机器学习实战KNN

伪代码：

1. 计算已知类别数据集中的点与当前点之间的距离。
2. 按照距离递增次序排序
3. 选取与当前点距离最小的k个点
4. 确定前k个点所在类别中的出现频率
5. 返回前k个点出现频率最高的类别作为当前点的预测分类

---

程序

def 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    sortedDistIndicies = distances.argsort()    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)    return sortedClassCount[0][0]

np.argsort: http://blog.csdn.net/maoersong/article/details/21875705
dict.get: http://www.runoob.com/python/att-dictionary-get.html
sorted: https://www.cnblogs.com/sysu-blackbear/p/3283993.html

数据转换

def file2matrix(filename):    fr = open(filename)    numberOfLines = len(fr.readlines())             returnMat = zeros((numberOfLines,3))           classLabelVector = []                           fr = open(filename)    index = 0    for line in fr.readlines():        line = line.strip()        listFromLine = line.split('\t')        returnMat[index,:] = listFromLine[0:3]        classLabelVector.append(int(listFromLine[-1]))        index += 1    return returnMat,classLabelVector

40920 8.326976 0.953952 3
14488 7.153469 1.673904 2
26052 1.441871 0.805124 1

归一化

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))   #element wise divide    return normDataSet, ranges, minVals

测试

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))    print errorCountdatingClassTest()

预测

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 cosumed 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]

手写数字

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():    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" % (errorCo

os.listdir: http://www.runoob.com/python/os-listdir.html
string.split: http://www.runoob.com/python/att-string-split.html

0_0
0_1
0_2
…