0415学习笔记：2.3手写识别系统-k近邻算法

1.二进制图像转换为1x1024的向量

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

2.测试

from os import listdir #列出给定目录的文件名

def handwritingCClassTest():
    hwLabels = []
    trainingFileList = listdir(r'/home/yang/Software/pycharm-community-2017.3.4/bin/桌面/PycharmProjects/untitled/k18/traingDigits') #获取目录内容
    m = len(trainingFileList) #目录中的文件数
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = traingFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('.')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector(r'/home/yang/Software/pycharm-community-2017.3.4/bin/桌面/PycharmProjects/untitled/k18/traingDigits/%s'%fileNameStr)
    testFileList = listdir(r'/home/yang/Software/pycharm-community-2017.3.4/bin/桌面/PycharmProjects/untitled/k18/traingDigits')
    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(r'/home/yang/Software/pycharm-community-2017.3.4/bin/桌面/PycharmProjects/untitled/k18/traingDigits/%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 error rate is :%f" % (errorCount / float(mTest)))  # 计算错误率

小结：

k近邻算法缺点：

    必须保存全部数据集，耗用大量存储空间;

    耗时

    无法给出任何数据的基础结构信息，所以我们无法知道平均实例样本和典型实例样本有什么特征。