基于KNN的手写数字识别

from numpy import *
import operator
import os



def classify0(inX, dataSet, labels, k):  # 构造分类器 KNN原理
    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()  # 这里是脚标的排列顺序如：[2 3 1 0]
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


def img2vector(filename):  # 把32*32的矩阵转化成1*1024的向量
    returnVector = zeros((1, 1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVector[0, 32 * i + j] = int(lineStr[j])
    return returnVector


def handwritingClassTest():
    hwLabels = []
    trainingFileList = os.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=os.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('./testDigits/%s' %(fileNameStr))
        classifyResult=classify0(vectorUnderTest,trainingMat,hwLabels,3)
        # print("识别结果是%d,真实结果是%d" %(classifyResult,classNumStr))
        if (classifyResult!=classNumStr):
            errorCount +=1
            print("识别结果是%d,真实结果是%d" %(classifyResult,classNumStr))

    print("错误数为%d" %(errorCount))
    print("错误率是%f" %(errorCount/mTest))



def main():
    handwritingClassTest()



if __name__ == '__main__':
    main()