机器学习之PYTHON实现KNN算法

代码出自于机器学习实战。

# -*- coding: cp936 -*-'''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 *import operatorfrom os import listdir#dataSet是矩阵，因为只有矩阵才有属性shape.#shape指的是矩阵有多少行多少列，属性返回为列表(a,b)，a代表的是行数，b代表的是列数#tile(a,(c,d))是一个函数，将列表a，拓展为c行，d列的矩阵。#a**b是求a的b次幂#sum(axis=0)是分别计算每一列的和#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]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]        #tmp = listFromLine[-1].strip()        #print tmp        classLabelVector.append(int((listFromLine[-1].strip())) )        index += 1    return returnMat,classLabelVector    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   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 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))