from numpy import *
import operator
from os import listdir


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]


 
def img2Vector(filename):
    returnVect = zeros((1,1024))
    # print(returnVect)
    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


def handwritingClassTest():
    hwLabels 
 
= []
    trainingFileList = 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 = 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)
        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
    print("the total number of errors is :%d"%errorCount)
    print("the total error rate is: %f"%(errorCount/float(mTest)))

handwritingClassTest()

測試集+訓練集數據地址：https://i.cnblogs.com/Files.aspx

knn.rar

KNN算法實現手寫數字