
total_length = sum(obtained_cluster_sizes);
if (total_length != len(sample)):
continue;
cluster_sizes.sort();
obtained_cluster_sizes.sort();
if (cluster_sizes != obtained_cluster_sizes):
continue;
result_testing = True;
break;
assert result_testing == True;
def templateLengthProcessData(path_to_file, start_centers, expected_cluster_length, ccore, **kwargs):
sample = read_sample(path_to_file)
metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE))
itermax = kwargs.get('itermax', 200)
kmeans_instance = kmeans(sample, start_centers, 0.001, ccore, metric=metric, itermax=itermax)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
wce = kmeans_instance.get_total_wce()
if itermax == 0:
assertion.eq(start_centers, centers)
assertion.eq([], clusters)
assertion.eq(0.0, wce)
return
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
assertion.eq(len(sample), sum(obtained_cluster_sizes))
assertion.eq(len(clusters), len(centers))
for center in centers:
assertion.eq(len(sample[0]), len(center))
if expected_cluster_length is not None:
obtained_cluster_sizes.sort()
expected_cluster_length.sort()
assertion.eq(obtained_cluster_sizes, expected_cluster_length)
def templateClusteringWithAnswers(sample_path, answer_path, radius, neighbors, ccore, **kwargs):
random_order = kwargs.get('random_order', False)
repeat = kwargs.get('repeat', 1)
for _ in range(repeat):
sample = read_sample(sample_path)
sample_index_map = [ i for i in range(len(sample)) ]
if random_order:
shuffle(sample_index_map)
sample_shuffled = [ sample[i] for i in sample_index_map ]
dbscan_instance = dbscan(sample_shuffled, radius, neighbors, ccore)
dbscan_instance.process()
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
for cluster in clusters:
for i in range(len(cluster)):
cluster[i] = sample_index_map[cluster[i]]
for i in range(len(noise)):
noise[i] = sample_index_map[noise[i]]
noise = sorted(noise)
reader = answer_reader(answer_path)
expected_noise = sorted(reader.get_noise())
expected_length_clusters = reader.get_cluster_lengths()
assertion.eq(len(sample), sum([len(cluster) for cluster in clusters]) + len(noise))
assertion.eq(sum(expected_length_clusters), sum([len(cluster) for cluster in clusters]))
assertion.eq(expected_length_clusters, sorted([len(cluster) for cluster in clusters]))
assertion.eq(expected_noise, noise)
def template_clustering(path,
count_clusters,
chromosome_count,
population_count,
count_mutation_gens,
coeff_mutation_count=0.25,
select_coeff=1.0,
fps=15,
animation=False):
sample = read_sample(path)
algo_instance = genetic_algorithm(data=sample,
count_clusters=count_clusters,
chromosome_count=chromosome_count,
population_count=population_count,
count_mutation_gens=count_mutation_gens,
coeff_mutation_count=coeff_mutation_count,
select_coeff=select_coeff,
observer=ga_observer(True, True, True))
start_time = time.time()
algo_instance.process()
print("Sample: ", path, "\t\tExecution time: ", time.time() - start_time, "\n")
observer = algo_instance.get_observer()
ga_visualizer.show_clusters(sample, observer)
if (animation is True):
ga_visualizer.animate_cluster_allocation(sample, observer, movie_fps=fps, save_movie="clustering_animation.mp4")
def templateClustering(self, file, radius, order, solver, initial, storage_flag, conn_weigh_flag, tolerance, connection, expected_cluster_length, ccore_flag):
result_testing = False;
# If phases crosses each other because of random part of the network then we should try again.
for attempt in range(0, 4, 1):
sample = read_sample(file);
network = syncnet(sample, radius, connection, initial, conn_weigh_flag, ccore_flag);
analyser = network.process(order, solver, storage_flag);
clusters = analyser.allocate_clusters(tolerance);
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
if (len(obtained_cluster_sizes) != len(expected_cluster_length)):
continue;
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
if (obtained_cluster_sizes != expected_cluster_length):
continue;
# Unit-test is passed
result_testing = True;
break;
assert result_testing;
def template_clustering(file, map_size, trust_order, sync_order = 0.999, show_dyn = False, show_layer1 = False, show_layer2 = False, show_clusters = True):
# Read sample
sample = read_sample(file);
# Create network
network = syncsom(sample, map_size[0], map_size[1]);
# Run processing
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, trust_order, show_dyn, sync_order);
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n");
