K-近邻算法

《机器学习实战》第2章K-近邻算法

from numpy import *

import operator

from os import listdir

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX, (dataSetSize,1)) - dataSet #tile（A，n）将A重复n次
    sqDiffMat = diffMat**2
    sqDistances = sqDiffMat.sum(axis=1) #axis=0结果为1行，每列相加；axis=1结果为1列，每行相加
    distances = sqDistances**0.5
    sortedDistIndicies = distances.argsort()    #将得到的距离进行排序
    classCount={}          
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)#选出最大的K个距离，逆序

    return sortedClassCount[0][0]

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 file2matrix(filename):
    love_dictionary={'largeDoses':3, 'smallDoses':2, 'didntLike':1}
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)            #get the number of lines in the file
    returnMat = zeros((numberOfLines,3))        #prepare matrix to return
    classLabelVector = []                       #prepare labels return   
    index = 0
    for line in arrayOLines:
        line = line. strip()     #截取掉回车符
        listFromLine = line. split('\t') #以tab键划分
        returnMat[index,:] = listFromLine[0:3]
        if(listFromLine[-1].isdigit()):
            classLabelVector.append(int(listFromLine[-1]))
        else:
            classLabelVector.append(love_dictionary.get(listFromLine[-1]))
        index += 1

    return returnMat,classLabelVector

def autoNorm(dataSet):#正则化
    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))   #element wise divide
    return normDataSet, ranges, minVals
   
def datingClassTest():
    hoRatio = 0.50      #hold out 10%
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    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))

    print errorCount   

def classifyPerson():#约会人群分类测试
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(raw_input(\
                                  "percentage of time spent playing video games?"))
    ffMiles = float(raw_input("frequent flier miles earned per year?"))
    iceCream = float(raw_input("liters of ice cream consumed per year?"))
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')
    normMat, ranges, minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles, percentTats, iceCream, ])
    classifierResult = classify0((inArr - \
                                  minVals)/ranges, normMat, datingLabels, 3)

    print "You will probably like this person: %s" % resultList[classifierResult - 1]    

def img2vector(filename):#将二进制图像转换为向量
    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

def handwritingClassTest():#手写识别系统的测试
    hwLabels = []
    trainingFileList = listdir('trainingDigits')           #load the training set
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
    testFileList = listdir('testDigits')        #iterate through the test set
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]     #take off .txt
        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))