机器学习实战笔记--KNN-mnist分类

import numpy as np
from os import listdir
import operator

def img2vector(filename):
    returnVect=np.zeros((1,1024))
    fr=open(filename)
    for i in range(32):
        linStr=fr.readline()
        for j in range(32):
            returnVect[0,32*i+j]=int(linStr[j])
    return returnVect

def classify0(inX,dataSet,labels,k):
    dataSetSize=dataSet.shape[0]
    diffMat=np.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]

#对训练集数据进行分析
file='D:/anicode/spyderworkspace/examtest/trainingDigits'
file_name=listdir('D:/anicode/spyderworkspace/examtest/trainingDigits')
num_files=len(file_name)
clsLabel=[]
trainingMat=np.zeros((num_files,1024))
for i in range(num_files):
    cls=file_name[i].split('.')[0]
    clsNum=int(cls.split('_')[0])
    clsLabel.append(clsNum)
    file_name_one=file+'/'+file_name[i]
    trainingMat[i,:]=img2vector(file_name_one)

#对测试集数据进行分析    
test_file='D:/anicode/spyderworkspace/examtest/testDigits'
test_file_name=listdir('D:/anicode/spyderworkspace/examtest/testDigits')
test_num_files=len(test_file_name)
errorCount=0.0
for i in range(test_num_files):
    test_cls=test_file_name[i].split('.')[0]
    test_clsNum=int(test_cls.split('_')[0])
    test_file_name_one=test_file+'/'+test_file_name[i]
    testvector=img2vector(test_file_name_one)
    clsResult=classify0(testvector,trainingMat,clsLabel,3)
    print("the predict answer is %d,the real anser is %d"%(clsResult,test_clsNum))
    if(clsResult!=test_clsNum):
        errorCount+=1
print("总错误个数为：%d,错误率为：%f%%"%(errorCount,errorCount/float(test_num_files)*100))