朴素贝叶斯Python实现

最新推荐文章于 2024-02-26 19:24:43 发布

转载最新推荐文章于 2024-02-26 19:24:43 发布 · 625 阅读

本文详细介绍了如何使用朴素贝叶斯分类器进行文本分类，包括数据预处理、特征提取、模型训练及评估等关键步骤。通过实例演示了垃圾邮件过滤器的实现过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

贝叶斯定理：

from math import *
from numpy import *
import random

创建数据集和标签
def loadData():
    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]#0是正常词汇，1是具有侮辱性的词汇
    return postingList,classVec

根据上面的数据集创建词汇库
输入即是上面的数据集postingList
输出无重复的词汇库
def createVocaList(dataset):
    vocabset=set([])
    for document in dataset:
        vocabset=vocabset|set(document)#union交集，除去重复性词汇
    return list(vocabset)

将单个样本隐射到词汇库中，统计单个样本在词库中的出现情况
def setOfWords2Vec(vocabList,inputset):
    returnVec=[0]*len(vocabList)#创建一个与词汇库长度相同的0向量表
    for word in inputset:
        if word in vocabList:
            returnVec[vocabList.index(word)]=1#词汇表中出现过的词汇记1
        else:
            print("the word:{0} is not in my vocabulary".format(word))
    return returnVec

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs=len(trainMatrix)#统计训练样本的大小此处numTrainDocs=6
    numWords=len(trainMatrix[0])#统计样本中第一个文档中包含的词汇个数
    pAbusive=sum(trainCategory)/float(numTrainDocs)#计算侮辱性词汇的概率
    p0Num=ones(numWords)#初始样本个数为1，防止条件概率为0
    p1Num=ones(numWords)
    p0Denom=2.0#初始样本个数为2，防止条件概率为0
    p1Denom=2.0
    for i in range(numTrainDocs):
        if trainCategory[i]==1:#计算类别为1的词汇出现概率
            p1Num+=trainMatrix[i]#当某一文档中出现1时，p1Num加1
            p1Denom+=sum(trainMatrix[i])#同时，在整个训练样本中类别为1的词汇数+1
        else:
            p0Num+=trainMatrix[i]
            p1Denom+=sum(trainMatrix[i])
    p1Vect=p1Num/p1Denom
    p1Vect=[log(x) for x in p1Vect]#p1Vect表示条件概率P（Wi|c=1）
    p0Vect=p0Num/p0Denom
    p0Vect=[log(x) for x in p0Vect]#p0Vect表示条件概率P（Wi|c=0）
    return p0Vect,p1Vect,pAbusive

训练贝叶斯分类算法
def classifyNB(vec2classify,p0Vec,p1Vec,pclass1):
    p1=sum(vec2classify*p1Vec)+log(pclass1)
    p0=sum(vec2classify*p0Vec)+log(1.0-pclass1)
    if p1>p0:
        return 1
    else:
        return 0

测试分类模型
def testingNB():
    listOPosts,listclass=loadData()#加载数据集和类标号
    myVocabList=createVocaList(listOPosts)#创建词库
    trainMat=[]
    for postinDoc in listOPosts:#计算词库中的每个样本的出现情况
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V, p1V, pAb = trainNB0(numpy.array(trainMat), numpy.array(listclass))#计算条件概率
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = numpy.array(setOfWords2Vec(myVocabList, testEntry))
    print("testEntry classified as:{0}".format(classifyNB(thisDoc, p0V, p1V, pAb)))
    testEntry = ['stupid', 'garbage','quit']
    thisDoc = numpy.array(setOfWords2Vec(myVocabList, testEntry))
    print("testEntry classified as:{0}".format(classifyNB(thisDoc, p0V, p1V, pAb)))

利用朴素贝叶斯进行垃圾邮件测试

def textParse(bigstring):
    import re#导入正则式
    listOfTokens=re.split(r'\w*',bigstring)
    return [tok.lower() for tok in listOfTokens if len(tok)>2]#去掉少于两个字符的字符串，，并将所有的字符串转换为小写

def spamTest():
    docList=[]
    classList=[]
    fullText=[]
    for i in range(1,26):
        wordList=textParse(open('spam/%d.txt'%i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList=textParse(open('ham/%d.txt'%i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList=createVocaList(docList)
    trainingSet=list(range(50))
    testSet=[]
    for i in range(10):#随机选择十封邮件 作为测试集
        randIndex=int(random.uniform(0,len(trainingSet)))#随机选择十个数字，数字对应的文档被添加到测试集
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])#将选中的文档从训练集中删除
    trainMat=[]
    trainClasses=[]
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam=trainNB0(array(trainMat),array(trainClasses))
    errorCount=0
    for docIndex in testSet:
        wordVector=setOfWords2Vec(vocabList,docList[docIndex])
        if classifyNB(array(wordVector),p0V,p1V,pSpam)!=classList[docIndex]:
            errorCount+=1
        print("the error rate is {0}".format(float(errorCount)/len(testSet)))