python代码大全k_python-k中心聚类代码

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

"""

Created on Mon Feb 18 14:59:53 2019

@author: Administrator

"""

#from pyclust import KMedoids #保留，用于切换函数

import numpy as np

from sklearn.manifold import TSNE

import matplotlib.pyplot as plt

import random

def im_txt(file):

"""

读取数据

"""

data=np.loadtxt(file,dtype=np.float32)

return data

def out_txt(outfile,line):

f=open(outfile,"w")

try:

for i in line:

f.write(str(i))

f.write("\n")

f.close()

except:

f.close()

print("分类数据未保存！！！！")

def initianlize_centers(n_clusters):

"""初始化，生成随机聚类中心"""

global n_data

centers=[] #聚类中心位置信息例：[101,205,5,3,7]

i=0

while i

temp=random.randint(0,n_data-1)

if temp not in centers:

centers.append(temp)

i=i+1

else:

pass

return centers

def clus_process(centers,data):

"""根据聚类中心进行聚类"""

result_clusters=[]

centers=np.array(centers)

"""遍历每个样本"""

for i in range(0,len(data)):

uni_temp=[] #临时存储距离数据

for j in centers:

temp=np.sqrt(np.sum(np.square(data[i]-data[j])))

uni_temp.append(temp)

c_min=min(uni_temp) #距离最小值

result_clusters.append(uni_temp.index(c_min)) #距离最小值所在位置即为归属簇

return result_clusters

def chose_centers(result_clusters,n_clusters):

centers=[]

for i in range(0,n_clusters): #逐个簇进行随机

temp=[] #记录每个簇样本在data中的位置

for j in range(0,len(result_clusters)): #遍历每个样本

if result_clusters[j]==i: #寻找簇i的样本

temp.append(j)

try:

c_temp=random.sample(temp,1) #在样本中随机取一个值作为新的聚类中心

except:

print("sample bug")

print(temp)

centers.append(c_temp[0])

return centers

def count_E(centers_new,data,result_clusters_new):

"""计算价值函数"""

E=0

for i in range(0,len(centers_new)):

for j in range(0,len(data)):

if result_clusters_new[j]==i:

temp=np.sqrt(np.sum(np.square(data[j]-data[centers_new[i]])))

E+=temp

return E

def KMedoids(n_clusters,data,max_iter):

"""初始化"""

centers=initianlize_centers(n_clusters)

"""根据随机中心进行聚类"""

result_clusters=clus_process(centers,data)

"""重新选择聚类中心,并比较"""

xie=0 #计数器

E=5*5000

"""

_old：用来记录上一次的聚类结果

_new：新一次聚类的结果

无old和new：输出结果

"""

while xie<=max_iter:

centers_new=chose_centers(result_clusters,n_clusters) #新的聚类中心

result_clusters_new=clus_process(centers,data) #新的聚类结果

"""计算价值函数E"""

E_new=count_E(centers_new,data,result_clusters_new)

"""价值函数变小，则更新聚类中心和聚类结果"""

if E_new

centers=centers_new

result_clusters=result_clusters_new

E=E_new

print("价值函数为:%s"%E)

print("聚类中心:%s"%centers)

xie=0

"""阈值计数器"""

xie=xie+1

if xie%10==0 and xie!=0:

print(xie)

return centers,result_clusters

def randomcolor(x):

"""随机生成十六进制编码"""

colors=[]

i=0

while i

colorArr = ['1','2','3','4','5','6','7','8','9','A','B','C','D','E','F']

color = ""

j=0

while j<6:

color += colorArr[random.randint(0,14)]

j=j+1

color="#"+color

if color in colors:

continue

else:

colors.append(color)

i=i+1

return colors

def main():

global n_data

file="text.txt"

data=im_txt(file)

n_data=len(data)

'''准备可视化需要的降维数据'''

data_TSNE = TSNE(learning_rate=100,n_iter=5000).fit_transform(data)

'''对不同的k进行试探性K-medoids聚类并可视化'''

plt.figure(figsize=(12,8))

"""聚类数"""

k=18 ###

centers,result_clusters = KMedoids(k,data,10) ###

color=randomcolor(k)

colors = ([color[k] for k in result_clusters])

plt.subplot(222)

plt.rcParams['figure.dpi'] = 300

plt.scatter(data_TSNE[:,0],data_TSNE[:,1],s=10,c=colors)

plt.title('K-medoids Resul of '.format(str(k)))

out_txt("分类数数(ture).txt",result_clusters)

main()