机器学习实战 Kmeans

    

from numpy import *
from blaze import inf

def loadDataSet(filename):
    dataMat=[]
    fr=open(filename)
    for line in fr.readlines():
        curLine=line.strip().split('\t')
        fltLine=[float(s) for s 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))  #k个随机数
    return centroids

datMat=mat(loadDataSet('C:/Users/xuwei/Desktop/机器学习/机器学习实战(pdf版+源码)/machinelearninginaction/Ch10/testSet.txt'))

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', '<']
    axprops = dict(xticks=[], yticks=[])
    ax0=fig.add_axes(rect, label='ax0', **axprops)
    imgP = plt.imread('C:/Users/xuwei/Desktop/机器学习/机器学习实战(pdf版+源码)/machinelearninginaction/Ch10/Portland.png')
    ax0.imshow(imgP)
    ax1=fig.add_axes(rect, label='ax1', frameon=False)
    for i in range(numClust):
        ptsInCurrCluster = datMat[nonzero(clustAssing[:,0].A==i)[0],:]
        markerStyle = scatterMarkers[i % len(scatterMarkers)]
        ax1.scatter(ptsInCurrCluster[:,0].flatten().A[0], ptsInCurrCluster[:,1].flatten().A[0], marker=markerStyle, s=90)
    ax1.scatter(myCentroids[:,0].flatten().A[0], myCentroids[:,1].flatten().A[0], marker='+', s=300)
    plt.show()
    
clusterClubs()