KNN算法实现手写识别系统

'''
Created on 2015-3-13

@author: lzy
'''
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.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def image2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        linestr = fr.readline()
        for j in range(32):
            returnVect[0,i*32 + 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,:] = image2vector('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 = image2vector('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 += 1.0
    print "the total error rate is %f" % (errorCount / float(mTest))
        
handwritingClassTest()

运行结果：the total error rate is 0.011628

    classifiy0实现了KNN分类算法；image2vector是将图片转换为一维向量的形式，这里的图像是经过处理的32像素*32像素的黑白图像；handwritingClassTest则是训练数据、预测数据；该算法的准确率为0.011628。

    numpy.tile(A,reps)是把A重复reps次来构造数组；

    argsort函数返回的是数组值从小到大的索引值

    from os import listdir 这段代码的主要功能是从os模块中导入函数listdir，它可以列出给定目录的文件名。