数据分析——K聚类

import cv2
import numpy as np
import matplotlib.pyplot as plt

# 创建2个25*2数组
X = np.random.randint(25,50,(25,2))
Y = np.random.randint(60,85,(25,2))
# 按行顺序堆叠数组
Z = np.vstack((X,Y))

# convert to np.float32
Z = np.float32(Z)

# 迭代次数为10次，精确度为1.0
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
# 聚类个数为2，起始中心选择方式包括cv2.KMEANS_RANDOM_CENTERS和cv2.KMEANS_PP_CENTERS
ret,label,center=cv2.kmeans(Z,2,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)

A = Z[label.ravel()==0]
B = Z[label.ravel()==1]

# Plot the data
plt.scatter(A[:,0],A[:,1],c = 'b')
plt.scatter(B[:,0],B[:,1],c = 'r')
plt.scatter(center[:,0],center[:,1],s = 80,c = 'y', marker = 's')
plt.xlabel('x'),plt.ylabel('y')
plt.show()