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 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), len(links));
index_canvas = 0;
if (type_link.CENTROID_LINK in links):
agglomerative_centroid_link = agglomerative(sample, number_clusters, type_link.CENTROID_LINK, True);
(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 template_clustering(
start_centers,
path,
tolerance=0.025,
criterion=splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore=False):
sample = read_sample(path)
start = time.clock()
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion,
ccore)
(ticks, _) = timedcall(xmeans_instance.process)
# clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
end = time.clock()
print(end - start)
criterion_string = "UNKNOWN"
if criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION:
criterion_string = "BAYESIAN INFORMATION CRITERION"
elif criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH:
criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH"
print("Sample: ", ntpath.basename(path), "\nInitial centers: '",
(start_centers is not None), "', Execution time: '", ticks,
"', Number of clusters:", len(centers), ",", criterion_string, "\n")
def planTrace_clustering(start_medoids,
data_points,
tolerance=0.25,
show=False):
"""
:param start_medoids: is a list of indices, which correspond to the medoids
:param data_points:
:param tolerance:
:param show:
:return:
"""
# todo note start mediods is represented by the data point index
chosen_metric = metric.distance_metric(metric.type_metric.MANHATTAN)
kmedoids_instance = kmedoids(data_points,
start_medoids,
tolerance,
metric=chosen_metric)
(ticks, result) = timedcall(kmedoids_instance.process)
print("execution time in ticks = ", ticks)
clusters = kmedoids_instance.get_clusters()
medoids = kmedoids_instance.get_medoids()
print("----finished clustering")
# if show is True:
# visualizer = cluster_visualizer_multidim()
# visualizer.append_clusters(clusters, data_points, 0)
# visualizer.append_cluster([data_points[index] for index in start_medoids], marker='*', markersize=15)
# visualizer.append_cluster(medoids, data=data_points, marker='*', markersize=15)
# visualizer.show()
return clusters, medoids
def cluster(number_clusters, iterations, maxneighbours):
data = read_sample('data.data')
m_clarans = clarans(data, number_clusters, iterations, maxneighbours)
(ticks, result) = timedcall(m_clarans.process)
print("Execution time: ", ticks, "\n")
clusters = m_clarans.get_clusters()
draw_clusters(data, clusters)
def template_clustering(
number_clusters,
path,
branching_factor=5,
max_node_entries=5,
initial_diameter=0.0,
type_measurement=measurement_type.AVERAGE_INTER_CLUSTER_DISTANCE,
entry_size_limit=200,
diameter_multiplier=1.5,
show_result=True):
sample = read_sample(path)
birch_instance = birch(sample, number_clusters, branching_factor,
max_node_entries, initial_diameter,
type_measurement, entry_size_limit,
diameter_multiplier)
(ticks, result) = timedcall(birch_instance.process)
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
clusters = birch_instance.get_clusters()
if (show_result is True):
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
return (sample, clusters)
def template_clustering(
start_centers,
path,
tolerance=0.025,
criterion=splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore=False):
sample = read_sample(path)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion,
ccore)
(ticks, result) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION):
criterion_string = "BAYESIAN_INFORMATION_CRITERION"
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH):
criterion_string = "MINIMUM_NOISELESS_DESCRIPTION_LENGTH"
print("Sample: ", path, "\nInitial centers: '",
(start_centers is not None), "', Execution time: '", ticks,
"', Number of clusters:", len(clusters), ",", criterion_string, "\n")
draw_clusters(sample, clusters)
def template_clustering(
start_centers,
path,
tolerance=0.025,
criterion=splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore=True):
sample = read_sample(path)
xmeans_instance = xmeans(sample,
start_centers,
20,
tolerance,
criterion,
ccore,
repeat=5)
(ticks, _) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION):
criterion_string = "BAYESIAN INFORMATION CRITERION"
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH):
criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH"
print("Sample: ", ntpath.basename(path), "\nInitial centers: '",
(start_centers is not None), "', Execution time: '", ticks,
