def relative_validity_possibilistic(X):
''' Defines the several values of the possibilistic parameter. Then conducts successive executions of the algorithm by passing to it
those values and calculates all the proper relative indices.
Parameters:
X((N x m) numpy array): a data set of N instances and m features
Returns:
no_of_clusters_list: the different values of the clusters number
values_of_q: the different values of the q parameter
PC, PE, XB, FS: the arrays holding the values of the relative indices
'''
# Initialization
no_of_clusters_list = [i for i in range(2, 11)]
values_of_q = [1.25, 1.5, 1.75]
N = reduce(lambda x, y: x * y, X.shape[:-1])
m = X.shape[-1]
# Conversion to 2-D array
X = X.reshape(N, m)
# Initialize arrays to hold the indices. We use separate arrays for easier modification of the code if needed.
# If we wanted to use one array then this would be a 3 - dimensional array.
PC = np.zeros((len(no_of_clusters_list), len(values_of_q)))
PE = np.zeros((len(no_of_clusters_list), len(values_of_q)))
XB = np.zeros((len(no_of_clusters_list), len(values_of_q)))
FS = np.zeros((len(no_of_clusters_list), len(values_of_q)))
for i, total_clusters in tqdm(
enumerate(no_of_clusters_list)): # no_of_clusters
# IMPORTANT: The centroids must remain the same for every run of the algorithm with the same no_of_clusters
centroids_initial = np.random.choice(np.arange(np.min(X), np.max(X),
0.1),
size=(total_clusters, len(X[0])),
replace=False)
for j, q_value in enumerate(values_of_q): #edw vazw to q
# When X returns it has one more column that needs to be erased
X_, centroids, ita, centroids_history, partition_matrix = fuzzy_clustering.fuzzy(
X, total_clusters, centroids_initial, q=q_value)
X_, centroids, centroids_history, typicality_matrix = possibilistic_clustering.possibilistic(
X, total_clusters, ita, centroids_initial=centroids, q=q_value)
# Calculate indices
# In order to calculate indices we pass them the normalized typicality matrix, see Yang, Wu, Unsupervised possibilistic learning
typicality_matrix_norm = typicality_matrix / np.sum(
typicality_matrix, axis=1).reshape(len(X), 1)
PC[i, j] = partition_coefficient(X, typicality_matrix_norm)
PE[i, j] = partition_entropy(X, typicality_matrix_norm)
XB[i, j] = Xie_Beni(X, centroids, typicality_matrix_norm)
FS[i, j] = fukuyama_sugeno(X,
centroids,
typicality_matrix_norm,
q=2)
return no_of_clusters_list, values_of_q, PC, PE, XB, FS
def testBlobs(self):
no_of_clusters = 3
# Create the dataset
X, y = make_blobs(n_samples=100,
centers=no_of_clusters,
n_features=2,
random_state=None)
# Run the clustering algorithm. First run fuzzy clustering to get ita
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 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 testImageSegmentation(self):
image = ndimage.imread('..//..//images//181091.jpg')
image = image.astype(np.int32, copy = False)
# Algorithm execution.
clusters_number_to_execute = 28
clustered_data, centroids, total_clusters = BSAS.basic_sequential_scheme(image)
X_, centroids, ita, centroids_history, partition_matrix = fuzzy_clustering.fuzzy(image, clusters_number_to_execute, centroids_initial = centroids)
X_, centroids, centroids_history, typicality_matrix = possibilistic_clustering.possibilistic(image, clusters_number_to_execute, ita, centroids_initial = centroids)
###################################################################
# Merging procedure
X_ = image_segm_utility.merging_procedure(X_, 500)
# Calculate the Rand Index to test similarity to external data
original_image = '181091.jpg'
seg_file = '181091.seg'
external_info = image_segm_utility.insert_clusters(original_image, seg_file)
rand_index = image_segm_utility.rand_index_calculation(X_, external_info)
print(rand_index)
# Draw the clustered image
draw_clustered_image(X_, image.shape, rand_index)
plt.show()