机器学习实战-使用朴素贝叶斯分类器来做垃圾邮件分类

coding:

from numpy import *
import re

def loadDataSet():
    postingList = [['my', ' dog', 'has', 'flea', 'problem', 'help', 'please'],
                   ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
                   ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
                   ['stop', 'posting', 'stupid', 'worthless', 'garbage', 'to', 'stop', 'him'],
                   ['quit', 'buying', 'worthleaa', 'dog', 'food', 'stupid']]
    classsVec = [0, 1, 0, 1]
    return postingList, classsVec

def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)

def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else:
            print("the word: %s is not in my Vocabulary" %word)
    return returnVec

def trainNBO(trainMartix, trainCategory):
    numTrainDocs = len(trainMartix)
    numWords = len(trainMartix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = ones(numWords)
    p1Num = ones(numWords)
    p0Demo = 2.0
    p1Demo = 2.0
    for i in range(numTrainDocs):
        if trainCategory[i-1] == 1:
            p1Num += trainMartix[i]
            p1Demo += sum(trainMartix[i])
        else:
            p0Num += trainMartix[i]
            p0Demo += sum(trainMartix[i])
    p1Vect = log(p1Num/p1Demo)
    p0Vect = log(p0Num/p0Demo)
    return p0Vect, p1Vect, pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify*p1Vec) + log(pClass1)
    p0 = sum(vec2Classify*p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

def testingNB():
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V, p1V, pAb = trainNBO(array(trainMat), array(listClasses))
    testEntry = {'love', 'my', 'dalmation'}
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as:', classifyNB(thisDoc, p0V, p1V, pAb))
    testEntry = {'stupid', 'garbage'}
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as:', classifyNB(thisDoc, p0V, p1V, pAb))

def textParse(bigSreing):
    listOfTokens = re.split(r'\w*', bigSreing)
    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 = createVocabList(docList)
    trainingSet = list(range(50))
    testSet = []
    for i in range(20):
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat = []
    trainClasses = []
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNBO(array(trainMat), array(trainClasses))
    errorCount = 0
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print("the error rate is : ", float(errorCount)/len(testSet))

spamTest()