使用朴素贝叶斯分类器从个人广告中获取区域倾向

引入

使用来自不同城市的广告训练一个分类器，然后观察分类器的效果。我们的目的并不是使用该分类器进行分类，而是通过观察单词和条件概率值来发现与特定城市相关的内容。

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

第一个函数遍历词汇表中的每个词并统计它在文本中出现的次数，然后根据出现次数从高到低对词典进行排序，最后返回排序最高的30个单词

第二个函数使用两个RSS源作为参数。这个函数和之前的spamTest函数几乎相同。区别在于这里访问的是RSS源而不是文件。

词袋模型在解决文档分类问题上比词集模型有所提高。

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]

>>> import feedparser
>>> import bayes
>>> ny=feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
>>> sf=feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
>>> voacblist,psf,pny=bayes.localWords(ny,sf)
the error rate is:  0.25
>>> voacblist,psf,pny=bayes.localWords(ny,sf)
the error rate is:  0.45
>>> voacblist,psf,pny=bayes.localWords(ny,sf)
the error rate is:  0.4
>>> voacblist,psf,pny=bayes.localWords(ny,sf)
the error rate is:  0.3
voacblist,psf,pny=bayes.localWords(ny,sf)
>>> 
>>> 
KeyboardInterrupt
>>> 
>>> voacblist,psf,pny=bayes.localWords(ny,sf)
the error rate is:  0.25
>>> bayes.getTopWords(ny,sf)

使用两个RSS源作为输入，然后训练并测试朴素贝叶斯分类器，返回使用的概率值。然后创建两个列表用于元素的存储，返回大于某个阈值的所有词，然后按照他们的条件概率进行排序。