kNN算法实现识别手写数字

kNN算法实现识别手写数字并将结果写入文件Result.txt

数据集为二维点阵图（32*32）

from os import listdir
from numpy import *

# 分类器
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.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


# 从文件中读取
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

// testvector = img2vector('C:/Users/Aurora/Desktop/机器学习/machinelearninginaction/Ch02/testDigits/0_12.txt')
// print(testvector[0,33:1024])

# 手写识别具体实现
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir('C:/Users/Aurora/Desktop/机器学习/machinelearninginaction/Ch02/trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0]  # 提取第一部分，0_12
        classNumstr = int(fileStr.split('_')[0])  # 提取0_12的第一部分，0
        hwLabels.append(classNumstr)
        trainingMat[i,:] = img2vector('C:/Users/Aurora/Desktop/机器学习/machinelearninginaction/Ch02/trainingDigits/%s'\
                                      % fileNameStr)
    testFileList = listdir('C:/Users/Aurora/Desktop/机器学习/machinelearninginaction/Ch02/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('C:/Users/Aurora/Desktop/机器学习/ \
        machinelearninginaction/Ch02/trainingDigits/%s'% fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwLabels,3)
        result = ('No.%d ,the classifier came back with : %d , the real anwser is : %d '\
              % (i+1,classifierResult,classNumstr))
        fileSave = open("Result.txt",'a')
        fileSave.write(result+'\n')
        fileSave.close()
        if(classifierResult != classNumstr):
            errorCount += 1.0
    print('the total number of errors is : %d' %errorCount)
    print('the total error rate is : %f'%(errorCount/float(mTest)))

# 测试
handwritingClassTest()

运行结果：