K-means聚类的Python实现

 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Wed Dec  6 16:01:17 2017
 4 
 5 @author: zxzhu
 6 """
 7 import numpy as np
 8 import matplotlib.pyplot as plt
 9 from numpy import random
10 
11 def Distance(x):
12     def Dis(y):
13         return np.sqrt(sum((x-y)**2))                      #欧式距离
14     return Dis
15 
16 def init_k_means(k):
17     k_means = {}
18     for i in range(k):
19         k_means[i] = []
20     return k_means
21 
22 def cal_seed(k_mean):                                      #重新计算种子点
23     k_mean = np.array(k_mean)
24     new_seed = np.mean(k_mean,axis=0)                      #各维度均值
25     return new_seed
26     
27 def K_means(data,seed_k,k_means):
28     for i in data:
29         f = Distance(i)
30         dis = list(map(f,seed_k))                        #某一点距所有种子点的距离
31         index = dis.index(min(dis))
32         k_means[index].append(i)
33     
34     new_seed = []                                           #存储新种子
35     for i in range(len(seed_k)):
36         new_seed.append(cal_seed(k_means[i]))
37     new_seed = np.array(new_seed)
38     return k_means,new_seed
39     
40 def run_K_means(data,k):
41     seed_k = data[random.randint(len(data),size=k)]       #随机产生种子点
42     k_means = init_k_means(k)                                #初始化每一类
43     result = K_means(data,seed_k,k_means)
44     count = 0
45     while not (result[1] == seed_k).all():                     #种子点改变，继续聚类
46         count+=1
47         seed_k = result[1]
48         k_means = init_k_means(k=7)   
49         result = K_means(data,seed_k,k_means)
50     print(‘Done‘)
51     #print(result[1])
52     print(count)
53     plt.figure(figsize=(8,8))
54     Color = ‘rbgyckm‘
55     for i in range(k):
56         mydata = np.array(result[0][i])
57         plt.scatter(mydata[:,0],mydata[:,1],color = Color[i])
58     return result[0]
59 
60 data = np.loadtxt(‘K-means_data‘)
61 run_K_means(data,k=7)