机器学习实战笔记--朴素贝叶斯

#encoding:utf-8
from numpy import *
import feedparser

#加载数据集
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表示侮辱性言论，0表示正常言论
    return postingList, classVec


def createVocabList(dataSet):  #得到词汇集合
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)  #两个集合的并集
    return list(vocabSet)


def setOfWords2Vec(vocabList, inputSet):  #内容转化为向量
    returnVec = [0] * len(vocabList)   #所有元素都为0的向量
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1   #如果有这个词条，则置1
        else:
            print "这个词条: %s 不在我的词典中!" % word
    return returnVec


def trainNB0(trainMatrix, trainCategory):   #朴素贝叶斯分类器训练函数
    numTrainDocs = len(trainMatrix)          #文档数量
    numWords = len(trainMatrix[0])           #每篇文档的词条数
    pAbusive = sum(trainCategory) / float(numTrainDocs)   #侮辱性文档的比例
    p0Num = ones(numWords)
    p1Num = ones(numWords)  # change to ones()
    p0Denom = 2.0
    p1Denom = 2.0  # change to 2.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])   #侮辱性文档的总词数
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])  #正常文档的总词数
    p1Vect = log(p1Num / p1Denom)  # change to log()  表示p(wi/c1)
    p0Vect = log(p0Num / p0Denom)  # change to log()  表示p(wi/c0)
    return p0Vect, p1Vect, pAbusive


def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):    #对输入的vec2Classify进行分类
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)  # element-wise mult
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0


def testingNB():   #是对以上方法的整合，方便运行和调试
    listOPosts, listClasses = loadDataSet()   #加载数据
    myVocabList = createVocabList(listOPosts)   #得到字典
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))     #转化为0,1向量
    p0V, p1V, pAb = trainNB0(array(trainMat), array(listClasses))
    testEntry = ['love', 'my', 'dalmation']           #代分类的输入
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))    #转化
    print testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb)   #进行分类
    testEntry = ['stupid', 'garbage']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry, 'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb)


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):  # 处理字符串得到字符串列表，并过滤
    import re
    listOfTokens = re.split(r'\W*', bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

#垃圾邮件测试函数
def spamTest():
    docList = [];
    classList = [];
    fullText = []
    for i in range(1, 26):
        wordList = textParse(open('email/spam/%d.txt' % i).read())   #读取文件
        docList.append(wordList)         #注意append和extend
        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)  # 建立字典
    trainingSet = range(50);
    testSet = []
    for i in range(10):
        randIndex = int(random.uniform(0, len(trainingSet)))   #随机取10个作为测试集
        testSet.append(trainingSet[randIndex])
        del (trainingSet[randIndex])    #从训练集中删除
    trainMat = [];
    trainClasses = []
    for docIndex in trainingSet:  # 训练
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    errorCount = 0
    for docIndex in testSet:  # 分类
        #wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
            print "classification error", docList[docIndex]
    print 'the error rate is: ', float(errorCount) / len(testSet)
    # return vocabList,fullText


def calcMostFreq(vocabList, fullText):   #计算出现频率
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token] = fullText.count(token)
    sortedFreq = sorted(freqDict.iteritems(), key=operator.itemgetter(1), reverse=True)  #排序
    return sortedFreq[:30]  #返回前30


def localWords(feed1, feed0):
    import feedparser
    docList = [];
    classList = [];
    fullText = []
    minLen = min(len(feed1['entries']), len(feed0['entries']))
    for i in range(minLen):
        wordList = textParse(feed1['entries'][i]['summary'])    #每次访问一条RSS源
        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)  # 建立字典
    top30Words = calcMostFreq(vocabList, fullText)  # 去掉次数最高的前30个词
    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


def getTopWords(ny, sf):
    import operator
    vocabList, p0V, p1V = localWords(ny, sf)
    topNY = [];
    topSF = []
    for i in range(len(p0V)):
        if p0V[i] > -6.0: topSF.append((vocabList[i], p0V[i]))
        if p1V[i] > -6.0: topNY.append((vocabList[i], p1V[i]))
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
    print "SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**"
    for item in sortedSF:
        print item[0]
    sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
    print "NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**"
    for item in sortedNY:
        print item[0]

if __name__ == '__main__':
    # postingList, classVec = loadDataSet()
    # vocabList = createVocabList(postingList)
    # trainMat = []
    # for line in postingList:
    #     trainMat.append(setOfWords2Vec(vocabList,line))
    # p0V,p1V,p = trainNB0(trainMat,classVec)
    # print p0V
    # print p1V
    # print p
    # spamTest()
    ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
    sf = feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
    getTopWords(ny,sf)