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 x_means(X, num_init_clusters=8, visualize=True):
from pyclustering.cluster.kmeans import kmeans, kmeans_visualizer
from pyclustering.cluster.xmeans import xmeans
from pyclustering.cluster import cluster_visualizer
from pyclustering.cluster.center_initializer import kmeans_plusplus_initializer
from pyclustering.cluster import cluster_visualizer_multidim
X = list(X)
start_centers = kmeans_plusplus_initializer(
X, num_init_clusters).initialize()
xmeans_instance = xmeans(X, start_centers, 32, ccore=True, criterion=0)
# Run cluster analysis and obtain results.
xmeans_instance.process()
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
print('Number of cluster centers calculated :', len(centers))
if visualize:
visualizer = cluster_visualizer_multidim()
visualizer.append_clusters(clusters, X)
visualizer.show()
return centers, clusters
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_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_visualize_adding_step_by_step(self, path_sample, path_answer, filter=None, **kwargs):
data = read_sample(path_sample)
clusters = answer_reader(path_answer).get_clusters()
visualizer = cluster_visualizer_multidim()
for cluster in clusters:
visualizer.append_cluster(cluster, data)
visualizer.show(filter, **kwargs)
def template_visualize(self, path_sample, path_answer, filter=None, **kwargs):
return_type = kwargs.get('return_type', 'list')
data = read_sample(path_sample, return_type=return_type)
clusters = answer_reader(path_answer).get_clusters()
visualizer = cluster_visualizer_multidim()
visualizer.append_clusters(clusters, data)
visualizer.show(filter, **kwargs)
def template_visualize_adding_step_by_step(self, path_sample, path_answer, filter=None, **kwargs):
data = read_sample(path_sample)
clusters = answer_reader(path_answer).get_clusters()
visualizer = cluster_visualizer_multidim()
for cluster in clusters:
visualizer.append_cluster(cluster, data)
visualizer.show(filter, **kwargs)
def template_clustering(start_centers, path):
sample = read_sample(path)
fcm_instance = fcm(sample, start_centers)
fcm_instance.process()
clusters = fcm_instance.get_clusters()
centers = fcm_instance.get_centers()
membership = fcm_instance.get_membership()
visualizer = cluster_visualizer_multidim()
visualizer.append_clusters(clusters, sample)
visualizer.append_cluster(centers, marker='*', markersize=10)
visualizer.show()
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)
# Sample for cluster analysis.
# sample = read_sample(FCPS_SAMPLES.SAMPLE_CHAINLINK)
sample = read_sample(FAMOUS_SAMPLES.SAMPLE_IRIS)
lines = open("t4.8k", "r")
inp = []
for line in lines:
cords = line.split()
if len(cords) != 2:
continue
inp.append([float(cords[0]), float(cords[1])])
# print(inp)
# Create DBSCAN algorithm.
dbscan_instance = dbscan(inp, 5, 3)
# dbscan_instance = dbscan(sample, 5, 3)
# Start processing by DBSCAN.
dbscan_instance.process()
# Obtain results of clustering.
clusters = dbscan_instance.get_clusters()
# noise = dbscan_instance.get_noise()
# Visualize clustering results
visualizer = cluster_visualizer_multidim()
# visualizer = cluster_visualizer()
visualizer.append_clusters(clusters, inp, marker='o')
# visualizer.append_clusters(clusters, sample, marker='o')
# visualizer.append_cluster(noise, inp, marker='x')
visualizer.show()