# Show dynamic of the last layer.
if (show_dyn == True):
draw_dynamics(dyn_time, dyn_phase, x_title = "Time", y_title = "Phase", y_lim = [0, 2 * 3.14]);
if (show_clusters == True):
clusters = network.get_som_clusters();
draw_clusters(network.som_layer.weights, clusters);
# Show network stuff.
if (show_layer1 == True):
network.show_som_layer();
if (show_layer2 == True):
network.show_sync_layer();
if (show_clusters == True):
clusters = network.get_clusters();
draw_clusters(sample, clusters);
def correct_ksearch(sample_path, answer_path, kmin, kmax, algorithm, ccore_flag):
attempts = 10
testing_result = False
sample = read_sample(sample_path)
clusters = answer_reader(answer_path).get_clusters()
for _ in range(attempts):
ksearch_instance = silhouette_ksearch(sample, kmin, kmax, algorithm=algorithm, ccore=ccore_flag).process()
amount = ksearch_instance.get_amount()
score = ksearch_instance.get_score()
scores = ksearch_instance.get_scores()
assertion.le(-1.0, score)
assertion.ge(1.0, score)
assertion.eq(kmax - kmin, len(scores))
upper_limit = len(clusters) + 1
lower_limit = len(clusters) - 1
if lower_limit < 1:
lower_limit = 1
if (amount > upper_limit) or (amount < lower_limit):
continue
testing_result = True
break
assertion.true(testing_result)
def template_clustering(number_clusters, path, links):
sample = read_sample(path);
clusters_centroid_link = None;
clusters_single_link = None;
clusters_complete_link = None;
clusters_average_link = None;
visualizer = cluster_visualizer(len(links));
index_canvas = 0;
if (type_link.CENTROID_LINK in links):
agglomerative_centroid_link = agglomerative(sample, number_clusters, type_link.CENTROID_LINK);
(ticks, result) = timedcall(agglomerative_centroid_link.process);
clusters_centroid_link = agglomerative_centroid_link.get_clusters();
visualizer.append_clusters(clusters_centroid_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Centroid', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Centroid", "\tExecution time: ", ticks, "\n");
if (type_link.SINGLE_LINK in links):
agglomerative_simple_link = agglomerative(sample, number_clusters, type_link.SINGLE_LINK);
(ticks, result) = timedcall(agglomerative_simple_link.process);
clusters_single_link = agglomerative_simple_link.get_clusters();
visualizer.append_clusters(clusters_single_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Single', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Single", "\tExecution time: ", ticks, "\n");
if (type_link.COMPLETE_LINK in links):
agglomerative_complete_link = agglomerative(sample, number_clusters, type_link.COMPLETE_LINK);
(ticks, result) = timedcall(agglomerative_complete_link.process);
clusters_complete_link = agglomerative_complete_link.get_clusters();
visualizer.append_clusters(clusters_complete_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Complete', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Complete", "\tExecution time: ", ticks, "\n");
if (type_link.AVERAGE_LINK in links):
agglomerative_average_link = agglomerative(sample, number_clusters, type_link.AVERAGE_LINK);
(ticks, result) = timedcall(agglomerative_average_link.process);
clusters_average_link = agglomerative_average_link.get_clusters();
visualizer.append_clusters(clusters_average_link, sample, index_canvas);
visualizer.set_canvas_title('Link: Average', index_canvas);
index_canvas += 1;
print("Sample: ", path, "Link: Average", "\tExecution time: ", ticks, "\n");
visualizer.show();
def templateLengthProcessData(self, file, som_map_size, avg_num_conn, eps, expected_cluster_length):
result_testing = False;
# If phases crosses each other because of random part of the network then we should try again.
for attempt in range(0, 3, 1):
sample = read_sample(file);
network = syncsom(sample, som_map_size[0], som_map_size[1]);
network.process(avg_num_conn, collect_dynamic = False, order = eps);
clusters = network.get_clusters();
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
if (len(sample) != sum(obtained_cluster_sizes)):
continue;
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
#print(obtained_cluster_sizes, expected_cluster_length);
if (obtained_cluster_sizes != expected_cluster_length):
continue;
# Unit-test is passed
result_testing = True;
break;
assert result_testing;
def elbow_analysis(sample_file_path, kmin, kmax, **kwargs):
initializer = kwargs.get('initializer', kmeans_plusplus_initializer)
sample = read_sample(sample_file_path)
elbow_instance = elbow(sample, kmin, kmax, initializer=initializer)
elbow_instance.process()
amount_clusters = elbow_instance.get_amount()
wce = elbow_instance.get_wce()
centers = kmeans_plusplus_initializer(sample, amount_clusters).initialize()
kmeans_instance = kmeans(sample, centers)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
centers = kmeans_instance.get_centers()
print("Sample '%s': Obtained amount of clusters: '%d'." % (sample_file_path, amount_clusters))
figure = plt.figure(1)
ax = figure.add_subplot(111)
ax.plot(range(kmin, kmax), wce, color='b', marker='.')
