import numpy as np
import matplotlib.pyplot as plt
from GMM import GMM
if __name__ == '__main__':
group_a = np.random.normal(loc=(20.00, 14.00), scale=(4.0, 4.0), size=(1000, 2))
group_b = np.random.normal(loc=(15.00, 8.00), scale=(2.0, 2.0), size=(1000, 2))
group_c = np.random.normal(loc=(30.00, 40.00), scale=(2.0, 2.0), size=(1000, 2))
group_d = np.random.normal(loc=(25.00, 32.00), scale=(7.0, 7.0), size=(1000, 2))
data = np.concatenate((group_a, group_b, group_c, group_d))
g = GMM(n_components=4)
eval_train = g.train(data)
for c in g.components:
print '*****'
print c.mean
print c.cov
plt.plot(eval_train)
plt.show()
chapter9 EM algorithm for Gaussian Misture Model
Using iris dataset for clustering
"""
import DatasetUtil as DS
from HTMLTable import HTMLTable
import re
from GMM import GMM
if __name__ == "__main__":
print("\t============ Chap9 EM for GMM ============")
ds = DS.DATAUtil()
x_train, y_train = ds.load(True, r".\dataset.dat")
model = GMM()
model.train(x_train)
y_pred = model.predict(x_train)
y_train = ds.y_int2str(y_train)
table = HTMLTable(caption='Iris Data Cluster')
table.append_header_rows((
('No.', 'A1', 'A2', 'A3', 'A4', 'Classification', ''),
('', '', '', '', '', 'Label-C', 'Predict-C'),
))
table[0][0].attr.rowspan = 2
table[0][1].attr.rowspan = 2
table[0][2].attr.rowspan = 2
table[0][3].attr.rowspan = 2
table[0][4].attr.rowspan = 2
table[0][5].attr.colspan = 2
marker='o')
ax.scatter(real_data[0][(N[0] + N[1]):, 0],
real_data[0][(N[0] + N[1]):, 1],
real_data[0][(N[0] + N[1]):, 2],
c='orange',
marker='o')
ax.text2D(0.05, 0.95, "Original Clusters", transform=ax.transAxes)
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z')
plt.show()
#Fitting model
GMM_model = GMM(dim=3, num_clusters=3)
GMM_model.train(real_data[0], 10**(-10))
#Showing the predicted clusters
assignments = (real_data[0],
np.argmax(np.apply_along_axis(GMM_model.resp, 1, real_data[0]),
axis=1))
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(assignments[0][np.where(assignments[1] == 0), 0],
assignments[0][np.where(assignments[1] == 0), 1],
assignments[0][np.where(assignments[1] == 0), 2],
c='green',
marker='o')
ax.scatter(assignments[0][np.where(assignments[1] == 1), 0],