"', Number of clusters:", len(clusters), ",", criterion_string, "\n")
visualizer = cluster_visualizer()
visualizer.set_canvas_title(criterion_string)
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(centers, None, marker='*')
visualizer.show()
def clustering_random_points(amount, ccore):
sample = [ [ random.random(), random.random() ] for _ in range(amount) ]
dbscan_instance = dbscan(sample, 0.05, 20, ccore)
(ticks, _) = timedcall(dbscan_instance.process)
print("Execution time ("+ str(amount) +" 2D-points):", ticks)
def template_clustering_random_points_performance(cluster_length,
amount_clusters, ccore_flag):
sample = [[random.random(), random.random()]
for _ in range(cluster_length)]
for index in range(1, amount_clusters):
default_offset = 5
sample += [[
random.random() + default_offset * index,
random.random() + default_offset * index
] for _ in range(cluster_length)]
initial_center = [[random.random(), random.random()],
[random.random(), random.random()]]
ticks_array = []
amount_measures = 5
for _ in range(amount_measures):
xmeans_instance = xmeans(sample, initial_center, 20, 0.25,
splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore_flag)
(ticks, _) = timedcall(xmeans_instance.process)
ticks_array.append(ticks)
print(
"Random sample: (size:" + str(len(sample)) + ") ', Execution time: '",
sum(ticks_array) / amount_measures)
def experiment_execution_one_cluster_dependence(layer_first_size, radius,
order):
print("Experiment: map size =", layer_first_size[0] * layer_first_size[1],
"radius =", radius, "order =", order)
cluster_sizes = [
10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150
]
for cluster_size in cluster_sizes:
# generate data sets
dataset = []
dataset += [[random(), random()] for _ in range(cluster_size)]
general_value = 0.0
amount_attempt = 5
for _ in range(amount_attempt):
network = syncsom(dataset, layer_first_size[0],
layer_first_size[1], radius)
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, False,
order)
general_value += ticks
print("Sample: ", cluster_size, "\t\tExecution time: ",
general_value / float(amount_attempt))
print("\n")
def template_clustering(start_medoids, path, tolerance=0.25, show=True):
sample = read_sample(path)
metric = distance_metric(type_metric.EUCLIDEAN_SQUARE, data=sample)
kmedoids_instance = kmedoids(sample,
start_medoids,
tolerance,
metric=metric)
(ticks, result) = timedcall(kmedoids_instance.process)
clusters = kmedoids_instance.get_clusters()
medoids = kmedoids_instance.get_medoids()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if show is True:
visualizer = cluster_visualizer(1)
visualizer.append_clusters(clusters, sample, 0)
visualizer.append_cluster([sample[index] for index in start_medoids],
marker='*',
markersize=15)
visualizer.append_cluster(medoids,
data=sample,
marker='*',
markersize=15)
visualizer.show()
return sample, clusters
def process_kmedoids(sample):
instance = kmedoids(sample, [
CURRENT_CLUSTER_SIZE * multiplier
for multiplier in range(NUMBER_CLUSTERS)
])
(ticks, _) = timedcall(instance.process)
return ticks
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 process_xmeans(sample):
instance = xmeans(
sample, [[random() + (multiplier * 5),
random() + (multiplier + 5)]
for multiplier in range(NUMBER_CLUSTERS)])
(ticks, _) = timedcall(instance.process)
return ticks
def template_clustering(
start_centers,
path,
tolerance=0.025,
criterion=splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore=False):
sample = read_sample(
'/home/tengmo/crawler_to_server_set_time/crawler/source_code_python2.7/cluster/test.txt'
)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion,
ccore)
(ticks, result) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION):
criterion_string = "BAYESIAN INFORMATION CRITERION"
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH):
criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH"
#print("Sample: ", path, "\nInitial centers: '", (start_centers is not None), "', Execution time: '", ticks, "', Number of clusters:", len(clusters), ",", criterion_string, "\n");
print {'length': len(clusters), 'clus': clusters, 'cen': centers}
def template_clustering(start_centers, path, tolerance=0.25, ccore=False):
sample = read_sample(path)
dimension = len(sample[0])
metric = distance_metric(type_metric.MANHATTAN)
observer = kmeans_observer()
kmeans_instance = kmeans(sample,
start_centers,
tolerance,
ccore,
observer=observer,
metric=metric)
(ticks, _) = 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_multidim()
