K-means聚类的Python实现

生物信息学原理作业第五弹：K-means聚类的实现。

转载请保留出处！

K-means聚类的Python实现

原理参考：K-means聚类（上）

数据是老师给的，二维，2 * 3800的数据。plot一下可以看到有7类。

怎么确定分类个数我正在学习，这个脚本就直接给了初始分类了，等我学会了再发。

下面贴上Python代码，版本为Python3.6。

 # -*- coding: utf-8 -*-

 """

 Created on Wed Dec  6 16:01:17 2017

 @author: zxzhu

 """

 import numpy as np

 import matplotlib.pyplot as plt

 from numpy import random

 def Distance(x):

     def Dis(y):

         return np.sqrt(sum((x-y)**2))                      #欧式距离

     return Dis

 def init_k_means(k):

     k_means = {}

     for i in range(k):

         k_means[i] = []

     return k_means

 def cal_seed(k_mean):                                      #重新计算种子点

     k_mean = np.array(k_mean)

     new_seed = np.mean(k_mean,axis=0)                      #各维度均值

     return new_seed

 def K_means(data,seed_k,k_means):

     for i in data:

         f = Distance(i)

         dis = list(map(f,seed_k))                        #某一点距所有种子点的距离

         index = dis.index(min(dis))

         k_means[index].append(i)

     new_seed = []                                           #存储新种子

     for i in range(len(seed_k)):

         new_seed.append(cal_seed(k_means[i]))

     new_seed = np.array(new_seed)

     return k_means,new_seed

 def run_K_means(data,k):

     seed_k = data[random.randint(len(data),size=k)]       #随机产生种子点

     k_means = init_k_means(k)                                #初始化每一类

     result = K_means(data,seed_k,k_means)

     count = 0

     while not (result[1] == seed_k).all():                     #种子点改变，继续聚类

         count+=1

         seed_k = result[1]

         k_means = init_k_means(k=7)

         result = K_means(data,seed_k,k_means)

     print('Done')

     #print(result[1])

     print(count)

     plt.figure(figsize=(8,8))

     Color = 'rbgyckm'

     for i in range(k):

         mydata = np.array(result[0][i])

         plt.scatter(mydata[:,0],mydata[:,1],color = Color[i])

     return result[0]

 data = np.loadtxt('K-means_data')

 run_K_means(data,k=7)   

附上结果图：

这个算法太依赖于初始种子点的选取了，随机选点很有可能会得到局部最优的结果，所以下一步学习一下怎么设置初始种子点以及分类数目。