机器学习实战——练习（朴素贝叶斯——从个人广告中获取区域倾向）

朴素贝叶斯——从个人广告中获取区域倾向

示例：使用朴素贝叶斯分类器从个人广告中获取区域倾向

Craigslist个人广告链接已经找不到了，改用该网站的社会事件event与政治politics的RSS源

https://newyork.craigslist.org/search/eve?format=rss&sale_date=2018-06-11

https://losangeles.craigslist.org/search/eve?format=rss&sale_date=2018-06-11

https://newyork.craigslist.org/search/pol?format=rss

https://sfbay.craigslist.org/search/pol?format=rss

代码如下：

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 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 = list(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])


ny = feedparser.parse('https://newyork.craigslist.org/search/pol?format=rss')
sf = feedparser.parse('https://sfbay.craigslist.org/search/pol?format=rss')
vocabList, psf, pny = localWords(ny, sf)
print(vocabList)
print(psf)
print(pny)

vocabList, psf,pny = localWords(ny, sf)