ax.plot(amount_clusters, wce[amount_clusters - kmin], color='r', marker='.', markersize=10)
ax.annotate("Elbow", (amount_clusters + 0.1, wce[amount_clusters - kmin] + 5))
ax.grid(True)
plt.ylabel("WCE")
plt.xlabel("K")
plt.show()
kmeans_visualizer.show_clusters(sample, clusters, centers)
def templateLengthProcessData(data, start_medians, expected_cluster_length, ccore, **kwargs):
tolerance = kwargs.get('tolerance', 0.01)
metric = kwargs.get('metric', None)
itermax = kwargs.get('itermax', 200)
if isinstance(data, str):
sample = read_sample(data)
else:
sample = data
kmedians_instance = kmedians(sample, start_medians, tolerance, ccore, metric=metric, itermax=itermax)
kmedians_instance.process()
clusters = kmedians_instance.get_clusters()
medians = kmedians_instance.get_medians()
if itermax == 0:
assert clusters == []
assert start_medians == medians
return
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
assert len(sample) == sum(obtained_cluster_sizes)
assert len(medians) == len(clusters)
if expected_cluster_length is not None:
obtained_cluster_sizes.sort()
expected_cluster_length.sort()
if obtained_cluster_sizes != expected_cluster_length:
print(obtained_cluster_sizes)
assert obtained_cluster_sizes == expected_cluster_length
def testVisualizeByDataOnly(self):
visualizer = cluster_visualizer();
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer.append_clusters([ sample ]);
visualizer.show();
def templateTestAwardNeurons(file, rows, cols, time, expected_result, autostop, ccore_flag, parameters = None, **kwargs):
store_load = kwargs.get('store_load', False)
types = [type_conn.func_neighbor, type_conn.grid_eight, type_conn.grid_four, type_conn.honeycomb]
sample = read_sample(file)
if (parameters is None):
parameters = som_parameters()
for stucture in types:
network = som(rows, cols, stucture, parameters, ccore = ccore_flag)
if store_load:
dump_network = pickle.dumps(network)
network = pickle.loads(dump_network)
network.train(sample, time, autostop)
winners = network.get_winner_number()
assert winners == len(expected_result)
if sorted(network.awards) != expected_result:
network.show_network(awards = True)
assert sorted(network.awards) == expected_result
total_capture_points = 0
for points in network.capture_objects:
total_capture_points += len(points)
assert total_capture_points == sum(expected_result)
del network
def template_cluster_allocation(input_data, cluster_sizes, number_cluster, number_represent_points = 5, compression = 0.5, ccore_flag = False, **kwargs):
if isinstance(input_data, str):
sample = read_sample(input_data)
else:
sample = input_data
numpy_usage = kwargs.get('numpy_usage', False)
if numpy_usage is True:
sample = numpy.array(sample)
cure_instance = cure(sample, number_cluster, number_represent_points, compression, ccore = ccore_flag)
cure_instance.process()
clusters = cure_instance.get_clusters()
representors = cure_instance.get_representors()
means = cure_instance.get_means()
assertion.eq(len(clusters), number_cluster)
assertion.eq(len(representors), number_cluster)
assertion.eq(len(means), number_cluster)
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
total_length = sum(obtained_cluster_sizes)
assertion.eq(total_length, len(sample))
cluster_sizes.sort()
obtained_cluster_sizes.sort()
assertion.eq(cluster_sizes, obtained_cluster_sizes)
def templateDataClustering(self, sample_path,
amount_clusters,
chromosome_count,
population_count,
count_mutation_gens,
coeff_mutation_count,
expected_clusters_sizes):
testing_result = False
for _ in range(3):
sample = read_sample(sample_path)
ga_instance = genetic_algorithm(sample, amount_clusters, chromosome_count, population_count,
