def main():
# declare variables
K_value = 3
max_epoch = 1000
repeat_num = 8
repeat_num_gmm = 1
name = 'GMM_dataset.txt'
# get the training data
training_data = data_loading(name)
if (sys.argv[1] == 'kmean'):
# run the K-mean program
program_name = './a.out'
parameter_line = ' ' + 'training_kmeans ' + str(K_value) + ' ' + str(
repeat_num) + ' 0'
print('Running K-mean')
os.system(program_name + parameter_line)
print('The Program is done.')
# read minimum SSE Position
min_sse_pos = np.loadtxt('./min_sse_pos.csv',
delimiter=',',
skiprows=0)
# read clusters from K-mean algorithm
kmean_name = './all_cluster_center' + str(int(min_sse_pos)) + '.csv'
kmean_clusters = np.loadtxt(kmean_name, delimiter=',', skiprows=0)
for draw_ind in range(int(kmean_clusters.shape[0] / K_value)):
# the last index: (int(kmean_clusters.shape[0] / K_value) - 1)
start_index = draw_ind * K_value
iter_kmean_clusters = kmean_clusters[start_index:start_index +
K_value, :]
# label assignment
out_label, cov_list = label_assignment(iter_kmean_clusters,
training_data)
# save the figures
plt.rcParams.update({'figure.max_open_warning': 0})
fig, ax = plt.subplots()
ax.scatter(training_data[:, 0],
training_data[:, 1],
c=out_label,
alpha=0.5)
ax.scatter(iter_kmean_clusters[:, 0],
iter_kmean_clusters[:, 1],
c='b',
s=100,
alpha=0.5)
plt.xlabel('Feature: x1')
plt.ylabel('Feature: x2')
plt.title('K-mean Clustering')
fig.savefig('./kmean_result/iter' + str(draw_ind) + '.png')
#fig.clf()
elif (sys.argv[1] == 'gmm'):
# read minimum SSE Position
min_sse_pos = np.loadtxt('./min_sse_pos.csv',
delimiter=',',
skiprows=0)
# read clusters from K-mean algorithm
kmean_name = './all_cluster_center' + str(int(min_sse_pos)) + '.csv'
kmean_clusters = np.loadtxt(kmean_name, delimiter=',', skiprows=0)
start_index = (int(kmean_clusters.shape[0] / K_value) - 1) * K_value
iter_kmean_clusters = kmean_clusters[start_index:start_index +
K_value, :]
out_label, cov_list = label_assignment(iter_kmean_clusters,
training_data)
# call GMM class
gmm = GMM(K_value, repeat_num_gmm, max_epoch, training_data)
all_likelihood, parameters = gmm.model_training(
iter_kmean_clusters, out_label, cov_list)
true_mu, true_covariance = gmm.fit_true_model(training_data)
# find the mu, covariance, and prior
best_likelihood, all_mu, all_cov, all_prior = find_the_best(
all_likelihood, parameters)
# prediction phase
prediction = gmm.model_predict(all_mu[-1], all_cov[-1], all_prior[-1],
training_data)
labels = label_GMM(prediction)
# drawing gaussian functions
for ind in range(len(all_mu)):
out_para = drawing_Gaussian(all_mu[ind], all_cov[ind],
training_data, all_mu[-1], 1, ind)
if ind == (len(all_mu) - 1):
# print out parameters of the Gaussian function
for ind_2 in range(K_value):
print('Cluster:', ind_2)
print('Mu:')
print(out_para[str(ind_2)][0])
print('Covariance:')
print(out_para[str(ind_2)][1])
print('=====================')
# drawing true gaussian functions
if K_value == 3:
out_param_true = drawing_Gaussian(true_mu, true_covariance,
training_data, true_mu, 2, None)
# print out parameters of the Gaussian function
for ind_3 in range(K_value):
print('Cluster:', ind_3)
print('Actual Mu:')
print(out_param_true[str(ind_3)][0])
print('Actual Covariance:')
print(out_param_true[str(ind_3)][1])
print('=====================')
# drawing log-likelihood values
drawing_Log_likelihood(best_likelihood)
elif (sys.argv[1] == 'saving'):
# save the data as a csv file
save_data_csv_file(training_data)
else:
print('Error Input. Please re-choose the task!!')
