kMeans算法学习笔记（一）

#coding=utf-8
from numpy import *

#数据集的读取
def loadDataSet(fileName):
    dataMat=[]
    fr=open(fileName)
    for line in fr.readlines():
        currentLine=line.strip().split('\t')
        fltLine=map(float,currentLine)
        dataMat.append(fltLine)
    return dataMat

#计算欧氏距离
def distEclud(vecA,vecB):
    return sqrt(sum(power(vecA-vecB,2)))

#构建一个包含k个质心的集合
def randCent(dataSet,k):
    n=shape(dataSet)[1]
    centroids=mat(zeros((k,n)))
    for j in range(n):
        minJ=min(dataSet[:,j])
        rangeJ=float(max(dataSet[:,j])-minJ)
        centroids[:,j]=minJ+rangeJ*random.rand(k,1)
    return centroids

#k-均值聚类算法
def kMeans(dataSet,k,distMeas=distEclud,createCent=randCent):
    m=shape(dataSet)[0]
    clusterAssment=mat(zeros((m,2)))#一列存储簇索引值，一列存储误差
    centroids=createCent(dataSet,k)#随机产生质心
    clusterChanged=True
    while clusterChanged:#当簇分配发生改变时
        clusterChanged=False
        for i in range(m):#计算每一个点与质心的距离
            minDist=inf;
            minIndex=-1
            for j in range(k):
                distJI=distMeas(centroids[j,:],dataSet[i,:])
                if distJI<minDist:
                    minDist=distJI;minIndex=j
            if clusterAssment[i,0]!=minIndex:
                clusterChanged=True
            clusterAssment[i,:]=minIndex,minDist**2
        print centroids
        for cent in range(k):#更新质心的值
             ptsInClust=dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]
             centroids[cent,:]=mean(ptsInClust,axis=0)
    return centroids,clusterAssment

dataMat=mat(loadDataSet('testSet.txt'))
myCentroids,clustAssing=kMeans(dataMat,4)