count_mutations_gen=count_mutation_gens,
coeff_mutation_count=coeff_mutation_count)
ga_instance.process()
clusters = ga_instance.get_clusters()
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
if len(sample) != sum(obtained_cluster_sizes):
continue
if expected_clusters_sizes is not None:
obtained_cluster_sizes.sort()
expected_clusters_sizes.sort()
if obtained_cluster_sizes != expected_clusters_sizes:
continue
testing_result = True
break
assert testing_result is True
def clustering(path, amount, threshold, expected, ccore, **kwargs):
metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN));
sample = read_sample(path);
bsas_instance = bsas(sample, amount, threshold, ccore=ccore, metric=metric);
bsas_instance.process();
clusters = bsas_instance.get_clusters();
representatives = bsas_instance.get_representatives();
obtained_length = 0;
obtained_cluster_length = [];
for cluster in clusters:
obtained_length += len(cluster);
obtained_cluster_length.append(len(cluster));
assertion.eq(len(sample), obtained_length);
assertion.eq(len(expected), len(clusters));
assertion.eq(len(expected), len(representatives));
assertion.ge(amount, len(clusters));
dimension = len(sample[0]);
for rep in representatives:
assertion.eq(dimension, len(rep));
expected.sort();
obtained_cluster_length.sort();
assertion.eq(expected, obtained_cluster_length);
def template_visualize(self, path_sample, path_answer, filter=None, **kwargs):
data = read_sample(path_sample)
clusters = answer_reader(path_answer).get_clusters()
visualizer = cluster_visualizer_multidim()
visualizer.append_clusters(clusters, data)
visualizer.show(filter, **kwargs)
def template_clustering(sample_file_path, amount_clusters, initializer, show_animation = False):
sample = read_sample(sample_file_path);
observer = None;
if (show_animation is True):
observer = ema_observer();
initial_means, initial_covariance = ema_initializer(sample, amount_clusters).initialize(initializer);
ema_instance = ema(sample, amount_clusters, initial_means, initial_covariance, observer=observer);
ema_instance.process();
clusters = ema_instance.get_clusters();
covariances = ema_instance.get_covariances();
means = ema_instance.get_centers();
cluster_length = [ len(cluster) for cluster in clusters ];
print("Data '" + sample_file_path + "'");
print("Clusters: " + str(len(clusters)) + ", Length:" + str(cluster_length));
if (observer is True):
ema_visualizer.show_clusters(observer.get_evolution_clusters()[0], sample, observer.get_evolution_covariances()[0], observer.get_evolution_means()[0]);
ema_visualizer.show_clusters(clusters, sample, covariances, means);
if (show_animation is True):
ema_visualizer.animate_cluster_allocation(sample, observer);
def templateLengthProcessData(input_sample, start_centers, expected_cluster_length, type_splitting, kmax, ccore):
if isinstance(input_sample, str):
sample = read_sample(input_sample)
else:
sample = input_sample
#clusters = xmeans(sample, start_centers, 20, ccore);
xmeans_instance = xmeans(sample, start_centers, kmax, 0.025, type_splitting, ccore)
xmeans_instance.process()
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
assert len(sample) == sum(obtained_cluster_sizes);
assert len(clusters) == len(centers);
assert len(centers) <= kmax;
if expected_cluster_length is not None:
assert len(centers) == len(expected_cluster_length);
obtained_cluster_sizes.sort()
expected_cluster_length.sort()
assert obtained_cluster_sizes == expected_cluster_length;
def calculate_elbow(path_to_data, path_to_answer, kmin, kmax, ccore, **kwargs):
repeat = 10 # Elbow method randomly chooses initial centers therefore we need to repeat test if it fails.
