朴树贝叶斯文本分类

朴树贝叶斯文本分类

前两个加载文件为特征分类文件，可以自己定义，例如：第一个文件是体育，第二个文件是新闻

第三个文件是测试文件 自己定义 目前这个demo是二分类

python3

from numpy import *
def textParse(bigString):    # input is big string, # output is word list # 分词
    import re
    listOfTokens = re.split(r'\W*', bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]

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

def createVocabList(dataSet):
    vocabSet = set([])  #create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document) #union of the two sets
    return list(vocabSet)


def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    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])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom)          #change to log()
    p0Vect = log(p0Num/p0Denom)          #change to log()

    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    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 spamTest():
    docList=[]; classList = []; fullText =[]
    docList1 = [];
    classList1 = [];
    fullText1 = []
    wordList = textParse(open('F:/logclassify/ws3.log').read())
    # print wordList
    docList.append(wordList)
    fullText.extend(wordList)
    classList.append(0)
    wordList = textParse(open('F:/logclassify/lm2.txt').read())
    docList.append(wordList)
    fullText.extend(wordList)
    classList.append(1)
    wordList1 = textParse(open('F:/logclassify/test/test1.txt').read())
    docList1.append(wordList1)
    fullText1.extend(wordList1)

    vocabList = createVocabList(docList) # create vocabulary

    trainingSet = range(3);
    trainingSet1 = range(1);

    testSet=[]           # create test set
    for i in range(1):
        randIndex = 0
        testSet.append(trainingSet1[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, docList1[docIndex])
        print(classifyNB(array(wordVector),p0V,p1V,pSpam));
    #     if classifyNB(array(wordVector),p0V,p1V,pSpam) != classList1[docIndex]:
    #         errorCount += 1
    #         print ("classification error",docList1[docIndex])
    # print ('the error rate is: ',float(errorCount)/len(testSet))
    #return vocabList,fullText

spamTest()