k-近邻算法（Python实现）

1 参考链接

机器学习实战

2 实现代码

from numpy import *from os import listdirimport matplotlib.pyplot as pltimport operatordef createDataSet():    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])    labels = ['A', 'A', 'B', 'B']    return group, labelsdef classify0(inX, dataSet, labels, k):    dataSetSize = dataSet.shape[0]    diffMat = tile(inX, (dataSetSize, 1)) - dataSet    sqDiffMat = diffMat**2    sqDistances = sqDiffMat.sum(axis=1)    distances = sqDistances**0.5    sortedDistIndices = distances.argsort()    classCount = {}    for i in range(k):        votelabel = labels[sortedDistIndices[i]]        classCount[votelabel] = classCount.get(votelabel, 0) + 1    sortedClassCount = sorted(classCount.iteritems(), 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, classLabelVectordef 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, minValsdef 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))def classifyPerson():    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: ", 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 returnVectdef handwritingClassTest():    # training data    hwLabels = []    trainingFileList = 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)    # test data    testFileList = 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 "\n the total number of errors is %d" % errorCount    print "\n the total error rate is: %f" % (errorCount/float(mTest))# TESThandwritingClassTest()

3 运行结果