【机器学习】朴素贝叶斯进行文本分类

基本步骤（2分类）：

根据要分类的文本，建立不重复词的列表->对于每一条文本，转化‘文档向量’（此向量长度为上一步的列表，值为1或者0）

->根据计算分类概率，大概思路是训练一个文档集合（已转化为文档向量），若文档为1，把文档list对应位置相加作为分子，同时分母+1，这样最后加起来的list再除分母（后面称这个分子除分母为listA）就得到了文档为1时所有单词的概率，即，在预测x文档向量时，直接可以用x与listA对应位置相乘，得到的就是x的，因为x也是文档向量，对应位置相乘后不是x的就已经为0了，最后再把这个x的list求和就行了，为什么不相乘，因为已经转化为log了，见下面代码。文档为0时同理，比较下哪个大就行了

具体代码：

import numpy as np
#创建数据集
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

#将数据集的所有条记录合并为一个集合
def createVocabList(dataSet):
    vocabSet = set([])  # create empty set
    for document in dataSet:
        vocabSet = vocabSet | set(document)  # union of the two sets
    return list(vocabSet)

#判断inputSet中的单词是否出现在vocabList中，并返回位置
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


#算出每一个单词在其分类中的条件概率（某类别单词在此类别所有文章中出现的次数÷此类别所有的单词数），得出的是最能代表此类别的单词
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)     #垃圾邮件的比例(侮辱性词汇的概率，即p（c）)
    p0Num = np.ones(numWords); p1Num = np.ones(numWords)      #change to ones()
    p0Denom = 2.0; p1Denom = 2.0                        #change to 2.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:                       #求p（a|c=1）
            p1Num += trainMatrix[i]
            p1Denom =p1Denom+1
        else:                                             #求p（a|c=0）
            p0Num += trainMatrix[i]
            p0Denom =p0Denom+1
    p1Vect = np.log(p1Num/p1Denom)          #change to log() 转成log后可将本来的连乘变为连加，防止概率过小相乘后为0
    p0Vect = np.log(p0Num/p0Denom)          #change to log()
    return p0Vect,p1Vect,pAbusive


# listOPosts,listClasses=loadDataSet()
# myVocabList=createVocabList(listOPosts)
# print("myVoc:",myVocabList)
# trainMat=[]
# for postinDoc in listOPosts:
#     trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
# p0v,p1v,pAb=trainNB0(trainMat,listClasses)
# print('p1v',p1v)

#分类方法
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)    #element-wise mult
    p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0


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

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



# testingNB()