bayes

朴素贝叶斯文本分类

最新推荐文章于 2024-10-21 03:32:30 发布

转载最新推荐文章于 2024-10-21 03:32:30 发布 · 298 阅读

文章标签：

#bayes

算法专栏收录该内容

105 篇文章

订阅专栏

本文介绍了一种基于朴素贝叶斯算法的文本分类方法，包括词汇表创建、文档向量化及训练分类器等步骤，并通过示例展示了如何进行垃圾邮件过滤。

from numpy import *

def trainNB0(trainMatrix,trainCatergory):
    #适用于二分类问题，其中一类的标签为1
    #return
    #p0Vect：标签为0的样本中，出现某个特征对应的概率
    #p1Vect：标签为1的样本中，出现某个特征对应的概率
    #pAbusive：标签为1的样本出现的概率
    numTrainDoc = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCatergory)/float(numTrainDoc)
    #防止多个概率的成绩当中的一个为0
    #p0Num: 在训练样本标签为0的数据中，所有特征的对应value值之和，为矩阵
    #p1Num: 在训练样本标签为1的数据中，所有特征的对应value值之和，为矩阵
    p0Num = ones(numWords)
    p1Num = ones(numWords)
    #p0Denom：在训练样本标签为0的数据中，所有特征的value值之和，为标量
    #p1Denom：在训练样本标签为1的数据中，所有特征的value值之和，为标量
    #为什么初始化为2？？
    p0Denom = 2.0
    p1Denom = 2.0
    for i in range(numTrainDoc):
        if trainCatergory[i] == 1:
            p1Num +=trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num +=trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    #出于精度的考虑，否则很可能到限归零，change to log()
    p1Vect = log(p1Num/p1Denom)
    p0Vect = log(p0Num/p0Denom)
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    #element-wise mult,只算分子的log值，因为只需比较大小，所以正负无关
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else: 
        return 0
####################3





#from numpy import *
#import os
#os.chdir(r"/home/luogan/lg/Python728/bayes/classical-machine-learning-algorithm-master/bayesian")
#import bayes
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 is abusive, 0 not
    return postingList,classVec

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 setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else: print ("the word: %s is not in my Vocabulary!" % word)
    return returnVec

def testingNB():
    listOPosts,listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat=[]
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print (testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry = ['stupid', 'garbage']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print (testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))

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

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


if __name__ == "__main__":
    listOPosts,listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    #print (myVocabList)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V,p1V,pAb = trainNB0(trainMat, listClasses)
    testingNB()