机器学习实战（10） ——K均值聚类算法（python实现）

这是学习机器学习算法实战这本书时，写的代码实战。让自己对各个算法有更直观的了解，不能一直不写啊。不管简单还是不简单都亲自一行一行的敲一遍啊。

具体的源码和和数据链接：https://pan.baidu.com/s/1G2S2pb5gfBnxGNNTFgTkEA 密码：fov0

这个第十章的代码和自己做的测试kMeans.py .这章代码较少，但后面的调用雅虎接口一直调不通。

# -*- coding: utf-8 -*-
# author: Yufeng Song
from numpy import*
import matplotlib.pyplot as plt
def loadDataSet(fileName):      #general function to parse tab -delimited floats
    dataMat = []                #assume last column is target value
    dataMat = genfromtxt(fileName,delimiter="\t",dtype=float)#可以用这一行代替
    # fr = open(fileName)
    # for line in fr.readlines():
    #     curLine = line.strip().split('\t')
    #     # fltLine = map(float,curLine) #map all elements to float()
    #     # dataMat.append(fltLine)
    #     temp = [] #这一行为我自己加的
    #     curLine = line.strip().split('\t')
    #     #fltLine = map(float, curLine) #书上代码
    #     temp.append(float(curLine[0]))
    #     temp.append(float(curLine[1]))
    #     dataMat.append(temp)
    #     genfromtxt("bikeSpeedVsIq_test.txt",delimiter="\t",dtype=float)
    return dataMat

def distEclud(vecA, vecB):
    return sqrt(sum(power(vecA - vecB, 2))) #la.norm(vecA-vecB)

def randCent(dataSet, k):
    n = shape(dataSet)[1]
    centroids = mat(zeros((k,n)))#create centroid mat
    for j in range(n):#create random cluster centers, within bounds of each dimension
        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)))#create mat to assign data points
                                      #to a centroid, also holds SE of each point
    centroids = createCent(dataSet, k)
    clusterChanged = True
    while clusterChanged:
        clusterChanged = False
        for i in range(m):#for each data point assign it to the closest centroid
            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):#recalculate centroids
            ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster
            centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean
    return centroids, clusterAssment

def showCluster(dataSet, k, centroids, clusterAssment):
    m, dim = shape(dataSet)
    if dim != 2:
        print ("Sorry! i can not draw because the dimension of data is not 2!")
        return 1

    mark = ['or','ob','og','ok','^r','+r','sr','dr','<r','pr']
    if k > len(mark):
        print ("Sorry! Your k is too large!")
        return 1
    #draw all samples
    for i in range(m):
        markIndex = int(clusterAssment[i,0]) #为样本指定颜色
        plt.plot(dataSet[i,0], dataSet[i,1], mark[markIndex])

    mark = ['Dr', 'Db', 'Dg', 'Dk', '^b', '+b', 'sb', 'db', '<b', 'pb']
    #draw the centroids
    for i in range(k):
        plt.plot(centroids[i,0], centroids[i,1], mark[i],marker= '+',color = 'red',markersize=18)
        #用marker来指定质心样式，用color和markersize来指定颜色和大小

    plt.show()


def biKmeans(dataSet, k, distMeas=distEclud):
    m = shape(dataSet)[0]
    clusterAssment = mat(zeros((m,2)))
    centroid0 = mean(dataSet, axis=0).tolist()[0]
    centList =[centroid0] #create a list with one centroid
    for j in range(m):#calc initial Error
        clusterAssment[j,1] = distMeas(mat(centroid0), dataSet[j,:])**2
    while (len(centList) < k):
        lowestSSE = inf
        for i in range(len(centList)):
            ptsInCurrCluster = dataSet[nonzero(clusterAssment[:,0].A==i)[0],:]#get the data points currently in cluster i
            centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
            sseSplit = sum(splitClustAss[:,1])#compare the SSE to the currrent minimum
            sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A!=i)[0],1])
            print ("sseSplit, and notSplit: ",sseSplit,sseNotSplit)
            if (sseSplit + sseNotSplit) < lowestSSE:
                bestCentToSplit = i
                bestNewCents = centroidMat
                bestClustAss = splitClustAss.copy()
                lowestSSE = sseSplit + sseNotSplit
        bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList) #change 1 to 3,4, or whatever
        bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
        print ('the bestCentToSplit is: ',bestCentToSplit)
        print ('the len of bestClustAss is: ', len(bestClustAss))
        centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]#replace a centroid with two best centroids
        centList.append(bestNewCents[1,:].tolist()[0])
        clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:]= bestClustAss#reassign new clusters, and SSE
    return mat(centList), clusterAssment


