日常复习KNN近邻算法补充

# 手写识别系统

#准备数据：将图片转换为测试向量
def img2vector(filename):
    returnvect = zero((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：使用K近邻算法识别手写数字

def handwritingclasstest():
    from os import listdir
    hwlabels = []#存储类别标签
    trainingfilelist = listdir('trainingDigits')#读取trainingDigits文件夹下的文件的内容
    m = len(trainingfilelist)#获取文件数目
    trainingmat = zeros((m,1024))#书上的二进制图像矩阵是32*32的,将其转化成1*1024的向量
    #trainingDigits下的文件用于训练，然后再对testdigits中的进行测试
    for i in range(m):#遍历每一个文件，将每一个文件转换成1*1024的矩阵
        filenamestr = trainingfilelist[i]#type是列表
        filestr = filenamestr.split('.')[0]#去掉.txt
        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(filestr.split('.'))[0]
        vectorundertest = img2vector('trainingDigits/%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("errors is: %d"%errorcount)
    print("errors rate is: %f"%(errorcount/float(mtest)))