knn--手写数字的识别

机器学习实战书上的Demo案例，很实用 直接上代码:

#!/usr/bin/python
#-*-coding:utf-8-*-

from numpy import *
import operator
from os import listdir

#knn算法,inX是测试数据，dataSet是训练数据,labels是标签,k是选取的
def classify0(inX, dataSet, labels, k):
    #shape返回行列的大小，这里shape[0]将是行的大小
    dataSetSize = dataSet.shape[0]  
    #这里的tile函数是重复的意思，整体重复.repeat是单个重复
    #这里的作用是求差集                
    diffMat = tile(inX, (dataSetSize,1)) - dataSet
    #差集的平方      
    sqDiffMat = diffMat**2
    #平方和
    sqDistances = sqDiffMat.sum(axis=1)                  
    distances = sqDistances**0.5
    #argsort()返回从小到大的索引，这样就在labels中找对应索引就可以了
    sortedDistIndicies = distances.argsort()            
    classCount={}  
    //求最近的k个                                    
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

#图片转化为二进制
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

def handwritingClassTest():
    hwLabels = []
    #获取训炼数据文件列表
    trainingFileList = listdir('trainingDigits')  
    #有多少个文件        
    m = len(trainingFileList)
    #每个文件对应二维数组中的一行，每行是图片的二进制值
    trainingMat = zeros((m,1024))
    for i in range(m):
        #由于数字直接是文件名的每一个数字，形如:4_5.txt,表示数字4的第5个训练数据
        fileNameStr = trainingFileList[i]                  
        fileStr = fileNameStr.split('.')[0]   
        #classNumstr是真实的数字             
        classNumStr = int(fileStr.split('_')[0])          
        hwLabels.append(classNumStr)
        #添加图片的二进制到训练数据中
        trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr)
     
    testFileList = listdir('testDigits')       
    errorCount = 0.0
    #处理测试数据
    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)
        #knn
        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 "\nthe total number of errors is: %d" % errorCount
    print "\nthe total error rate is: %f" % (errorCount/float(mTest))

if __name__ == '__main__':
    handwritingClassTest()

转载于:https://my.oschina.net/vintnee/blog/726201