import urllib
import json
def geoGrab(stAddress, city):
    apiStem = 'http://where.yahooapis.com/geocode?'  #create a dict and constants for the goecoder
    params = {}
    params['flags'] = 'J'#JSON return type
    params['appid'] = 'aaa0VN6k'
    params['location'] = '%s %s' % (stAddress, city)
    # url_params = urllib.urlencode(params)
    url_params = urllib.parse.urlencode(params)
    yahooApi = apiStem + url_params      #print url_params
    print(yahooApi)
    # c=urllib.urlopen(yahooApi)
    c=urllib.request.urlopen(yahooApi)
    return json.loads(c.read())

from time import sleep
def massPlaceFind(fileName):
    fw = open('places.txt', 'w')
    for line in open(fileName).readlines():
        line = line.strip()
        lineArr = line.split('\t')
        retDict = geoGrab(lineArr[1], lineArr[2])
        if retDict['ResultSet']['Error'] == 0:
            lat = float(retDict['ResultSet']['Results'][0]['latitude'])
            lng = float(retDict['ResultSet']['Results'][0]['longitude'])
            print ("%s\t%f\t%f" % (lineArr[0], lat, lng))
            fw.write('%s\t%f\t%f\n' % (line, lat, lng))
        else: print ("error fetching")
        sleep(1)
    fw.close()

def distSLC(vecA, vecB):#Spherical Law of Cosines
    a = sin(vecA[0,1]*pi/180) * sin(vecB[0,1]*pi/180)
    b = cos(vecA[0,1]*pi/180) * cos(vecB[0,1]*pi/180) * \
                      cos(pi * (vecB[0,0]-vecA[0,0]) /180)
    return arccos(a + b)*6371.0 #pi is imported with numpy

import matplotlib
import matplotlib.pyplot as plt
def clusterClubs(numClust=5):
    datList = []
    for line in open('places.txt').readlines():
        lineArr = line.split('\t')
        datList.append([float(lineArr[4]), float(lineArr[3])])
    datMat = mat(datList)
    myCentroids, clustAssing = biKmeans(datMat, numClust, distMeas=distSLC)
    fig = plt.figure()
    rect=[0.1,0.1,0.8,0.8]
    scatterMarkers=['s', 'o', '^', '8', 'p', \
                    'd', 'v', 'h', '>', '<']
    axprops = dict(xticks=[], yticks=[])
    ax0=fig.add_axes(rect, label='ax0', **axprops)
    imgP = plt.imread('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()

if __name__ == '__main__':
    #dataMat = mat(loadDataSet('testSet.txt'))
    # print(min(dataMat[:,0]))
    # print(randCent(dataMat,2))
    # print(random.rand(2,1))
    # print(distEclud(dataMat[0],dataMat[1]))
    # print(kMeans(dataMat,4))
    # myCentroids,clustAssing = kMeans(dataMat,4)
    # showCluster(dataMat,4,myCentroids,clustAssing)
    # datMat3 = mat(loadDataSet('testSet2.txt'))
    # # centList,myNewAssments = biKmeans(datMat3,3)
    # centList,myNewAssments = kMeans(datMat3,3, distMeas=distEclud, createCent=randCent)
    #
    # print(centList)
    # showCluster(datMat3,3,centList,myNewAssments)

    geoResult = geoGrab('1 VA Center','Augusta, ME')
    print(geoResult)