k-Nearest Neighbors

# -*- coding: UTF-8 -*-    //显示中文，中文编码'''Created on Sep 16, 2010kNN: k Nearest NeighborsInput:      inX: vector to compare to existing dataset (1xN)            dataSet: size m data set of known vectors (NxM)            labels: data set labels (1xM vector)            k: number of neighbors to use for comparison (should be an odd number)            Output:     the most popular class label@author: pbharrin'''from numpy import *         #scientific computingimport operator             #for sortingfrom os import listdir'''just for convenience to create dataset and labels'''def createDataSet():    #numpy中 array创建时参数必须为list    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):    '''    inX:the input vector to classfy    dataSet:training examples    labels:a vector of labels     k:the number of nearest neighbor to use In the voting      '''    #distance calculation    dataSetSize = dataSet.shape[0]  #get the length of fist dimension     diffMat = tile(inX, (dataSetSize,1)) - dataSet  #将inX向量复制dataSetSize次得到一个矩阵，再将去dataset矩阵得到差值矩阵    sqDiffMat = diffMat**2              #对差值矩阵中的值进行平方（求点之间距离的公式）    sqDistances = sqDiffMat.sum(axis=1) #axis=1将矩阵的每一行相加,得到一维向量，默认是anis=0，即普通的相加    distances = sqDistances**0.5    #开方，得到inX向量点到其他点的距离    sortedDistIndicies = distances.argsort()    # argsort对distances中数据进行由小到大排序，返回排序下标数组        #dictionary 该变量在后面多次用到，所以此处提前进行声明    classCount={}            for i in range(k):        voteIlabel = labels[sortedDistIndicies[i]]#sortedDistIndicies[i]为下标值        #get():Return the value for key if key is in the dictionary, else default（here default is 0）.        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1    #以classCount的第二个域进行排序,即以value进行排序，倒序    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)'''注意Python中array 与list的区别。 二维list的访问方式为a[0][1]二维array的访问方式为a[1,:] 即访问a的第二行中所有成员，具体区别查看CSDN'''    return sortedClassCount[0][0]'''将文本文件内容存储到array矩阵中'''def 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(numberOfLines*3大小的矩阵array)    classLabelVector = []                       #prepare labels return       fr = open(filename)#fr.readlines()会将游标放到末尾，此处使用open()将游标放到开头    index = 0    for line in fr.readlines():        line = line.strip()        listFromLine = line.split('\t')     #\t是制表符，相当于一个很大的空格。返回一个list        returnMat[index,:] = listFromLine[0:3]  #将每行的数据存入矩阵returnMat        classLabelVector.append((listFromLine[-1]))  #数据的最后一个label        index += 1    return returnMat,classLabelVector'''将不同的属性值进行变为0-1，使得影响力变为相同'''def autoNorm(dataSet):    minVals = dataSet.min(0)#返回的是一个list，每个项都是各列中最小值    maxVals = dataSet.max(0)    ranges = maxVals - minVals    normDataSet = zeros(shape(dataSet))             #shape(dataSet)返回一个dataSet大小的array    #shape[0] 只读取第一维的长度    m = dataSet.shape[0]    normDataSet = dataSet - tile(minVals, (m,1))    #得到所有数据集合与集合中最小值的差    normDataSet = normDataSet/tile(ranges, (m,1))   #element wise divide    return normDataSet, ranges, minVals'''error rate'''def 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 errorCount    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" % (errorCount/float(mTest))