朴素贝叶斯算法学习笔记（二）使用算法进行交叉验证

import bayes
from numpy import *


def bagOfWords2VecMN(vocabList,inputSet):
    returnVec=0*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)]+=1
    return returnVec

def textParse(bigString):
    import re
    listOfTokens=re.split(r'\W*',bigString)
    return [tok.lower() for tok in listOfTokens if len(tok)>2]

def spamTest():
    docList=[]
    classList=[]
    fullText=[]
    for i in range(1,26):
        wordList=textParse(open('email/spam/%d.txt'%i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList=bayes.createVocabList(docList)
    trainingSet=range(50)
    testSet=[]
    for i in range(10):
        randIndex=int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del (trainingSet[randIndex])
    trainMat=[]
    trainClasses=[]
    for docIndex in trainingSet:
        trainMat.append(bayes.setOfWords2Vec(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0v,p1v,pSpsm=bayes.trainNB0(trainMat,trainClasses)
    errorCount=0
    for docIndex in testSet:
        wordVector=bayes.setOfWords2Vec(vocabList,docList[docIndex])
        if bayes.classifyNB(wordVector,p0v,p1v,pSpsm) != classList[docIndex]:
            errorCount+=1
    print 'the error rate is :',float(errorCount)/len(testSet)

spamTest()
spamTest()