def random_state(kmin, kmax, algorithm, random_state, ccore_flag):
sample = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE4)
ksearch_instance_1 = silhouette_ksearch(sample,
kmin,
kmax,
algorithm=algorithm,
random_state=random_state,
ccore=ccore_flag).process()
ksearch_instance_2 = silhouette_ksearch(sample,
kmin,
kmax,
algorithm=algorithm,
random_state=random_state,
ccore=ccore_flag).process()
assertion.eq(ksearch_instance_1.get_amount(),
ksearch_instance_2.get_amount())
assertion.eq(ksearch_instance_1.get_score(),
ksearch_instance_2.get_score())
assertion.eq(len(ksearch_instance_1.get_scores()),
len(ksearch_instance_2.get_scores()))
scores1 = ksearch_instance_1.get_scores()
scores2 = ksearch_instance_2.get_scores()
for key in scores1:
key = int(key)
if math.isnan(scores1[key]) and math.isnan(scores2[key]):
continue
else:
assertion.eq(scores1[key], scores2[key])
def correct_ksearch(sample_path, answer_path, kmin, kmax, algorithm,
ccore_flag):
attempts = 15
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 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 find_best_k(samples):
search_instance = silhouette_ksearch(samples, 2, 10, algorithm=silhouette_ksearch_type.KMEDOIDS).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
print(f"Best Silhouette Score for k = {amount}: {scores[amount]}")
return amount
def find_best_k(samples):
logging.info("Searching best k for clustering.")
search_instance = silhouette_ksearch(samples, 2, 10, algorithm=silhouette_ksearch_type.KMEDOIDS).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
logging.info(f"Best Silhouette Score for k = {amount}: {scores[amount]}")
return amount
def use_experiment_with_pyclustering_kmedoids(file):
TimingLogger.start('pyclustering.kmedoids', 'kmedoids')
x = read_matrix(file)
X = np.array(x)
clusters = len(x)
search_instance = silhouette_ksearch(
X, 2, clusters, algorithm=silhouette_ksearch_type.KMEDOIDS).process()
scores = search_instance.get_scores()
for i in range(2, len(scores)):
logging.info('For n_clusters = ' + str(i) +
' The average silhouette_score is : ' +
str(scores[i - 2]))
logging.info('Better choice is ' + str(search_instance.get_amount()) +
' clusters')
TimingLogger.stop('pyclustering.kmedoids')
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 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_correct_ksearch(self, sample_path, answer_path, kmin, kmax,
algorithm):
attempts = 5
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).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))
if amount != len(clusters): continue
testing_result = True
break
assertion.true(testing_result)
from pyclustering.cluster.kmeans import kmeans
from pyclustering.cluster.silhouette import silhouette
from pyclustering.cluster.silhouette import silhouette_ksearch_type, silhouette_ksearch
from pyclustering.utils.metric import distance_metric, type_metric
# Prepare initial centers
centers = kmeans_plusplus_initializer(data, 4).initialize()
manhattan_metric = distance_metric(type_metric.MANHATTAN)
kmeans_instance = kmeans(data, centers, metric = manhattan_metric)
kmeans_instance.process()
clusters = kmeans_instance.get_clusters()
# # Calculate Silhouette score
# score = silhouette(data, clusters).process().get_score()
# %%
search_instance = silhouette_ksearch(data, 2, 10, algorithm=silhouette_ksearch_type.KMEANS).process()
amount = search_instance.get_amount()
scores = search_instance.get_scores()
print("Scores: '%s'" % str(scores))
#%%
scores
# %%
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(2, 10, 1)