visualizer.append_clusters(clusters, sample)
visualizer.show()
if dimension > 3:
kmeans_visualizer.show_clusters(sample, clusters, centers,
start_centers)
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def template_clustering(file,
radius,
order,
show_dyn=False,
show_conn=False,
show_clusters=True,
ena_conn_weight=False,
ccore_flag=True,
tolerance=0.1):
sample = read_sample(file)
network = syncnet(sample,
radius,
enable_conn_weight=ena_conn_weight,
ccore=ccore_flag)
(ticks, analyser) = timedcall(network.process, order, solve_type.FAST,
show_dyn)
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n")
if (show_dyn == True):
sync_visualizer.show_output_dynamic(analyser)
sync_visualizer.animate(analyser)
#sync_visualizer.animate_output_dynamic(analyser);
#sync_visualizer.animate_correlation_matrix(analyser, colormap = 'hsv');
if ((show_conn == True) and (ccore_flag == False)):
network.show_network()
if (show_clusters == True):
clusters = analyser.allocate_clusters(tolerance)
print("amout of clusters: ", len(clusters))
draw_clusters(sample, clusters)
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 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 clustering_random_points(amount, ccore):
sample = [[random.random(), random.random()] for _ in range(amount)]
optics_instance = optics(sample, 0.05, 20, None, ccore)
(ticks, _) = timedcall(optics_instance.process)
print("Execution time (" + str(amount) + " 2D-points):", ticks)
def template_clustering(number_clusters,
path,
number_represent_points=5,
compression=0.5,
draw=True,
ccore_flag=False):
sample = read_sample(path)
cure_instance = cure(sample, number_clusters, number_represent_points,
compression, ccore_flag)
(ticks, _) = timedcall(cure_instance.process)
clusters = cure_instance.get_clusters()
representors = cure_instance.get_representors()
means = cure_instance.get_means()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
#print([len(cluster) for cluster in clusters])
if draw is True:
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 clustering_random_points(amount, ccore):
sample = [ [ random.random(), random.random() ] for _ in range(amount) ];
dbscan_instance = dbscan(sample, 0.05, 20, ccore);
(ticks, _) = timedcall(dbscan_instance.process);
print("Execution time ("+ str(amount) +" 2D-points):", ticks);
def template_clustering(number_clusters,
path,
number_represent_points=5,
compression=0.5,
draw=True,
ccore_flag=False):
sample = read_sample(path)
cure_instance = cure(sample, number_clusters, number_represent_points,
compression, ccore_flag)
(ticks, _) = timedcall(cure_instance.process)
clusters = cure_instance.get_clusters()
representors = cure_instance.get_representors()
means = cure_instance.get_means()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if (draw is True):
visualizer = cluster_visualizer()
if (ccore_flag is True):
visualizer.append_clusters(clusters, sample)
else:
visualizer.append_clusters(clusters, None)
visualizer.append_clusters(representors, marker='*', markersize=10)
visualizer.append_clusters([means], None, marker='o')
visualizer.show()
def template_clustering(radius,
neighb,
path,
invisible_axes=False,
ccore=True,
show=True):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighb, ccore)
(ticks, _) = timedcall(dbscan_instance.process)
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
print([len(cluster) for cluster in clusters])
if show:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker='x')
visualizer.show()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
return sample, clusters, noise
def clustering_random_points(amount_points, amount_centers, ccore):
sample = [ [ random.random(), random.random() ] for _ in range(amount_points) ]
centers = [ [ random.random(), random.random() ] for _ in range(amount_centers) ]
kmeans_instance = kmeans(sample, centers, 0.0001, ccore)
(ticks, _) = timedcall(kmeans_instance.process)
print("Execution time ("+ str(amount_points) +" 2D-points):", ticks)
def clustering_random_points(amount_points, amount_centers, ccore):
sample = [ [ random.random(), random.random() ] for _ in range(amount_points) ]
centers = [ [ random.random(), random.random() ] for _ in range(amount_centers) ]
kmeans_instance = kmeans(sample, centers, 0.0001, ccore)
(ticks, _) = timedcall(kmeans_instance.process)
print("Execution time ("+ str(amount_points) +" 2D-points):", ticks)
def template_clustering(number_clusters, path, iterations, maxneighbors):
