[置顶] 贝叶斯分类(三)

前两篇已经将算法思想实现，这次对其进项下更新修正一些小的细节，我们知道计算概率乘积时候如果某个概率为0，那么概率相乘结果为0，这显然不是我们想要的结果，还有就是如果出现很多非常小的数相乘会向下溢出。

实现起来就修改4行代码：

    p0Num = ones(numWords)
    p1Num = ones(numWords)      #change to ones() 
    #print(p0Num,p1Num )
    p0Denom = 2.0
    p1Denom = 2.0                        #change to 0.0

同样后面的值也要取对数：

 

    p1Vect = log(p1Num/p1Denom)         #change to log()
    p0Vect = log(p0Num/p0Denom)     #change to log()

对了还有个词袋模型：

def bagOFWords2VecMN(vocabList,inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] +=1
    return returnVec

这样我们的朴素贝叶斯的理论和实际代码就都完成了。一定觉得非常简单，下面给出我的全部代码，方便大家使用：

from numpy import *
import time

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):
    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):
    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):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = zeros(numWords)
    p1Num = zeros(numWords)      #change to ones() 
    #print(p0Num,p1Num )
    p0Denom = 0.0
    p1Denom = 0.0                        #change to 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         #change to log()
    p0Vect = p0Num/p0Denom     #change to log()
    return p0Vect,p1Vect,pAbusive

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



listOposts,listClasses = loadDataSet()


myVocabList = createVocabList(listOposts)
print(myVocabList)

tmp= setOfWords2Vec(myVocabList, listOposts[0])
print(tmp)

trainMat =[]
for postinDoc in listOposts:
    trainMat.append(setOfWords2Vec(myVocabList, postinDoc))



p0V, p1V, pAb = trainNB0(trainMat, listClasses)

print(p0V)
print(p1V)
print(pAb)

testEntry = ['love', 'my','dalmation']

thisDoc = setOfWords2Vec(myVocabList, testEntry)

print(classifyNB(thisDoc, p0V, p1V, pAb))

来张截图：