testing_result = False
initializer = kwargs.get('initializer', kmeans_plusplus_initializer)
sample = read_sample(path_to_data)
answer = answer_reader(path_to_answer)
additional_info = []
for _ in range(repeat):
elbow_instance = elbow(sample, kmin, kmax, ccore=ccore, initializer=initializer)
elbow_instance.process()
actual_elbow = elbow_instance.get_amount()
actual_wce = elbow_instance.get_wce()
assertion.gt(actual_elbow, kmin)
assertion.lt(actual_elbow, kmax)
assertion.eq(len(actual_wce), kmax - kmin)
assertion.lt(actual_wce[-1], actual_wce[0] + 0.0000001)
if actual_elbow != len(answer.get_clusters()):
additional_info.append(actual_elbow)
#time.sleep(0.05) # sleep to gain new seed for random generator
continue
testing_result = True
break
message = str(len(answer.get_clusters())) + ": " + str(additional_info)
assertion.true(testing_result, message=message)
def testShowLayersProcessing(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
network = syncsom(sample, 4, 4, 1.0);
network.process(collect_dynamic = False, order = 0.99);
network.show_som_layer();
network.show_sync_layer();
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 templateAnimateClusteringResultNoFailure(filename, initial_centers, ccore_flag):
sample = read_sample(filename)
observer = kmeans_observer()
kmeans_instance = kmeans(sample, initial_centers, 0.025, ccore_flag, observer=observer)
kmeans_instance.process()
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def testVisualizeOnExistedFigure(self):
figure = plt.figure();
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer = cluster_visualizer();
visualizer.append_clusters([ sample ]);
visualizer.show(figure);
def testVisualizeRectangeRepresentation3x5(self):
visualizer = cluster_visualizer(15, 5);
for i in range(15):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
visualizer.append_clusters([ sample ], None, i, markersize = 5);
visualizer.show();
def templateClusteringResults(path, radius, neighbors,
expected_length_clusters, ccore):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighbors, ccore)
dbscan_instance.process()
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
assert sum([len(cluster)
for cluster in clusters]) + len(noise) == len(sample)
assert sum([len(cluster)
for cluster in clusters]) == sum(expected_length_clusters)
assert sorted([len(cluster)
for cluster in clusters]) == expected_length_clusters
def template_clustering(start_centers, path, tolerance = 0.25, ccore = True):
sample = read_sample(path);
kmeans_instance = kmeans(sample, start_centers, tolerance, ccore);
(ticks, result) = timedcall(kmeans_instance.process);
clusters = kmeans_instance.get_clusters();
centers = kmeans_instance.get_centers();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(start_centers, marker = '*', markersize = 20);
visualizer.append_cluster(centers, marker = '*', markersize = 20);
visualizer.show();
def random_state(rows, cols, connections, random_state, ccore_flag):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1)
params = som_parameters()
params.random_state = random_state
network_1 = som(rows, cols, connections, ccore=ccore_flag)
steps_1 = network_1.train(sample, 100, True)
network_2 = som(rows, cols, connections, ccore=ccore_flag)
steps_2 = network_2.train(sample, 100, True)
assert steps_1 == steps_2
assert network_1.weights == network_2.weights
assert network_1.capture_objects == network_2.capture_objects
assert network_1.awards == network_2.awards
def templateEncoderProcedures(sample, initial_centers, number_clusters,
ccore_flag):
sample = read_sample(sample)
cure_instance = kmeans(sample, initial_centers, 0.025, ccore_flag)
cure_instance.process()
clusters = cure_instance.get_clusters()
encoding = cure_instance.get_cluster_encoding()
encoder = cluster_encoder(encoding, clusters, sample)
encoder.set_encoding(type_encoding.CLUSTER_INDEX_LABELING)
encoder.set_encoding(type_encoding.CLUSTER_OBJECT_LIST_SEPARATION)
encoder.set_encoding(type_encoding.CLUSTER_INDEX_LIST_SEPARATION)
assert number_clusters == len(clusters)
def templateLengthProcessData(path_to_file, radius, cluster_numbers,
threshold, expected_cluster_length, ccore):
sample = read_sample(path_to_file)
rock_instance = rock(sample, radius, cluster_numbers, threshold, ccore)
rock_instance.process()
clusters = rock_instance.get_clusters()
length = sum([len(cluster) for cluster in clusters])
assert len(sample) == length
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
obtained_cluster_sizes.sort()
expected_cluster_length.sort()
assert obtained_cluster_sizes == expected_cluster_length
def templateLengthProcessData(path_to_file, initial_medoids,
expected_cluster_length, ccore_flag):
sample = read_sample(path_to_file)
kmedoids_instance = kmedoids(sample, initial_medoids, 0.025,
ccore_flag)
kmedoids_instance.process()
clusters = kmedoids_instance.get_clusters()
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
assert len(sample) == sum(obtained_cluster_sizes)
obtained_cluster_sizes.sort()
expected_cluster_length.sort()
assert obtained_cluster_sizes == expected_cluster_length
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 template_clustering(file,
map_size,
radius,
sync_order=0.999,
show_dyn=False,
show_layer1=False,
show_layer2=False,
show_clusters=True):
# Read sample
sample = read_sample(file)
# Create network
network = syncsom(sample, map_size[0], map_size[1], radius)
# Run processing
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, show_dyn,
sync_order)
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n")
