机器学习实战-第四章 朴素贝叶斯算法

from numpy import *
import feedparser

def loadDataSet():
    postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
                   ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
                   ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
                   ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
                   ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
                   ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    classVec = [0, 1, 0, 1, 0, 1]  # 1 is abusive, 0 not
    return postingList, classVec


def createVocabList(dataSet):
    vocabSet = set([])  # create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document)  # union of the two sets
    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 trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    # print("numTrainDocs:", numTrainDocs)
    # print("numWords:", numWords)
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    print("pAbusive:", pAbusive)


    # p0Num = zeros(numWords)
    # p1Num = zeros(numWords)
    #
    # p0Denom = 0.0
    # p1Denom = 0.0


    p0Num = ones(numWords); p1Num = ones(numWords)
    p0Denom = 2.0; p1Denom = 2.0

    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])

    p1Vect = log(p1Num/p1Denom)
    p0Vect = log(p0Num/p0Denom)

    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 = trainNB0(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, "classifed as: ", classifyNB(thisDoc, p0V, p1V, pAb))

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, encoding='ISO-8859-1').read())

        docList.append(wordList)
        fullText.extend(wordList)

        classList.append(1)

        wordList = textParse(open("./email/ham/%d.txt" % i, encoding='ISO-8859-1').read())
        docList.append(wordList)
        fullText.extend(wordList)

        classList.append(0)

    # print("docList:", len(docList))
    # print("fullText:", len(fullText))
    vocabList = createVocabList(docList)

    # print("vocabList:", vocabList)
    # trainingSet = range(50)

    # 一共50封邮件
    trainingSet = list(range(50))
    # print("trainingSet:", trainingSet)
    testSet = []

    for i in range(10): # 10份邮件随测试集
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    # print("testSet:", testSet)
    # print("traingSet:", trainingSet)

    trainMat = []
    trainClasses = []

    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])

    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    # 训练完毕


    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))


def calcMostFreq(vocabList,fullText):
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True)
    return sortedFreq[:30]

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

    return returnVec

def localWords(feed1,feed0):
    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    print("feed1['entries']:", feed1['entries'])
    print("minLen:", minLen)
    for i in range(minLen):
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1) #NY is class 1
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    top30Words = calcMostFreq(vocabList,fullText)   #remove top 30 words
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])
    trainingSet = range(2*minLen); testSet=[]           #create test set
    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:#train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
    print('the error rate is: ',float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

if __name__ == "__main__":
    print("---------------------loadDataSet-------------------------------------")
    listOPosts, listClasses = loadDataSet()
    print("listOPosts:", listOPosts)
    print("listClasses:", listClasses)
    print("---------------------createVocabList-------------------------------------")
    myVocabList = createVocabList(listOPosts)
    print("myVocabList:", myVocabList)
    print("---------------------setOfWords2Vec-------------------------------------")
    temp = setOfWords2Vec(myVocabList, listOPosts[0])
    print("temp:", temp)

    temp = setOfWords2Vec(myVocabList, listOPosts[3])
    print("temp:", temp)
    print("---------------------trainNB0-------------------------------------")
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    # print("trainMat:", trainMat)

    p0V, p1V, pAb = trainNB0(trainMat, listClasses)
    # print("listClasses:", listClasses)
    print("myVocabList:", myVocabList)
    print("pAb:", pAb)
    print("p0V:", p0V)
    print("p1V:", p1V)
    print(1/(32))
    print("---------------------testingNB-------------------------------------")
    testingNB()
    print("---------------------4.6  示例:使用朴素贝叶斯过滤垃圾邮件-------------------------------------")
    mySent = "This book is the best book on Python or M.L. I have ever laid eyes upon."
    print("mySent.split():", mySent.split())
    import re
    regEx = re.compile("\\W*")
    listOfTokens = regEx.split(mySent)
    print("listOfTokens:", listOfTokens)
    print([tok for tok in listOfTokens if len(tok) > 0])
    print([tok.lower() for tok in listOfTokens if len(tok) > 0])
    emailText = open("./email/ham/6.txt", encoding='ISO-8859-1').read()
    print("emailTest:", emailText)
    # listOfTokens = regEx.split(emailText)
    # print(listOfTokens)
    print("---------------------spamTest-------------------------------------")
    spamTest()
    print("---------------------localWords-------------------------------------")
    ny = feedparser.parse("http://newyork.craigslist.org/stp/index.rss")
    sf = feedparser.parse("http://sfbay.craigslist.org/stp/index.rss")
    print("ny:", ny)
    print("sf:", sf)
    # vocabList, pSF, pNY = localWords(ny, sf)
    # vocabList, pSF, pNY = localWords(ny, sf)