朴素贝叶斯的实现

'''
Created on 2017年8月10日

@author: fujianfei
'''
import numpy as np

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):
    '''
    .产生一个词汇set，里面包含了所有的词，但不重复
    '''
    vocaList = set([])
    for vocaRow in dataSet:
        vocaList = vocaList | set(vocaRow)#与每行不重复词汇取并，表示如果vocaList原先有这些词汇，则过，没有则加上
    return list(vocaList)

def setOfWords2Vec(vocaList, inputSet):
    '''
    .将输入的词组变成0,1向量，vocaList中某个词在inputSet中出现，则为1，否则为0
    '''
    numVect = [0] * len(vocaList)
    for input in inputSet:
        if input in vocaList:
            numVect[vocaList.index(input)] = 1
    return numVect

def trainNB(trainMat, trainCategory):
    '''
    .用来训练数据，生成类别C的先验概率P(C)和条件概率P(X|C)
    '''
    numTrain = len(trainMat)
    numWords = len(trainMat[0])
    pc = sum(trainCategory)/float(numTrain)
    p0Num = np.zeros(numWords);p1Num = np.zeros(numWords)
    p0Denom = 0.0;p1Denom = 0.0
    for i in range(numTrain):
        if trainCategory[i] == 1:
            p1Num += trainMat[i]
            p1Denom += np.sum(trainMat[i])
        else:
            p0Num += trainMat[i]
            p0Denom += np.sum(trainMat[i])    
    p1Vect = p1Num/p1Denom
    p0Vect = p0Num/p0Denom
    return p0Vect,p1Vect,pc        

def classifyNB(vec2Classify, p0Vect, p1Vect, pClass1):
    p1 = np.sum(vec2Classify * p1Vect) + np.log(pClass1)
    p0 = np.sum(vec2Classify * p0Vect) + np.log(1-pClass1)
    print(p1,p0)
    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 = trainNB(np.array(trainMat),np.array(listClasses))
#     print(p0V,p1V,pAb)
    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()