#50 Clustering using python

import os
import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import norm
from numpy import array,vstack
from scipy.cluster.vq import vq,kmeans
#from mpl_toolkits.mplot3d import Axes3D
os.chdir(r'D:\projects\wordpress\ex50')
os.getcwd()
# generate data
data=norm.rvs(0,0.3,size=(10000,2))
inside_ball=np.hypot(data[:,0],data[:,1])<1.0
data=data[inside_ball]
data = vstack((data, data+array([1,1]),data+array([-1,1])))
#request the data to be separated into three clusters
centroids, distortion = kmeans(data,3)
cluster_assignment, distances = vq(data,centroids)
plt.plot(data[cluster_assignment==0,0], data[cluster_assignment==0,1], 'r.')
plt.plot(data[cluster_assignment==1,0], data[cluster_assignment==1,1], 'g.')
plt.plot(data[cluster_assignment==2,0], data[cluster_assignment==2,1], 'b.')
plt.savefig("example50.png", dpi=100)
plt.show()
plt.close()