def templateRandomCenterInitializer(self, data, amount):
centers = random_center_initializer(data, amount).initialize()
self.assertEqual(amount, len(centers))
for center in centers:
self.assertEqual(len(data[0]), len(center))
def templateMaxAllocatedClusters(ccore_flag, amount_clusters, size_cluster,
offset, kinitial, kmax):
input_data = []
for index in range(amount_clusters):
for _ in range(size_cluster):
input_data.append([
random.random() * index * offset,
random.random() * index * offset
])
initial_centers = random_center_initializer(input_data,
kinitial).initialize()
xmeans_instance = xmeans(input_data, initial_centers, kmax, 0.025,
splitting_type.BAYESIAN_INFORMATION_CRITERION,
ccore_flag)
xmeans_instance.process()
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
if len(clusters) != len(centers):
print(input_data)
print(initial_centers)
assertion.ge(kmax, len(clusters))
assertion.ge(kmax, len(centers))
assertion.eq(len(clusters), len(centers))
def templateRandomCenterInitializer(self, data, amount):
centers = random_center_initializer(data, amount).initialize()
self.assertEqual(amount, len(centers))
for center in centers:
self.assertEqual(len(data[0]), len(center))
def random_state(ccore_flag, kinitial, kmax, random_state):
data = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE5)
initial_centers = random_center_initializer(data, kinitial, random_state=random_state).initialize()
xmeans_instance1 = xmeans(data, initial_centers, kmax, ccore=ccore_flag, random_state=random_state).process()
xmeans_instance2 = xmeans(data, initial_centers, kmax, ccore=ccore_flag, random_state=random_state).process()
assertion.eq(xmeans_instance1.get_total_wce(), xmeans_instance2.get_total_wce())
assertion.eq(xmeans_instance1.get_centers(), xmeans_instance2.get_centers())
assertion.eq(xmeans_instance1.get_clusters(), xmeans_instance2.get_clusters())
def templateMaxAllocatedClusters(ccore_flag, amount_clusters, size_cluster, offset, kinitial, kmax):
input_data = [];
for index in range(amount_clusters):
input_data.append([random.random() * index * offset, random.random() * index * offset]);
initial_centers = random_center_initializer(input_data, kinitial).initialize();
xmeans_instance = xmeans(input_data, initial_centers, kmax, 0.025, splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore_flag);
xmeans_instance.process();
clusters = xmeans_instance.get_clusters();
centers = xmeans_instance.get_centers();
assert kmax >= len(clusters);
assert kmax >= len(centers);
assert len(clusters) == len(centers);
def templateMaxAllocatedClusters(ccore_flag, amount_clusters, size_cluster, offset, kinitial, kmax):
input_data = []
for index in range(amount_clusters):
for _ in range(size_cluster):
input_data.append([random.random() * index * offset, random.random() * index * offset])
initial_centers = random_center_initializer(input_data, kinitial).initialize()
xmeans_instance = xmeans(input_data, initial_centers, kmax, 0.025, splitting_type.BAYESIAN_INFORMATION_CRITERION, ccore_flag)
xmeans_instance.process()
clusters = xmeans_instance.get_clusters()
centers = xmeans_instance.get_centers()
if len(clusters) != len(centers):
print(input_data)
print(initial_centers)
assertion.ge(kmax, len(clusters))
assertion.ge(kmax, len(centers))
assertion.eq(len(clusters), len(centers))
def __create_pyclustering_model(self,
model_name,
model_instance,
k_val):
if model_name == "K-Medoids":
model = model_instance(self.__scaled,
[i for i in
self.__get_unique_random_indexes(
k_val)])
elif model_name == "Somsc" or model_name == "Cure":
model = model_instance(self.__scaled,
k_val)
elif model_name == "K-Means" or model_name == "Fuzzy C-means":
initial_centers = kmeans_plusplus_initializer(self.__scaled, k_val).initialize()
model = model_instance(self.__scaled, initial_centers)
else:
# Create instance of K-Means algorithm with prepared centers.
initial_centers = random_center_initializer(self.__scaled,
k_val).initialize()
model = model_instance(self.__scaled, initial_centers)
return model
