python中kmeans聚类实现

k-means算法思想较简单，说的通俗易懂点就是物以类聚，花了一点时间在python中实现k-means算法，k-means算法有本身的缺点，比如说k初始位置的选择，针对这个有不少人提出k-means++算法进行改进；另外一种是要对k大小的选择也没有很完善的理论，针对这个比较经典的理论是轮廓系数，二分聚类的算法确定k的大小，在最后还写了二分聚类算法的实现，代码主要参考机器学习实战那本书：

#encoding:utf-8
'''
Created on 2015年9月21日
@author: ZHOUMEIXU204
'''


path=u"D:\\Users\\zhoumeixu204\\Desktop\\python语言机器学习\\机器学习实战代码   python\\机器学习实战代码\\machinelearninginaction\\Ch10\\"
import  numpy  as np
def loadDataSet(fileName):  #读取数据
    dataMat=[]
    fr=open(fileName)
    for line  in fr.readlines():
        curLine=line.strip().split('\t')
        fltLine=map(float,curLine)
        dataMat.append(fltLine)
    return  dataMat
def  distEclud(vecA,vecB):    #计算距离
    return np.sqrt(np.sum(np.power(vecA-vecB,2)))
def randCent(dataSet,k):      #构建镞质心
    n=np.shape(dataSet)[1]
    centroids=np.mat(np.zeros((k,n)))
    for j in  range(n):
        minJ=np.min(dataSet[:,j])
        rangeJ=float(np.max(dataSet[:,j])-minJ)
        centroids[:,j]=minJ+rangeJ*np.random.rand(k,1)
    return centroids
dataMat=np.mat(loadDataSet(path+'testSet.txt'))
print(dataMat[:,0])


# 所有数都比-inf大
# 所有数都比+inf小
def  kMeans(dataSet,k,distMeas=distEclud,createCent=randCent):
    m=np.shape(dataSet)[0]
    clusterAssment=np.mat(np.zeros((m,2)))
    centroids=createCent(dataSet,k)
    clusterChanged=True
    while clusterChanged:
        clusterChanged=False
        for i in range(m):
            minDist=np.inf;minIndex=-1  #np.inf表示无穷大
            for j in range(k):
                distJI=distMeas(centroids[j,:],dataSet[i,:])
                if distJI
                    minDist=distJI;minIndex=j
            if clusterAssment[i,0]!=minIndex:clusterChanged=True
            clusterAssment[i,:]=minIndex,minDist**2
        print centroids
        for cent in range(k):
            ptsInClust=dataSet[np.nonzero(clusterAssment[:,0].A==cent)[0]]  #[0]这里取0是指去除坐标索引值，结果会有两个
            #np.nonzero函数，寻找非0元素的下标  nz=np.nonzero([1,2,3,0,0,4,0])结果为0,1,2
            centroids[cent,:]=np.mean(ptsInClust,axis=0)
        
    return  centroids,clusterAssment
myCentroids,clustAssing=kMeans(dataMat,4)  
print(myCentroids,clustAssing)  
    
#二分均值聚类(bisecting  k-means)
def   biKmeans(dataSet,k,distMeas=distEclud):
    m=np.shape(dataSet)[0]
    clusterAssment=np.mat(np.zeros((m,2)))
    centroid0=np.mean(dataSet,axis=0).tolist()[0]
    centList=[centroid0]
    for j in range(m):
        clusterAssment[j,1]=distMeas(np.mat(centroid0),dataSet[j,:])**2
    while (len(centList)
        lowestSSE=np.Inf
        for  i  in range(len(centList)):
            ptsInCurrCluster=dataSet[np.nonzero(clusterAssment[:,0].A==i)[0],:]
            centroidMat,splitClusAss=kMeans(ptsInCurrCluster,2,distMeas)
            sseSplit=np.sum(splitClusAss[:,1])
            sseNotSplit=np.sum(clusterAssment[np.nonzero(clusterAssment[:,0].A!=i)[0],1])
            print "sseSplit, and notSplit:",sseSplit,sseNotSplit
            if (sseSplit+sseNotSplit)
                bestCenToSplit=i
                bestNewCents=centroidMat
                bestClustAss=splitClusAss.copy()
                lowestSSE=sseSplit+sseNotSplit
        bestClustAss[np.nonzero(bestClustAss[:,0].A==1)[0],0]=len(centList)
        bestClustAss[np.nonzero(bestClustAss[:,0].A==0)[0],0]=bestCenToSplit
        print "the bestCentToSplit is:",bestCenToSplit
        print 'the len of  bestClustAss is:',len(bestClustAss)
        centList[bestCenToSplit]=bestNewCents[0,:]
        centList.append(bestNewCents[1,:])
        clusterAssment[np.nonzero(clusterAssment[:,0].A==bestCenToSplit)[0],:]=bestClustAss
    return centList,clusterAssment
print(u"二分聚类分析结果开始")
dataMat3=np.mat(loadDataSet(path+'testSet2.txt'))
centList,myNewAssments=biKmeans(dataMat3, 3)
print(centList)