sample = read_sample(path);
clarans_instance = clarans(sample, number_clusters, iterations, maxneighbors);
(ticks, result) = timedcall(clarans_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = clarans_instance.get_clusters();
draw_clusters(sample, clusters);
def template_clustering(number_clusters, path, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.0, type_measurement = measurement_type.CENTROID_EUCLIDIAN_DISTANCE, entry_size_limit = 200, ccore = True):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, ccore);
(ticks, result) = timedcall(birch_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = birch_instance.get_clusters();
draw_clusters(sample, clusters);
def template_clustering(number_clusters, path, iterations, maxneighbors):
sample = read_sample(path);
clarans_instance = clarans(sample, number_clusters, iterations, maxneighbors);
(ticks, result) = timedcall(clarans_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = clarans_instance.get_clusters();
draw_clusters(sample, clusters);
def template_clustering(number_clusters, path, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.0, type_measurement = measurement_type.CENTROID_EUCLIDIAN_DISTANCE, entry_size_limit = 200, ccore = True):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, ccore)
(ticks, result) = timedcall(birch_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = birch_instance.get_clusters();
draw_clusters(sample, clusters);
def template_clustering(start_medians, path, tolerance=0.25):
sample = read_sample(path)
kmedians_instance = kmedians(sample, start_medians, tolerance)
(ticks, result) = timedcall(kmedians_instance.process)
clusters = kmedians_instance.get_clusters()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
draw_clusters(sample, clusters)
def template_clustering(start_centers, path, tolerance = 0.25):
sample = read_sample(path);
kmedians_instance = kmedians(sample, start_centers, tolerance);
(ticks, result) = timedcall(kmedians_instance.process);
clusters = kmedians_instance.get_clusters();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
draw_clusters(sample, clusters);
def template_clustering_performance(start_centers, path, tolerance = 0.025, criterion = splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore = False):
sample = read_sample(path)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion, ccore)
(ticks, _) = timedcall(xmeans_instance.process)
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION): criterion_string = "BAYESIAN INFORMATION CRITERION";
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH): criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH";
print("Sample: ", ntpath.basename(path), "', Execution time: '", ticks, "',", criterion_string)
def template_clustering_performance(start_centers, path, tolerance = 0.025, criterion = splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore = False):
sample = read_sample(path)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion, ccore)
(ticks, _) = timedcall(xmeans_instance.process)
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION): criterion_string = "BAYESIAN INFORMATION CRITERION";
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH): criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH";
print("Sample: ", ntpath.basename(path), "', Execution time: '", ticks, "',", criterion_string)
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 template_segmentation_image(source, map_som_size = [5, 5], radius = 128.0, sync_order = 0.998, show_dyn = False, show_som_map = False):
data = read_image(source);
network = syncsom(data, map_som_size[0], map_som_size[1], 1.0);
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, show_dyn, sync_order);
print("Sample: ", source, "\t\tExecution time: ", ticks, "\t\tWinners: ", network.som_layer.get_winner_number(), "\n");
if (show_dyn is True):
draw_dynamics(dyn_time, dyn_phase);
clusters = network.get_clusters();
draw_image_mask_segments(source, clusters);
def template_segmentation_image(source, map_som_size = [5, 5], average_neighbors = 5, sync_order = 0.998, show_dyn = False, show_som_map = False):
data = read_image(source);
network = syncsom(data, map_som_size[0], map_som_size[1]);
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, average_neighbors, show_dyn, sync_order);
print("Sample: ", source, "\t\tExecution time: ", ticks, "\t\tWinners: ", network.som_layer.get_winner_number(), "\n");
if (show_dyn is True):
draw_dynamics(dyn_time, dyn_phase);
