机器学习python-Kmeans

K-均值聚类算法

首先，随机确定k个初始点作为质心，然后将数据集中的每个点分配到一个簇中，即为每个点找距其最近的质心，并将其分配给该质心对应的簇，然后每个簇的质心更新为该簇所有点的平均值。算法流程如下：

创建K个点作为起始质心（一般随机选择）
任意一个点所属簇的结果发生改变时
    对数据集中每个点
        对每个质心
            计算数据与质心间的距离
        将数据划分到与它最近的簇
    对于每个簇，重新计算质心（所有点的均值）

二分K-均值算法

首先将所有点作为一个簇，然后将该簇一分为二，之后选择其中一个簇继续划分，选择哪一个簇取决于是否可以很大程度降低SSE（误差平方和）的值，循环直到得到指定的簇。算法流程如下：

将所有点看成一个簇
当簇数目小于k时
    对于每一个簇
        计算总误差
        在给定的簇上面进行K均值聚类（K=2）
        计算将该簇一分为二之后的总误差
    选择使得误差最小的那个簇进行划分操作

from numpy import *
def loadDataSet(filename):
    dataMat = []
    fr = open(filename)
    for line in fr.readlines():
        curLine = line.strip().split('\t')
        fltLine = [float(x) for x in curLine]
        dataMat.append(fltLine)
    return dataMat
def distEclud(vecA,vecB):
    return sqrt(sum(power(vecA - vecB, 2)))
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] = mat(minJ + rangeJ * random.rand(k,1))
    return centroids
def kMeans(dataSet,k,distMeas=distEclud,createCent=randCent):
    m = shape(dataSet)[0]
    clusterAssment = mat(zeros((m,2)))
    centroids = createCent(dataSet,k)
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False
        for i in range(m):
            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):
            ptsInClust = dataSet[nonzero(clusterAssment[:,0].A == cent)[0]]
            centroids[cent,:] = mean(ptsInClust,axis=0)
    return centroids,clusterAssment
def biKmeans(dataSet,k,distMeas=distEclud):
    m = shape(dataSet)[0]
    clusterAssment = mat(zeros((m,2)))
    centorid0 = mean(dataSet,axis=0).tolist()[0]
    centList = [centorid0]
    for j in range(m):
        clusterAssment[j,1] = distMeas(mat(centorid0),dataSet[j,:])**2
    while (len(centList) < k):
        lowestSSE = inf
        for i in range(len(centList)):
            ptsIncurrCluster = dataSet[nonzero(clusterAssment[:,0].A == i)[0],:]
            centroidMat,splitClustAss = kMeans(ptsIncurrCluster,2,distMeas)
            sseSplit = sum(splitClustAss[:,1])
            sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A != i)[0],1])
            print(sseSplit,sseNotSplit)
            if (sseSplit + sseNotSplit) < lowestSSE:
                bestCentToSplit = i
                bestNewCents = centroidMat
                bestClustAss = splitClustAss.copy()
                lowestSSE = sseNotSplit + sseSplit
        bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList)
        bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
        centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]
        centList.append(bestNewCents[1,:])
        clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:] = bestClustAss
    return mat(centList),clusterAssment
dataSet = mat(loadDataSet('testSet.txt'))
a,b = biKmeans(dataSet,3)