貝葉斯是搞概率論的。學(xué)術(shù)圈上有個(gè)貝葉斯學(xué)派。看起來(lái)吊吊的。關(guān)于貝葉斯是個(gè)啥網(wǎng)上有很多資料。想必讀者基本都明了。我這里只簡(jiǎn)單概括下：貝葉斯分類其實(shí)就是基于先驗(yàn)概率的基礎(chǔ)上的一種分類法，核心公式就是條件概率。舉個(gè)俗氣的例子，通過(guò)我們的以往觀察，鯉魚中尾巴是紅色的占比達(dá)90%，鯽魚中尾巴是紅色的占比只有1%不到，那么新來(lái)了一條小魚，他是鯉魚還是鯽魚呢？我看一下他的尾巴，發(fā)現(xiàn)是紅色，根據(jù)過(guò)去的先驗(yàn)概率經(jīng)驗(yàn)，它是鯉魚的概率比較大，我認(rèn)為它是鯉魚。

這當(dāng)時(shí)是個(gè)最簡(jiǎn)單的例子，實(shí)踐中的問題就復(fù)雜了。比如說(shuō)特征不止是尾巴紅不紅，還有魚嘴巴大不大，魚肥不肥，魚身子長(zhǎng)還是寬，各種，而且不是一個(gè)特征就能分辨出來(lái)的，還需要多方分析，然后貝爺感覺這個(gè)那個(gè)的真麻煩，就先假定每個(gè)特征都是獨(dú)立的，如果一條魚紅尾巴大嘴巴肥得很還是長(zhǎng)身子，就這樣求她是鯉魚的概率：鯉魚中紅尾巴0.9*鯉魚中大嘴巴0.3*鯉魚中肥豬0.6*鯉魚中長(zhǎng)身子0.4=0.27*0.24.。。。。

閑話少扯。上代碼分析。我代碼干的不是魚的分類了，而是一篇文檔。

from numpy import *

def loadDataSet():#這個(gè)函數(shù)呢，他建立了一個(gè)敏感詞典，并打了標(biāo)簽，共6個(gè)詞集合，其中2、4、6詞集合中的詞是敏感詞

postingList = [['my','dog','has','flea',\

'problems','help','please'],

['maybe','not','take','him',\

'to','dog','park','stupid'],

['my','dalmation','is','so','cute',\

'T','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]

return postingList,classVec

def createVocabList(dataSet):#這個(gè)函數(shù)呢，它是把輸入的dataset(就是一個(gè)新文檔嘛)進(jìn)行分解處理，返回的是這個(gè)文檔沒有重復(fù)詞的列表

vocabSet = set([])

for document in dataSet:

vocabSet = vocabSet | set(document)

return list(vocabSet)

def setOfWords2Vec(vocabList,inputSet):#這個(gè)函數(shù)呢，他就是根據(jù)輸入的新文檔，和詞匯表，來(lái)對(duì)新文檔打標(biāo)簽，看他有多少敏感詞，只要是出現(xiàn)了詞匯表里的詞，就將標(biāo)簽打1，沒有就默認(rèn)為0

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)

pAbusive = sum(trainCategory) / float(numTrainDocs)

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

p0Vect = p0Num /p0Denom

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

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 bagOfWords2VecMN(vocabList,inputSet):

returnVec = [0]*len(vocabList)

for word in inputSet:

if word in vocabList:

returnVec[vocabList.index(word)] +=1

return returnVec

def textParse(bigString):

import re

listOfTokens = re.split(r'\W*',bigString)

return [tok.lower() for tok in listOfTokens if len(tok) >2]

def spamTest():

docList = []; classList = [];fullText = []

for i in range(1,26):

wordList = textParse(open('E:/數(shù)據(jù)挖掘/MLiA_SourceCode/machinelearninginaction/Ch04/email/spam/%d.txt' % i).read())

docList.append(wordList)

fullText.extend(wordList)

classList.append(1)

#?? print('zhe li de i shi %d,',? i)

wordList = textParse(open('E:/數(shù)據(jù)挖掘/MLiA_SourceCode/machinelearninginaction/Ch04/email/ham/%d.txt' % i).read())

docList.append(wordList)

fullText.extend(wordList)

classList.append(0)

vocabList = createVocabList(docList)

trainingSet = list(range(50));testSet=[]

for i in range(10):

randIndex? = int(random.uniform(0,len(trainingSet)))

testSet.append(trainingSet[randIndex])

del(trainingSet[randIndex])

trainMat=[];trainClasses=[]

for docIndex in trainingSet:

trainMat.append(setOfWords2Vec(vocabList,docList[docIndex]))

trainClasses.append(classList[docIndex])

p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))

errorCount=0

for docIndex in testSet:

wordVector = setOfWords2Vec(vocabList,docList[docIndex])

if classifyNB(array(wordVector),p0V,p1V,pSpam) !=classList[docIndex]:

errorCount +=1

print ('the error rate is :',float(errorCount)/len(testSet))

總結(jié)

以上是生活随笔為你收集整理的贝叶斯分类python代码_机器学习实战之朴素贝叶斯进行文档分类（Python 代码版）...的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。