机器学习实战--chapter 2 k-NN

1 大话k-NN

k-NN就是拿输入与模型中的数据进行比较，比较的方式可以是计算距离（如欧式距离，即二范数），对这些距离进行升序，选择前k个，然后从这个k个中选择标签众数。说白了就是看与谁最接近，那么就和你同类。

2 k-NN 一般流程

1. 收集数据： 可以使用任何方法。
2. 准备数据：距离计算，最好在计算前归一化，可以使用数据与最小的差值，除以该列特征最大与最小差值（即该特征的范围）。
3. 分析数据：比如可以可视化。
4. 训练数据：此步骤不适合k-NN，因为k-NN不需要训练得出模型的参数，每次都是将输入与所有样本比较。
5. 测试算法：可以计算错误率，即错误的次数除以总共测试的次数 。
6. 使用算法

3 书中例子

3.1 约会

模型的场景：A想要对约会的对象进行分类：不喜欢的、魅力一般的、极具魅力的。以此决定怎么合理安排时间约会。要求输入一些对象的特征，得出这个对象的分类 。

3.2 识别手写数字

模型场景：将所有数字处理成黑白图像32*32，像素点的值只有0和1。要求输入图像，得出该图像的类别。

3.3 思路

可以采用k-NN的算法，收集带标签的样本，然后拿输入的数据和这些样本进行比较，利用k-NN算法，得出该输入的分类，明确k-NN的本质，就是得出离样本最近的众数的那个类别。

3.4 评价模型

可以利用错误率。可以将样本数据随机抽出一部分作为测试集，用测试集去检验模型的好坏。

3.5 code

from numpy import *import operatorfrom os import listdirdef 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]def createDataSet():    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])    labels = ['A','A','B','B']    return group, labelsdef file2matrix(filename):    fr = open(filename)    numberOfLines = len(fr.readlines())         #get the number of lines in the file    returnMat = zeros((numberOfLines,3))        #prepare matrix to return    classLabelVector = []                       #prepare labels return       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,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))   #element wise divide    return normDataSet, ranges, minValsdef datingClassTest():    hoRatio = 0.10      #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 errorCountdef 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('digits/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('digits/trainingDigits/%s' % fileNameStr)    testFileList = listdir('digits/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('digits/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))def main():    print 'Test 1 createDataSet'    group, labels = createDataSet()    print group    print labels    label = classify0([0,0], group, labels, 3)    print label    print 'Test 2 engagement'    datingClassTest()    print 'Test 3 handwriting'    handwritingClassTest()if __name__ == '__main__':    main()

3.6 运行

/Users/tl/.pyenv/versions/2.7.13ML/bin/python "/Applications/PyCharm CE.app/Contents/helpers/pydev/pydevd.py" --multiproc --qt-support --client 127.0.0.1 --port 65195 --file /Users/tl/Works/MLiA/0320/Ch02/kNN.pypydev debugger: process 17368 is connectingConnected to pydev debugger (build 163.15188.4)Test 1 createDataSet[[ 1.   1.1] [ 1.   1. ] [ 0.   0. ] [ 0.   0.1]]['A', 'A', 'B', 'B']BTest 2 engagementthe total error rate is: 0.0500005.0Test 3 handwritingthe total number of errors is: 11the total error rate is: 0.011628Process finished with exit code 0

---

参考
1.机器学习实战