KNN实现手写数字识别

KNN实现手写数字识别

from numpy import*
import operator
from os import listdir
#KNN
#inX:用于分类的数据，dataSet：训练集，labels：标签
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
    sortedDistIndices = distances.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndices[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0)+1
    sortedClassCount = sorted(classCount.items(),key = operator.itemgetter(1),reverse = True)
    return sortedClassCount[0][0]
#将图像转换为测试向量
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
#测试算法
def handwritingTest():
    hwLabels = []
    trainingFileList = listdir('D:\\AGAME\\MachineLearning\\KNN\\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('D:\\AGAME\\MachineLearning\\KNN\\trainingDigits/%s'%fileNameStr)
    testFileList = listdir('D:\\AGAME\\MachineLearning\\KNN\\testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('D:\\AGAME\\MachineLearning\\KNN\\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("the total number of error is:%d"%errorCount)
    print("the total error rate is:%f"%(errorCount/float(mTest)))
handwritingTest()