clusters = network.get_clusters();
draw_image_mask_segments(source, clusters);
def template_clustering(path, amount_clusters, epouch=100, ccore=True):
sample = read_sample(path)
somsc_instance = somsc(sample, amount_clusters, epouch, ccore)
(ticks, _) = timedcall(somsc_instance.process)
clusters = somsc_instance.get_clusters()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.show()
def template_clustering(file, number_clusters, arg_order = 0.999, arg_collect_dynamic = True, ccore_flag = False):
sample = read_sample(file);
network = hsyncnet(sample, number_clusters, initial_neighbors = int(len(sample) * 0.15), osc_initial_phases = initial_type.EQUIPARTITION, ccore = ccore_flag);
(ticks, analyser) = timedcall(network.process, arg_order, solve_type.FAST, arg_collect_dynamic);
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n");
clusters = analyser.allocate_clusters();
if (arg_collect_dynamic == True):
sync_visualizer.show_output_dynamic(analyser);
draw_clusters(sample, clusters);
def template_clustering(number_clusters, path, number_represent_points = 5, compression = 0.5, draw = True, ccore_flag = False):
sample = read_sample(path);
cure_instance = cure(sample, number_clusters, number_represent_points, compression, ccore_flag);
(ticks, result) = timedcall(cure_instance.process);
clusters = cure_instance.get_clusters();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
if (draw is True):
if (ccore_flag is True):
draw_clusters(sample, clusters);
else:
draw_clusters(None, clusters);
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = True):
sample = read_sample(path);
dbscan_instance = dbscan(sample, radius, neighb, ccore);
(ticks, result) = timedcall(dbscan_instance.process);
clusters = dbscan_instance.get_clusters();
noise = dbscan_instance.get_noise();
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.append_cluster(noise, sample, marker = 'x');
visualizer.show();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
def template_clustering(start_medoids, path, tolerance = 0.25, show = True):
sample = read_sample(path);
kmedoids_instance = kmedoids(sample, start_medoids, tolerance);
(ticks, result) = timedcall(kmedoids_instance.process);
clusters = kmedoids_instance.get_clusters();
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
if (show is True):
visualizer = cluster_visualizer(1);
visualizer.append_clusters(clusters, sample, 0);
visualizer.show();
return (sample, clusters);
def template_clustering(start_centers, path, tolerance = 0.025, criterion = splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore = False):
sample = read_sample(path);
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion, ccore);
(ticks, result) = timedcall(xmeans_instance.process);
clusters = xmeans_instance.get_clusters();
criterion_string = "UNKNOWN";
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION): criterion_string = "BAYESIAN_INFORMATION_CRITERION";
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH): criterion_string = "MINIMUM_NOISELESS_DESCRIPTION_LENGTH";
print("Sample: ", path, "\tExecution time: ", ticks, "Number of clusters: ", len(clusters), criterion_string, "\n");
draw_clusters(sample, clusters);
def template_clustering(number_clusters, path, branching_factor = 5, max_node_entries = 5, initial_diameter = 0.0, type_measurement = measurement_type.AVERAGE_INTER_CLUSTER_DISTANCE, entry_size_limit = 200, diameter_multiplier = 1.5, show_result = True):
sample = read_sample(path);
birch_instance = birch(sample, number_clusters, branching_factor, max_node_entries, initial_diameter, type_measurement, entry_size_limit, diameter_multiplier);
(ticks, result) = timedcall(birch_instance.process);
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n");
clusters = birch_instance.get_clusters();
if (show_result is True):
visualizer = cluster_visualizer();
visualizer.append_clusters(clusters, sample);
visualizer.show();
return (sample, 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 template_clustering(file, radius, order, show_dyn = False, show_conn = False, show_clusters = True, ena_conn_weight = False, ccore_flag = True, tolerance = 0.1):
sample = read_sample(file);
network = syncnet(sample, radius, enable_conn_weight = ena_conn_weight, ccore = ccore_flag);
(ticks, analyser) = timedcall(network.process, order, solve_type.FAST, show_dyn);
print("Sample: ", file, "\t\tExecution time: ", ticks, "\n");
if (show_dyn == True):
sync_visualizer.show_output_dynamic(analyser);