# Show dynamic of the last layer.
if (show_dyn == True):
draw_dynamics(dyn_time,
dyn_phase,
x_title="Time",
y_title="Phase",
y_lim=[0, 3.14])
if (show_clusters == True):
clusters = network.get_som_clusters()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, network.som_layer.weights)
visualizer.show()
# Show network stuff.
if (show_layer1 == True):
network.show_som_layer()
if (show_layer2 == True):
network.show_sync_layer()
if (show_clusters == True):
clusters = network.get_clusters()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
def correct_scores(sample_path, answer_path, ccore_flag, **kwargs):
data_type = kwargs.get('data_type', 'points')
sample = read_sample(sample_path)
if data_type == 'distance_matrix':
sample = calculate_distance_matrix(sample, distance_metric(type_metric.EUCLIDEAN_SQUARE))
clusters = answer_reader(answer_path).get_clusters()
scores = silhouette(sample, clusters, ccore=ccore_flag, data_type=data_type).process().get_score()
assertion.eq(len(sample), len(scores))
for score in scores:
assertion.le(-1.0, score)
assertion.ge(1.0, score)
return scores
def exception(type, input_data, number_cluster, number_represent_points, compression, ccore_flag):
try:
if isinstance(input_data, str):
sample = read_sample(input_data)
else:
sample = input_data
cure_instance = cure(sample, number_cluster, number_represent_points, compression, ccore=ccore_flag)
cure_instance.process()
except type:
return
except Exception as ex:
raise AssertionError("Expected: '%s', Actual: '%s'" % (type, type(ex).__name__))
raise AssertionError("Expected: '%s', Actual: 'None'" % type)
def templateClusterAllocation(self, path, cluster_sizes, number_clusters, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.1, type_measurement = measurement_type.CENTROID_EUCLIDIAN_DISTANCE, entry_size_limit = 200, diameter_multiplier = 1.5):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, diameter_multiplier);
birch_instance.process();
clusters = birch_instance.get_clusters();
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
total_length = sum(obtained_cluster_sizes);
assert total_length == len(sample);
if (cluster_sizes != None):
cluster_sizes.sort();
obtained_cluster_sizes.sort();
assert cluster_sizes == obtained_cluster_sizes;
def find_optimal_amout_clusters(sample_path, kmin, kmax, algorithm):
sample = read_sample(sample_path)
search_instance = silhouette_ksearch(sample, kmin, kmax, algorithm=algorithm).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
print("Sample: '%s', Scores: '%s'" % (sample_path, str(scores)))
initial_centers = kmeans_plusplus_initializer(sample, amount).initialize()
kmeans_instance = kmeans(sample, initial_centers).process()
clusters = kmeans_instance.get_clusters()
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
def template_clustering(path, amount, threshold, **kwargs):
metric = kwargs.get('metric', distance_metric(type_metric.EUCLIDEAN_SQUARE));
ccore = kwargs.get('ccore', False);
draw = kwargs.get('draw', True);
sample = read_sample(path);
print("Sample: ", path);
mbsas_instance = mbsas(sample, amount, threshold, ccore=ccore, metric=metric);
mbsas_instance.process();
clusters = mbsas_instance.get_clusters();
representatives = mbsas_instance.get_representatives();
if draw is True:
bsas_visualizer.show_clusters(sample, clusters, representatives);
def templateLengthProcessData(path_to_file, amount_clusters, expected_cluster_length, ccore):
sample = read_sample(path_to_file);
somsc_instance = somsc(sample, amount_clusters, 100, ccore);
somsc_instance.process();
clusters = somsc_instance.get_clusters();
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
assert len(sample) == sum(obtained_cluster_sizes);
if (expected_cluster_length != None):
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
if (obtained_cluster_sizes != expected_cluster_length):
print
assert obtained_cluster_sizes == expected_cluster_length;
def templatePredict(path_to_file, initial_centers, points, expected_amount,
expected_closest_clusters, ccore, **kwargs):
sample = read_sample(path_to_file)
kmax = kwargs.get('kmax', 20)
xmeans_instance = xmeans(sample, initial_centers, kmax, 0.025,
splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore)
xmeans_instance.process()
closest_clusters = xmeans_instance.predict(points)
assertion.eq(expected_amount, len(xmeans_instance.get_clusters()))
assertion.eq(len(expected_closest_clusters), len(closest_clusters))
assertion.true(
numpy.array_equal(numpy.array(expected_closest_clusters),
closest_clusters))
def template_clustering(path_sample, eps, minpts):
sample = read_sample(path_sample)
optics_instance = optics(sample, eps, minpts)
optics_instance.process()
clusters = optics_instance.get_clusters()
noise = optics_instance.get_noise()
draw_clusters(sample, clusters, [], '.')
