樸素貝葉斯算法

# coding=utf-8
from math import log
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 代表侮辱性文字  0代表正常言論
    return postingList,classVec

# 創建一個帶有所有單詞的列表
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

# 另一種模型
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if(word in vocabList):
            returnVec[vocabList.index(word)] += 1
    return returnVec

def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    # 防止多個概率的成績當中的一個爲0
    p0Num = zeros(numWords);p1Num = zeros(numWords)
    p0Denom = 0.0;p1Denom = 0.0
    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 = p1Num/p1Denom # 出於精度的考慮，否則很可能到限歸零
    p0Vect = p0Num/p0Denom
    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 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 main():
    testingNB()

if __name__ == "__main__":
    main()