sync_visualizer.animate_output_dynamic(analyser);
if ( (show_conn == True) and (ccore_flag == False) ):
network.show_network();
if (show_clusters == True):
clusters = analyser.allocate_clusters(tolerance);
draw_clusters(sample, clusters);
def template_clustering(start_medoids, path, tolerance = 0.25, show = True):
sample = read_sample(path)
kmedoids_instance = kmedoids(sample, start_medoids, tolerance)
(ticks, result) = timedcall(kmedoids_instance.process)
clusters = kmedoids_instance.get_clusters()
medoids = kmedoids_instance.get_medoids()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
if show is True:
visualizer = cluster_visualizer(1)
visualizer.append_clusters(clusters, sample, 0)
visualizer.append_cluster([sample[index] for index in start_medoids], marker='*', markersize=15)
visualizer.append_cluster(medoids, data=sample, marker='*', markersize=15)
visualizer.show()
return sample, clusters
def experiment_execution_one_cluster_dependence(layer_first_size, radius, order):
print("Experiment: map size =", layer_first_size[0] * layer_first_size[1], "radius =", radius, "order =", order);
cluster_sizes = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150];
for cluster_size in cluster_sizes:
# generate data sets
dataset = [];
dataset += [ [random(), random()] for _ in range(cluster_size) ];
general_value = 0.0;
amount_attempt = 5;
for _ in range(amount_attempt):
network = syncsom(dataset, layer_first_size[0], layer_first_size[1], radius);
(ticks, (dyn_time, dyn_phase)) = timedcall(network.process, False, order);
general_value += ticks;
print("Sample: ", cluster_size, "\t\tExecution time: ", general_value / float(amount_attempt));
print("\n");
def template_clustering_random_points_performance(cluster_length, amount_clusters, ccore_flag):
sample = [ [ random.random(), random.random() ] for _ in range(cluster_length) ]
for index in range(1, amount_clusters):
default_offset = 5
sample += [ [ random.random() + default_offset * index, random.random() + default_offset * index ] for _ in range(cluster_length) ]
initial_center = [ [ random.random(), random.random() ], [ random.random(), random.random() ] ]
xmeans_instance = xmeans(sample, initial_center, 20, 0.25, splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore_flag)
ticks_array = []
amount_measures = 5
for _ in range(amount_measures):
xmeans_instance = xmeans(sample, initial_center, 20, 0.25, splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore_flag)
(ticks, _) = timedcall(xmeans_instance.process)
ticks_array.append(ticks)
print("Random sample: (size:" + str(len(sample)) + ") ', Execution time: '", sum(ticks_array) / amount_measures)
def template_clustering(start_centers, path, tolerance = 0.025, criterion = splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore = False):
sample = read_sample(path)
xmeans_instance = xmeans(sample, start_centers, 20, tolerance, criterion, ccore)
(ticks, _) = timedcall(xmeans_instance.process)
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
criterion_string = "UNKNOWN"
if (criterion == splitting_type.BAYESIAN_INFORMATION_CRITERION): criterion_string = "BAYESIAN INFORMATION CRITERION";
elif (criterion == splitting_type.MINIMUM_NOISELESS_DESCRIPTION_LENGTH): criterion_string = "MINIMUM NOISELESS DESCRIPTION_LENGTH";
print("Sample: ", ntpath.basename(path), "\nInitial centers: '", (start_centers is not None), "', Execution time: '", ticks, "', Number of clusters:", len(clusters), ",", criterion_string, "\n")
visualizer = cluster_visualizer()
visualizer.set_canvas_title(criterion_string)
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(centers, None, marker = '*')
visualizer.show()
def template_clustering(radius, neighb, path, invisible_axes = False, ccore = True, show = True):
sample = read_sample(path)
dbscan_instance = dbscan(sample, radius, neighb, ccore)
(ticks, _) = timedcall(dbscan_instance.process)
clusters = dbscan_instance.get_clusters()
noise = dbscan_instance.get_noise()
print([len(cluster) for cluster in clusters])
if show:
visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(noise, sample, marker = 'x')
visualizer.show()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
return sample, clusters, noise
def template_clustering(start_centers, path, tolerance = 0.25, ccore = False):
sample = read_sample(path)
dimension = len(sample[0])
metric = distance_metric(type_metric.MANHATTAN)
observer = kmeans_observer()
kmeans_instance = kmeans(sample, start_centers, tolerance, ccore, observer=observer, metric=metric)