ordering = optics_instance.get_cluster_ordering()
indexes = [i for i in range(0, len(ordering))]
# visualization of cluster ordering in line with reachability distance.
plt.bar(indexes, ordering)
plt.show()
def testVisualizeClusterWithAttributes(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1);
cure_instance = cure(sample, 2, 5, 0.5, False);
cure_instance.process();
clusters = cure_instance.get_clusters();
representors = cure_instance.get_representors();
means = cure_instance.get_means();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
for cluster_index in range(len(clusters)):
visualizer.append_cluster_attribute(0, cluster_index, representors[cluster_index], '*', 10);
visualizer.append_cluster_attribute(0, cluster_index, [ means[cluster_index] ], 'o');
visualizer.show();
def templateDynamicLength(path, number_clusters, expected_length, initial_neighbors, increase_persent, collect_dynamic_flag, ccore_flag):
sample = read_sample(path);
network = hsyncnet(sample, number_clusters, initial_type.EQUIPARTITION, initial_neighbors, increase_persent, ccore = ccore_flag);
analyser = network.process(order = 0.995, solution = solve_type.FAST, collect_dynamic = collect_dynamic_flag);
assert len(analyser) != 0;
if (collect_dynamic_flag is True):
assert len(analyser) >= 1;
if (expected_length is None):
assert len(analyser) > 1;
else:
assert len(analyser) == expected_length;
else:
assert len(analyser) == 1;
def template_clustering(path,
radius,
cluster_numbers,
threshold,
draw=True,
ccore=True):
sample = read_sample(path)
rock_instance = rock(sample, radius, cluster_numbers, threshold, ccore)
(ticks, result) = timedcall(rock_instance.process)
clusters = rock_instance.get_clusters()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if (draw == True):
draw_clusters(sample, clusters)
def templateKmeansPlusPlusForKmedoidsClustering(self, path_sample, amount,
expected_clusters_length):
result_success = True
for _ in range(3):
try:
sample = read_sample(path_sample)
start_medoids = kmeans_plusplus_initializer(
sample, amount).initialize(return_index=True)
KmedoidsTestTemplates.templateLengthProcessData(
path_sample, start_medoids, expected_clusters_length,
False)
except AssertionError:
continue
break
assert result_success == True
def templateLengthProcessData(self, path_to_file, start_centers, expected_cluster_length, ccore = False):
sample = read_sample(path_to_file);
kmedians_instance = kmedians(sample, start_centers, 0.025, ccore);
kmedians_instance.process();
clusters = kmedians_instance.get_clusters();
obtained_cluster_sizes = [len(cluster) for cluster in clusters];
assert len(sample) == sum(obtained_cluster_sizes);
if (expected_cluster_length is not None):
obtained_cluster_sizes.sort();
expected_cluster_length.sort();
if (obtained_cluster_sizes != expected_cluster_length):
print(obtained_cluster_sizes);
assert obtained_cluster_sizes == expected_cluster_length;
def templateClusterAllocation(self, path, cluster_sizes, number_clusters, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.1, type_measurement = measurement_type.CENTROID_EUCLIDEAN_DISTANCE, entry_size_limit = 200, diameter_multiplier = 1.5):
sample = read_sample(path)
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, diameter_multiplier)
birch_instance.process()
clusters = birch_instance.get_clusters()
obtained_cluster_sizes = [len(cluster) for cluster in clusters]
total_length = sum(obtained_cluster_sizes)
self.assertEqual(total_length, len(sample))
if cluster_sizes is not None:
cluster_sizes.sort()
obtained_cluster_sizes.sort()
self.assertEqual(cluster_sizes, obtained_cluster_sizes)
def calculate_elbow(path_to_data, path_to_answer, kmin, kmax, ccore,
**kwargs):
repeat = 15 # Elbow method randomly chooses initial centers therefore we need to repeat test if it fails.
