def testBlobs(self):
no_of_clusters = 4
# Create the dataset
X, y = make_blobs(n_samples=500,
centers=no_of_clusters,
n_features=2,
random_state=185)
# Run the clustering algorithm but first run a sequential algorithm to obtain initial centroids
clustered_data, centroids, total_clusters = BSAS.basic_sequential_scheme(
X)
X, centroids, centroids_history = kmeans_clustering.kmeans(
X, no_of_clusters, centroids_initial=centroids)
# Plotting
plot_data(X, no_of_clusters, centroids, centroids_history)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, kmeans_clustering.kmeans)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, kmeans_clustering.kmeans)
# Histogram of gammas from internal criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testMoons(self):
no_of_clusters = 2
# Create the dataset
X, y = make_moons(n_samples=300,
shuffle=True,
noise=0.1,
random_state=10)
# Run the clustering algorithm
X, centroids, centroids_history = kmeans_clustering.kmeans(
X, no_of_clusters)
# Plotting
plot_data(X, no_of_clusters, centroids, centroids_history)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, kmeans_clustering.kmeans)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, kmeans_clustering.kmeans)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testMoons(self):
# Create the dataset
X, y = make_moons(n_samples=500,
shuffle=True,
noise=0.1,
random_state=121)
# Run the clustering algorithm
X, centroids, no_of_clusters = BSAS.basic_sequential_scheme(
X, threshold=1)
# Plotting
plot_data(X, no_of_clusters, centroids)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, BSAS.basic_sequential_scheme)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, BSAS.basic_sequential_scheme)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testBlobs(self):
no_of_clusters = 4
# Create the dataset
X, y = make_blobs(n_samples=500,
centers=no_of_clusters,
n_features=2,
random_state=352)
# Run the clustering algorithm but first run a sequential algorithm to obtain initial centroids
X_, no_of_clusters = DTA.minimum_spanning_tree_variation(X)
# Plotting
plot_data(X_, no_of_clusters)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X_, no_of_clusters, DTA.minimum_spanning_tree_variation)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X_, no_of_clusters, y, DTA.minimum_spanning_tree_variation)
# Histogram of gammas from internal criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testCircles(self):
# Create the dataset
X, y = make_circles(n_samples=500,
shuffle=True,
noise=0.07,
factor=0.27,
random_state=107)
# Run the clustering algorithm
X, no_of_clusters = DTA.minimum_spanning_tree_variation(X)
# Plotting
plot_data(X, no_of_clusters)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, DTA.minimum_spanning_tree_variation)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, DTA.minimum_spanning_tree_variation)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testMoons(self):
# Create the dataset
X, y = make_moons(n_samples=300,
shuffle=True,
noise=0.05,
random_state=10)
# Run the clustering algorithm
clusters_number_to_execute = 2
X, centroids, ita, centroids_history, partition_matrix = fuzzy_clustering.fuzzy(
X, no_of_clusters=clusters_number_to_execute)
# Plotting
plot_data(X, clusters_number_to_execute, centroids, centroids_history)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, clusters_number_to_execute, fuzzy_clustering.fuzzy)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, clusters_number_to_execute, y, fuzzy_clustering.fuzzy)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testBlobs(self):
no_of_clusters = 4
# Create the dataset
X, y = make_blobs(n_samples=500,
centers=no_of_clusters,
n_features=2,
random_state=46)
# Run the clustering algorithm
clusters_number_to_execute = 4
X, centroids, ita, centroids_history, partition_matrix = fuzzy_clustering.fuzzy(
X, no_of_clusters=clusters_number_to_execute)
# Plotting
plot_data(X, clusters_number_to_execute, centroids, centroids_history)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, clusters_number_to_execute, fuzzy_clustering.fuzzy)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, clusters_number_to_execute, y, fuzzy_clustering.fuzzy)
# Histogram of gammas from internal criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testMoons(self):
no_of_clusters = 2
# Create the dataset
X, y = make_moons(n_samples=300,
shuffle=True,
noise=0.1,
random_state=10)
# Run the clustering algorithm
X_, centroids, ita, centroids_history, partition_matrix = fuzzy_clustering.fuzzy(
X, no_of_clusters)
X, centroids, centroids_history, typicality_matrix = possibilistic_clustering.possibilistic(
X, no_of_clusters, ita, centroids_initial=centroids)
# Plotting
plot_data(X, centroids, no_of_clusters, centroids_history)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, possibilistic_clustering.possibilistic)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, possibilistic_clustering.possibilistic)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testBlobs(self):
no_of_clusters = 4
# Create the dataset
X, y = make_blobs(n_samples=500,
centers=no_of_clusters,
n_features=2,
random_state=124)
# Run the clustering algorithm
X, centroids, no_of_clusters = TTSS.two_threshold_sequential_scheme(
X, threshold1=3.20, threshold2=3.55)
# Plotting
plot_data(X, no_of_clusters, centroids)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(
X, no_of_clusters, TTSS.two_threshold_sequential_scheme)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(
X, no_of_clusters, y, TTSS.two_threshold_sequential_scheme)
# Histogram of gammas from internal criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testMoons(self):
# Create the dataset
X, y = make_moons(n_samples=500, shuffle = True, noise = 0.07, random_state = 10)
# Run the clustering algorithm
X, no_of_clusters = MST.minimum_spanning_tree(X, k = 3, f = 2.7)
# Plotting
plot_data(X, no_of_clusters)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(X, no_of_clusters, MST.minimum_spanning_tree)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(X, no_of_clusters, y, MST.minimum_spanning_tree)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
def testCircles(self):
no_of_clusters = 2
# Create the dataset
X, y = make_circles(n_samples=300, shuffle = True, noise = 0.05, factor = 0.5, random_state = 10)
# Run the clustering Algorithm
X, centroids, no_of_clusters = TTSS.two_threshold_sequential_scheme(X)
# Plotting
plot_data(X, centroids, no_of_clusters)
# Examine Cluster Validity with statistical tests
initial_gamma, list_of_gammas, result = internal_criteria.internal_validity(X, no_of_clusters , TTSS.two_threshold_sequential_scheme)
initial_indices, list_of_indices, result_list = external_criteria.external_validity(X, no_of_clusters, y, TTSS.two_threshold_sequential_scheme)
# Histogram of gammas from internal and external criteria
hist_internal_criteria(initial_gamma, list_of_gammas, result)
hist_external_criteria(initial_indices, list_of_indices, result_list)
plt.show()
