机器学习-朴素贝叶斯分类

# coding=utf-8

#朴素贝叶斯分类，P（ci|X)=P(X|ci)*P(ci)/P(X),因为P(X)与类无关，每个样本对各个类的概率一样。
#假设各特征相互独立，对一样本的不同类，可求P(X|ci)*P(ci)=P(X1|ci)P(X2|ci).。。P(Xn|ci)*P(ci)
#概率大着即为其类
#先根据所有样本，求所有特征的条件概率P(X1|ci)P(X2|ci).。。P(Xn|ci)和分类概率P(ci)
#样本X用0，1组成的向量表示，则dot(X,P(X1|ci)P(X2|ci).。。P(Xn|ci))即得到其对应的特征的条件概率，再*P(ci)就得到
#其对应的属于Ci类的概率，大则为其类


from numpy import *

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): #'建立词汇表集合=n个特征'
    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):#'将话语词汇与词汇表对照映射成0、1组成的n特征向量'
    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 trainNB0(trainMatrix,trainCategory):#'训练样本得到P(X1|ci)P(X2|ci).。。P(Xn|ci)，P(ci)
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)   #P(c1) 脏话
    p0Num = ones(numWords); p1Num = ones(numWords)      #change zeros() to ones() '防止有P(Xj|Ci)=0使联合概率成0'
    p0Denom = 2.0; p1Denom = 2.0                        #change 0.0 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() '进行对数变换，变*为+,ln(a*b)=lna+lnb防止很小的数连乘下溢出成0'
    p0Vect = log(p0Num/p0Denom)          #change to log() 'ln(f(x))和f(x)的极值点一致，走势一致'
    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 bagOfWords2VecMN(vocabList, inputSet): #'文档词袋模型:当话语中的特征词汇出现多次，使对应的向量特征+1，而不是=1。增强其对分类的影响'
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    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 textParse(bigString):    #input is big string, #output is word list
    import re
    listOfTokens = re.split(r'\W*', bigString) #'分隔符为除单词数字外的任意字符串'
    return [tok.lower() for tok in listOfTokens if len(tok) > 2] #'去掉空字符串并变小写'

testingNB()