000

import numpy as np

from random import random

from KMeans import load_data, kmeans, distance, save_result

 

FLOAT_MAX = 1e100 # 设置一个较大的值作为初始化的最小的距离

 

def nearest(point, cluster_centers):

min_dist = FLOAT_MAX

m = np.shape(cluster_centers)[0] # 当前已经初始化的聚类中心的个数

for i in xrange(m):

# 计算point与每个聚类中心之间的距离

d = distance(point, cluster_centers[i, ])

# 选择最短距离

if min_dist > d:

min_dist = d

return min_dist

 

def get_centroids(points, k):

m, n = np.shape(points)

cluster_centers = np.mat(np.zeros((k , n)))

# 1、随机选择一个样本点为第一个聚类中心

index = np.random.randint(0, m)

cluster_centers[0, ] = np.copy(points[index, ])

# 2、初始化一个距离的序列

d = [0.0 for _ in xrange(m)]

 

for i in xrange(1, k):

sum_all = 0

for j in xrange(m):

# 3、对每一个样本找到最近的聚类中心点

d[j] = nearest(points[j, ], cluster_centers[0:i, ])

# 4、将所有的最短距离相加

sum_all += d[j]

# 5、取得sum_all之间的随机值

sum_all *= random()

# 6、获得距离最远的样本点作为聚类中心点

for j, di in enumerate(d):

sum_all -= di

if sum_all > 0:

continue

cluster_centers[i] = np.copy(points[j, ])

break

return cluster_centers

 

if __name__ == "__main__":

k = 4#聚类中心的个数

file_path = "data.txt"

# 1、导入数据

print "---------- 1.load data ------------"

data = load_data(file_path)

# 2、KMeans++的聚类中心初始化方法

print "---------- 2.K-Means++ generate centers ------------"

centroids = get_centroids(data, k)

# 3、聚类计算

print "---------- 3.kmeans ------------"

subCenter = kmeans(data, k, centroids)

# 4、保存所属的类别文件

print "---------- 4.save subCenter ------------"

save_result("sub_pp", subCenter)

# 5、保存聚类中心

print "---------- 5.save centroids ------------"

save_result("center_pp", centroids)

其中，KMeans所在的文件为：

# coding:UTF-8

'''

Date:20160923

@author: zhaozhiyong

'''

import numpy as np

 

def load_data(file_path):

f = open(file_path)

data = []

for line in f.readlines():

row = [] # 记录每一行

lines = line.strip().split("\t")

for x in lines:

row.append(float(x)) # 将文本中的特征转换成浮点数

data.append(row)

f.close()

return np.mat(data)

 

def distance(vecA, vecB):

dist = (vecA - vecB) * (vecA - vecB).T

return dist[0, 0]

 

def randCent(data, k):

n = np.shape(data)[1] # 属性的个数

centroids = np.mat(np.zeros((k, n))) # 初始化k个聚类中心

for j in xrange(n): # 初始化聚类中心每一维的坐标

minJ = np.min(data[:, j])

rangeJ = np.max(data[:, j]) - minJ

# 在最大值和最小值之间随机初始化

centroids[:, j] = minJ * np.mat(np.ones((k , 1))) + np.random.rand(k, 1) * rangeJ

return centroids

 

def kmeans(data, k, centroids):

m, n = np.shape(data) # m：样本的个数，n：特征的维度

subCenter = np.mat(np.zeros((m, 2))) # 初始化每一个样本所属的类别

change = True # 判断是否需要重新计算聚类中心

while change == True:

change = False # 重置

for i in xrange(m):

minDist = np.inf # 设置样本与聚类中心之间的最小的距离，初始值为争取穷

minIndex = 0 # 所属的类别

for j in xrange(k):

# 计算i和每个聚类中心之间的距离

dist = distance(data[i, ], centroids[j, ])

if dist < minDist:

minDist = dist

minIndex = j

# 判断是否需要改变

if subCenter[i, 0] <> minIndex: # 需要改变

change = True

subCenter[i, ] = np.mat([minIndex, minDist])

# 重新计算聚类中心

for j in xrange(k):

sum_all = np.mat(np.zeros((1, n)))

r = 0 # 每个类别中的样本的个数

for i in xrange(m):

if subCenter[i, 0] == j: # 计算第j个类别

sum_all += data[i, ]

r += 1

for z in xrange(n):

try:

centroids[j, z] = sum_all[0, z] / r

except:

print " r is zero"

return subCenter

 

def save_result(file_name, source):

m, n = np.shape(source)

f = open(file_name, "w")

for i in xrange(m):

tmp = []

for j in xrange(n):

tmp.append(str(source[i, j]))

f.write("\t".join(tmp) + "\n")

f.close()