>>> bayes.getTopWords(ny,sf)
错误率为： 0.5
SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**
void
highlight
int
strong
codemacro
mov
lynx
kevin
display
tid
std
protobuf
call
NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**
the
this
and
from
space
jupiter
arrived

完整代码：

from numpy import *

def createVocabList(dataSet):
    vocabSet = set([])  #创建一个空集
    for document in dataSet:
        vocabSet = vocabSet | set(document)  #创建两个集合的合集
    return  list(vocabSet)

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

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbisive = sum(trainCategory)/float(numTrainDocs) #侮辱性文档的概率3/6
    #初始化概率
    # 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:
            #向量相加
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    # p1Vect = p1Num/p1Denom   #侮辱性文字的概率
    # p0Vect = p0Num/p0Denom   #正常文字的概率
    p1Vect = log(p1Num/p1Denom)   #侮辱性文字的概率
    p0Vect = log(p0Num/p0Denom)   #正常文字的概率
    return p0Vect,p1Vect,pAbisive
# #
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #元素相乘
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

def textParse(bigString):
    import re
    listOfTokens = re.split(r'\W+',bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

#计算出现频率
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):
        #每次访问一条RSS源
        wordList = textParse(feed1['entries'][i]['summary'])
        # 提取RSS源中的字符串文本并切分为字符串列表
        docList.append(wordList)
        # 将每个字符串列表放入一个总的列表里
        fullText.extend(wordList)
        # 将所有字符都存储在一个列表里
        classList.append(1)
        # 标记为垃圾广告，标签为1
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
        # 同上，这里标记为非垃圾广告
    #去掉出现最高次数的一些词
    vocabList = createVocabList(docList)
    top30Words = calcMostFreq(vocabList,fullText)
    for pairW in top30Words:
        if pairW[0] in vocabList:
            vocabList.remove(pairW[0])
    #遍历单词，在词汇表中去掉出现次数最高的那些单词
    trainingSet = list(range(2*minLen))
    #创建训练集的索引列表
    testSet=[]
    # 创建测试集的索引列表
    for i in range(20):
        randIndex = int(random.uniform(0,len(trainingSet)))
        # 随机生成索引值
        testSet.append(trainingSet[randIndex])
        # 添加训练集的索引值
        del(trainingSet[randIndex])
        # 删除训练集的索引值
    trainMat=[];trainClasses=[]
    for docIndex in trainingSet:
        trainMat.append(bagOfWords2VecMN(vocabList,docList[docIndex]))
        # 添加训练词集
        trainClasses.append(classList[docIndex])
        # 添加训练类别用例
    p0V,p1V,pSam=trainNB0(array(trainMat),array(trainClasses))
    # 朴素贝叶斯分类器
    errorCount = 0
    # 定义错误计数器
    for docIndex in testSet:
        wordVector = bagOfWords2VecMN(vocabList,docList[docIndex])
        # 测试集的词集
        if classifyNB(array(wordVector),p0V,p1V,pSam) != classList[docIndex]:
            errorCount += 1
            # 如果分类错误，计数器加一
    print("错误率为：",float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

def getTopWords(ny,sf): #最具有表征性的词汇显示函数
    import operator
    vocabList,p0V,p1V=localWords(ny,sf)
    # 获得概率值
    topNY=[]; topSF=[]
    for i in range(len(p0V)):
        # 遍历概率值
        if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
        if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
        # 若概率大于阈值，则往列表中加入相应的单词和其概率组成的二元列表
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
    #对每个二元列表的概率值进行从大到小排序
    print("SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**")
    for item in sortedSF:
        print(item[0])
        # 遍历每个列表，先输出概率值大的单词
    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])