testing_result = False
kstep = kwargs.get('kstep', 1)
sample = read_sample(path_to_data)
expected_clusters_amount = None
if path_to_answer is not None:
if isinstance(path_to_answer, int):
expected_clusters_amount = path_to_answer
else:
expected_clusters_amount = len(
answer_reader(path_to_answer).get_clusters())
additional_info = []
for _ in range(repeat):
elbow_instance = elbow(sample, kmin, kmax, ccore=ccore, **kwargs)
elbow_instance.process()
actual_elbow = elbow_instance.get_amount()
actual_wce = elbow_instance.get_wce()
assertion.gt(actual_elbow, kmin)
assertion.lt(actual_elbow, kmax)
assertion.eq(len(actual_wce),
math.floor((kmax - kmin) / kstep + 1))
assertion.lt(actual_wce[-1], actual_wce[0] + 0.0000001)
if (expected_clusters_amount is not None) and (
actual_elbow != expected_clusters_amount):
additional_info.append(actual_elbow)
continue
testing_result = True
break
message = None
if expected_clusters_amount is not None:
message = str(expected_clusters_amount) + ": " + str(
additional_info)
assertion.true(testing_result, message=message)
def clustering(path, levels, density_threshold, expected_clusters,
expected_noise, ccore, **kwargs):
sample = read_sample(path)
amount_threshold = kwargs.get('amount_threshold', 0)
bang_instance = bang(sample,
levels,
ccore,
density_threshold=density_threshold,
amount_threshold=amount_threshold)
bang_instance.process()
clusters = bang_instance.get_clusters()
noise = bang_instance.get_noise()
directory = bang_instance.get_directory()
dendrogram = bang_instance.get_dendrogram()
assertion.eq(len(clusters), len(dendrogram))
obtained_length = len(noise)
obtained_cluster_length = []
for cluster in clusters:
obtained_length += len(cluster)
obtained_cluster_length.append(len(cluster))
obtained_cluster_length.sort()
assertion.eq(len(sample), obtained_length)
assertion.eq(expected_noise, len(noise))
if expected_clusters is not None:
assertion.eq(len(expected_clusters), len(clusters))
assertion.eq(expected_clusters, obtained_cluster_length)
leafs = directory.get_leafs()
covered_points = set()
for leaf in leafs:
points = leaf.get_points()
for index_point in points:
covered_points.add(index_point)
assertion.eq(len(sample), len(covered_points))
return bang_instance
def templateClusteringResults(self, path, radius, neighbors, amount_clusters, expected_length_clusters, ccore):
sample = read_sample(path);
optics_instance = optics(sample, radius, neighbors, amount_clusters);
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;
assert analyser.extract_cluster_amount(optics_instance.get_radius()) == len(expected_length_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 templateSeachNearestNodeInTree(self, sample_path, **kwargs):
numpy_usage = kwargs.get('numpy_usage', False)
sample = read_sample(sample_path)
if numpy_usage is True:
sample = numpy.array(sample)
tree = kdtree()
for point in sample:
node = tree.find_nearest_dist_node(point, 0.0)
assert node == None
tree.insert(point, None)
node = tree.find_nearest_dist_node(point, 0.0)
assert node != None
assert node.data is point
def testObserver(self):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2)
means, variances = ema_initializer(sample, 3).initialize(
ema_init_type.RANDOM_INITIALIZATION)
observer_instance = ema_observer()
ema_instance = ema(sample, 3, means, variances, observer_instance)
ema_instance.process()
observer_length = len(observer_instance)
assert observer_length > 0
assert observer_length == len(
observer_instance.get_evolution_clusters())
assert observer_length == len(
observer_instance.get_evolution_covariances())
assert observer_length == len(observer_instance.get_evolution_means())
assert observer_length == observer_instance.get_iterations()
def random_state_fixed(path_to_data, kmin, kmax, ccore, **kwargs):
repeat = kwargs.get('repeat', 1)
for _ in range(repeat):
sample = read_sample(path_to_data)
elbow_instance = elbow(sample, kmin, kmax, ccore=ccore,
**kwargs).process()
elbow_1 = elbow_instance.get_amount()
wce_1 = elbow_instance.get_wce()
elbow_instance = elbow(sample, kmin, kmax, ccore=ccore,
**kwargs).process()
elbow_2 = elbow_instance.get_amount()
wce_2 = elbow_instance.get_wce()
assertion.eq(elbow_1, elbow_2)
assertion.eq(wce_1, wce_2)
def templateClusteringResults(path,
number_clusters,
link,
expected_length_clusters,
ccore_flag=False):
sample = read_sample(path)
agglomerative_instance = agglomerative(sample, number_clusters, link,
ccore_flag)
agglomerative_instance.process()
clusters = agglomerative_instance.get_clusters()
assert sum([len(cluster) for cluster in clusters]) == len(sample)
assert sum([len(cluster)
for cluster in clusters]) == sum(expected_length_clusters)
assert sorted([len(cluster)
for cluster in clusters]) == expected_length_clusters