(ticks, _) = 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_multidim()
visualizer.append_clusters(clusters, sample)
visualizer.show()
if dimension > 3:
kmeans_visualizer.show_clusters(sample, clusters, centers, start_centers)
kmeans_visualizer.animate_cluster_allocation(sample, observer)
def template_clustering(number_clusters, path, number_represent_points=5, compression=0.5, draw=True, ccore_flag=True):
sample = read_sample(path)
cure_instance = cure(sample, number_clusters, number_represent_points, compression, ccore_flag)
(ticks, _) = timedcall(cure_instance.process)
clusters = cure_instance.get_clusters()
representors = cure_instance.get_representors()
means = cure_instance.get_means()
print("Sample: ", path, "\t\tExecution time: ", ticks, "\n")
#print([len(cluster) for cluster in clusters])
if draw is True:
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 template_clustering(file, radius, order, show_dyn = False, show_conn = False, show_clusters = True, ena_conn_weight = False, ccore_flag = True, tolerance = 0.1):
sample = read_sample(file)
syncnet_instance = syncnet(sample, radius, enable_conn_weight = ena_conn_weight, ccore = ccore_flag)
(ticks, analyser) = timedcall(syncnet_instance.process, order, solve_type.FAST, show_dyn)
print("Sample: ", file, "\t\tExecution time: ", ticks)
if show_dyn == True:
sync_visualizer.show_output_dynamic(analyser)
sync_visualizer.animate(analyser)
sync_visualizer.show_local_order_parameter(analyser, syncnet_instance)
#sync_visualizer.animate_output_dynamic(analyser);
#sync_visualizer.animate_correlation_matrix(analyser, colormap = 'hsv')
if show_conn == True:
syncnet_instance.show_network()
if show_clusters == True:
clusters = analyser.allocate_clusters(tolerance)
print("Amount of allocated clusters: ", len(clusters))
draw_clusters(sample, clusters)
print("----------------------------\n")
return (sample, clusters)
def template_segmentation_image(source, color_radius, object_radius, noise_size, show_dyn):
data = read_image(source);
print("Pixel dimension: ", len(data[0]));
network = syncnet(data, color_radius, ccore = True);
print("Network has been created");
(ticks, analyser) = timedcall(network.process, 0.9995, solve_type.FAST, show_dyn);
print("Sample: ", source, "\t\tExecution time: ", ticks, "\n");
if (show_dyn is True):
sync_visualizer.show_output_dynamic(analyser);
clusters = analyser.allocate_clusters();
real_clusters = [cluster for cluster in clusters if len(cluster) > noise_size];
draw_image_mask_segments(source, real_clusters);
if (object_radius is None):
return;
# continue analysis
pointer_image = Image.open(source);
image_size = pointer_image.size;
object_colored_clusters = [];
object_colored_dynamics = [];
total_dyn = [];
for cluster in clusters:
coordinates = [];
for index in cluster:
y = floor(index / image_size[0]);
x = index - y * image_size[0];
coordinates.append([x, y]);
print(coordinates);
# perform clustering analysis of the colored objects
if (network is not None):
del network;
network = None;
if (len(coordinates) < noise_size):
continue;
network = syncnet(coordinates, object_radius, ccore = True);
analyser = network.process(0.999, solve_type.FAST, show_dyn);
if (show_dyn is True):
object_colored_dynamics.append( (analyser.time, analyser.output) );
object_clusters = analyser.allocate_clusters();
# decode it
real_description_clusters = [];
for object_cluster in object_clusters:
real_description = [];
for index_object in object_cluster:
real_description.append(cluster[index_object]);
real_description_clusters.append(real_description);
if (len(real_description) > noise_size):
object_colored_clusters.append(real_description);
# draw_image_mask_segments(source, [ cluster ]);
# draw_image_mask_segments(source, real_description_clusters);
draw_image_mask_segments(source, object_colored_clusters);
if (show_dyn is True):
draw_dynamics_set(object_colored_dynamics, None, None, None, [0, 2 * 3.14], False, False);
def process_syncnet(sample):
instance = syncnet(sample, 3.0, initial_phases = initial_type.EQUIPARTITION)
(ticks, _) = timedcall(instance.process)
return ticks
def process_syncsom(sample):
instance = syncsom(sample, 1, NUMBER_CLUSTERS)
(ticks, _) = timedcall(instance.process, 0, False, 0.998)
return ticks
def process_xmeans(sample):
instance = xmeans(sample, [ [random() + (multiplier * 5), random() + (multiplier + 5)] for multiplier in range(NUMBER_CLUSTERS) ])
(ticks, _) = timedcall(instance.process)
return ticks