朴素贝叶斯

1、相关公式：朴素贝叶斯最核心的部分是贝叶斯法则，而贝叶斯法则的基石是条件概率

• 贝叶斯法则：

• 条件概率：

2、实现代码

# coding:utf-8
from math import log
from numpy import ones,zeros
import numpy as np

def loadDataSet():
    # 六句话
    postingList=[['my','dog','has','flea','problem','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']]
    # 六句话对应的类型，0为普通类型语言，1为侮辱性语言
    classVec=[0,1,0,1,0,1]
    return postingList,classVec

def createVocabList(dataSet):
    vocabSet=set([])
    for document in dataSet:
        vocabSet=vocabSet|set(document)
    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 bagOfWords2Vec(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 trainNB(trainMatrix,trainCategory):                                        
    numTrainDocs=len(trainMatrix)     
    numWords=len(trainMatrix[0])        
    pAbusive=sum(trainCategory)/float(numTrainDocs) #统计侮辱性文档的总个数，然后除以总文档个数  
    p0Num=zeros(numWords);p1Num=zeros(numWords)    # 把属于同一类的文本向量加起来
    p0Denom=0.0;p1Denom=0.0
#    避免出现0值
#     p0Num=ones(numWords);p1Num=ones(numWords)
#     p0Denom=2.0;p1Denom=2.0
    for i in range(numTrainDocs):
        if trainCategory[i]==1: 
            p1Num+=trainMatrix[i]#把属于同一类的文本向量相加，实质是统计某个词条在该类文本中出现频率
            p1Denom+=sum(trainMatrix[i]) #把侮辱性文档向量的所有元素加起来
        else:
            p0Num+=trainMatrix[i]
            p0Denom+=sum(trainMatrix[i]) 
    p1Vec=p1Num/float(p1Denom) 
    p0Vec=p0Num/float(p0Denom)
#    防止出现下溢出
#     p1Vec=[log(x) for x in p1Num/p1Denom] #统计词典中所有词条在侮辱性文档中出现的概率
#     p0Vec=[log(x) for x in p0Num/p0Denom] #统计词典中所有词条在正常文档中出现的概率
    return pAbusive,p0Vec,p1Vec

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