机器学习实战之K近邻改进的约会网站代码及手写字体识别代码

from numpy import *
import operator
import os
def createDataSet():
    group=array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels=['A','A','B','B']
    return group,labels
def classify0(inX,dataSet,labels,k):
    dataSetSize=dataSet.shape[0] #查看数组维数
    diffMat=tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat=diffMat**2
    sqDistances=sqDiffMat.sum(axis=1)
    distances=sqDistances**0.5
    sortedDistIdicies=distances.argsort()
    classCount={}
    for i in range(k):
        voteIlabel=labels[sortedDistIdicies[i]]
        classCount[voteIlabel]=classCount.get(voteIlabel,0)+1
    sortedClassCount=sorted(classCount.items(),
                            key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]
def file2matrix(filename):
    fr=open(filename)
    arrayOLines=fr.readlines()
    numberOfLines=len(arrayOLines)
    returnMat=zeros((numberOfLines,3))
    classLabelVector=[]
    index=0
    for line in arrayOLines:
        line=line.strip()
        listFromLine=line.split('\t')
        returnMat[index,:]=listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index+=1
    return returnMat,classLabelVector
#datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
import matplotlib
import matplotlib.pyplot as plt
fig=plt.figure()
ax=fig.add_subplot(111)
#ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
#plt.show()
#ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
#plt.show()
def autoNorm(dataSet):
    minVals=dataSet.min(0)
    maxVals=dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet=zeros(shape(dataSet))
    m=dataSet.shape[0]
    normDataSet=dataSet-tile(minVals,(m,1))
    normDataSet=normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals
def datingClassTest():
    hoRatio=0.10
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    m=normMat.shape[0]
    numTestVecs=int(m*hoRatio)
    errorCount=0.0
    for i in range(numTestVecs):
        classifierResult=classify0(normMat[i,:],normMat[numTestVecs:m, :], datingLabels[numTestVecs:m],3)
        print("the classifier came back with:%d,the real answer is:%d",classifierResult, datingLabels[i])
        if(classifierResult != datingLabels[i]):errorCount += 1.0
    print("the total error rate is:%f"%(errorCount/float(numTestVecs)))

#程序清单2-5 约会网站预测函数

def classfyPerson():#这是真正与用户交互的程序，按照自己的习惯对原书的英文问答改为了中文，代码都是之前介绍过的，不重复做解释了，

    #唯一需要注意的是在python3.0中print与python2.0有较大差别,raw_input()不再适用

    resultList = ['讨厌','一般喜欢','非常喜欢']

    percentTats = float(input('打视频游戏所占时间比：'))

    ffMiles = float(input('飞行常客里程数：'))

    iceCream = float(input('每周消耗的冰淇淋公升数：'))

    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')

    normMat,ranges,minVals = autoNorm(datingDataMat)

    inArr = array([ffMiles,percentTats,iceCream])

    classifierResult = classify0((inArr-minVals)/ranges,normMat,datingLabels,3)

    print('你是否会喜欢这个人：%s' %resultList[classifierResult-1])
def img2vector(filename):
    returnVect=zeros((1,1024))
    fr=open(filename)
    for i in range(32):
        lineStr=fr.readline()
        for j in range(32):
            returnVect[0,32*i+j]=int(lineStr[j])
    return returnVect
#testVector=img2vector('testDigits/0_13.txt')
#print(testVector[0,0:31])

def handwritingClassTest():
    hwLabels=[]
    trainingFileList=os.listdir('trainingDigits')
    m=len(trainingFileList)
    trainingMat=zeros((m,1024))
    for i in range(m):
        fileNameStr=trainingFileList[i]
        fileStr=fileNameStr.split('.')[0]
        classNumStr=int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:]=img2vector('trainingDigits/%s' %fileNameStr)
    testFileList=os.listdir('testDigits')
    errorCount=0.0
    mTest=len(testFileList)
    for i in range(mTest):
        fileNameStr=testFileList[i]
        fileStr=fileNameStr.split('.')[0]
        classNumStr=int(fileStr.split('_')[0])
        vectorUnderTest=img2vector('testDigits/%s' %fileNameStr)
        classifierResult=classify0(vectorUnderTest,trainingMat,hwLabels,3)
        print("the classifier came back with:%d,the real answer is:%d",(classifierResult,classNumStr))
        if (classifierResult!=classNumStr):errorCount+=1.0
    print("\nthe total number of errors is:%d",errorCount)
    print("\nthe total error rate is:%f",(errorCount/float(mTest)))
handwritingClassTest()