机器学习实战之k-近邻算法（6）---手写数字识别系统（0-9识别）

from numpy import *
import operator
from os import listdir
#创建数据集
def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels
#根据输入测试实例进行k-近邻分类
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]
#处理输入格式问题，从txt文件中读取数据
def file2matrix(filename, dim2):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numberOfLines = len(arrayOLines)
    returnMat = zeros((numberOfLines, dim2))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index, :] = listFromLine[0:dim2]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat, classLabelVector
#归一化特征值
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))
    return normDataSet, ranges, minVals
#分类器针对约会网站的测试代码 hoRatio是测试样本占总样本数的比例
def datingClassTest(hoRatio):
    datingDataMat, datingLabels = file2matrix('datingTestSet2.txt', 3)
    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))
#kNN实现的手写识别系统的辅助函数，将图像转成测试向量
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 returnVect
#完整的手写识别系统
def handwritingClassTest():
    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)
    testFileList = listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileNameStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
        classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
        print "classifier came back whit: %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))

错误率仅为 0.011628

主要的函数还是classify0()这个函数，依旧是计算每个特征的差的平方和的开方。

没有归一化（因为都是0、1数据，不需要归一化）

the total number of errors is : 11

 the total error rate is 0.011628