朴素贝叶斯进行分类

python代码实现    

 主要是根据朴素贝叶斯 相互独立假设  p(w|c1)=p(w1|c1)*p(w2|c1)*p(w3|c1)......*p(wn|c1)  

从而 p(c1|w)=[p(w|c1)*p(c1)]/p(w)   而p(w)等于 i 从到n  所有的 p(w|ci)*p(ci)相加,从而p(w)不变 

因此只需要计算[p(w|c1)*p(c1)] 

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代表侮辱文字，0代表正常言论
    return postingList, classVec


# 创建不重复所有文档词的字典列表
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        # 并集操作
        vocabSet = vocabSet | set(document)
    return list(vocabSet)


# 把文档词汇表变成文档向量
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            # 获得某个词所在的索引位置
            returnVec[vocabList.index(word)] = 1
        else:
            print('the word:%s is not in my Vocabulart!' % word)
    return returnVec


# 词袋模型  统计每个词出现的次数
def bagOfWords2VecMN(vocabList, inputSet):
    retrunVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            retrunVec[vocabList.index(word)] += 1
    return retrunVec


import numpy as np


# 训练数据集
def trainB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    # 侮辱性类型所占的比例
    pAbusive = sum(trainCategory) / float(numTrainDocs)
    # P(x|c=0)的概率 转换为朴素贝叶斯函数 P(x1|c=0)*P(x2|c=0).......
    # p0Num = np.zeros(numWords)
    p0Num = np.ones(numWords)
    # P(x|c=1)的概率 如上
    # p1Num = np.zeros(numWords)
    p1Num = np.ones(numWords)
    # p0Denom = 0.0
    # p1Denom = 0.0
    p0Denom = 2.0
    p1Denom = 2
    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 = p1Num / p1Denom
    # p0Vect = p0Num / p0Denom
    # 防止数据出现下溢
    p1Vect = np.log(p1Num / p1Denom)
    p0Vect = np.log(p0Num / p0Denom)
    return p0Vect, p1Vect, pAbusive


# vec2Classify表示当前文档的词向量
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0


def textTrain():
    postingList, classVec = loadDataSet()
    dataSet = createVocabList(postingList)
    trainMatrix = []
    for postinDoc in postingList:
        # 获得每个文档的向量表示，并添加到trainMatrix矩阵中
        trainMatrix.append(setOfWords2Vec(dataSet, postinDoc))
        # trainMatrix.append(bagOfWords2VecMN(dataSet, postinDoc))
    p0v, p1v, pAb = trainB0(trainMatrix, classVec)
    print(p0v)
    print(p1v)
    print(pAb)  # textTrain()


def testingNB():
    listOppsts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOppsts)
    trainMat = []
    for postinDoc in listOppsts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0v, p1v, pAb = trainB0(trainMat, listClasses)
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print('testEntry , classified as :%s' % (classifyNB(thisDoc, p0v, p1v, pAb)))
    testEntry = ['stupid', 'garbage']
    thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
    print('testEntry , classified as :%s' % (classifyNB(thisDoc, p0v, p1v, pAb)))


def textParse(bigString):
    import re
    try:
        # 匹配所有非 字母、数字、下划线
        listOfTokens = re.split(r'W*', bigString)
    except FutureWarning:
        print("error")
        return []
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]


# 对贝叶斯垃圾邮件分类器进行自动化处理
# 交叉验证
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/spam/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    # 创建词汇集合
    vocabList = createVocabList(docList)
    # 训练数据集合
    trainingSet = list(range(50))
    testSet = []
    # 随机分割训练数据集和测试数据集
    for i in range(10):
        # 从0-49 随机选择一个数字，其实是随机选择一个样本
        randIndex = int(np.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 = trainB0(trainMat, trainClasses)
    errorCount = 0
    #     对于测试数据集
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print("the error rate is:", float(errorCount) / len(testSet))


import feedparser


# ny = feedparser.parse('http://feed.cnblogs.com/blog/u/205667/rss')
# print(ny['entries'][0]['summary'])


# spamTest()
# RSS源分类器及高频词去除函数
# 统计词频,并且取出从词频最高的前30个数据
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[:20]

# 从文件中加载停用词
def load_the_remov_words():
    rmwords = []
    with open('removeWords.txt', 'rb') as fr:
        for line in fr.readlines():
            strline = line.strip()
            rmwords.append(strline)
    fr.close()
    return rmwords


# //从RSS源中加载数据
def localWords(feed1, feed0):
    import feedparser
    # 文档列表
    docList = []
    # 类别列表
    classList = []
    # 没有去重的所有词表
    fullText = []

    # 选择其中最短的预料长度
    minLen = min(len(feed1['entries']), len(feed0['entries']))
    for i in range(minLen):
        # 把摘要分割成单词list集合
        wordList = textParse(feed1['entries'][i]['summary'])
        # 添加每篇文档的词集合
        docList.append(wordList)
        # 保存所有的词成一个list集合
        fullText.extend(wordList)
        # 添加类别
        classList.append(1)
        # 如上一样
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    # 创建不重复所有文档使用的单词列表
    vocabList = createVocabList(docList)
    # 选择词频最高的前30条数据  返回的格式是[({词:出现的次数})({词:出现的次数})....]
    top30Words = calcMostFreq(vocabList, fullText)
    # 移除频数最高的前30条数据
    for pairW in top30Words:
        if pairW[0] in vocabList:
            vocabList.remove(pairW[0])

    # 移除停用词
    rmwords = load_the_remov_words()
    for pairW in rmwords:
        if pairW in vocabList:
            vocabList.remove(pairW)

    # 训练数据集中数据的个数
    trainingSet = list(range(2 * minLen))
    # 测试数据集
    testSet = []
    # 任意选择二十条数据作为测试数据
    for i in range(20):
        # 产生一个随机数
        randIndex = int(np.random.uniform(0, len(trainingSet)))
        # 添加到测试集合上
        testSet.append(trainingSet[randIndex])
        # 删除测试数据索引
        del (trainingSet[randIndex])

    trainMat = []
    trainClasses = []
    for docIndex in trainingSet:
        # 获得训练数据相应的词向量
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        # 添加相应的类别
        trainClasses.append(classList[docIndex])

    p0V, p1V, pSpam = trainB0(np.array(trainMat), np.array(trainClasses))
    errorCount = 0
    for docIndex in testSet:
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print('the error rate is:', float(errorCount) / len(testSet))
    return vocabList, p0V, p1V


# 按顺序输出 满足一定阈值词
def getTopWords(ny, sf):
    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**" * 14)
    for item in sortedSF:
        print(item[0])
    sortedNF = sorted(topNY, key=lambda pair: pair[1], reverse=True)
    print("NF**" * 14)
    for item in sortedNF:
        print(item[0])


ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
sf = feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
getTopWords(ny, sf)
# vocabList, pSF, pNY = localWords(ny, sf)
# vocabList, pSF, pNY = localWords(ny, sf)
# print(vocabList)
# print("-" * 20)
# print(pSF)
# print('------------')
# print(pNY)

 停用词文件