怎么在Python中實(shí)現(xiàn)一個(gè)樸素貝葉斯算法-創(chuàng)新互聯(lián)
本篇文章為大家展示了怎么在Python中實(shí)現(xiàn)一個(gè)樸素貝葉斯算法，內(nèi)容簡(jiǎn)明扼要并且容易理解，絕對(duì)能使你眼前一亮，通過(guò)這篇文章的詳細(xì)介紹希望你能有所收獲。
#encoding:utf-8
#在該算法中類(lèi)標(biāo)簽為1和0，如果是多標(biāo)簽稍微改動(dòng)代碼既可
import numpy as np
path=u"D:\\Users\\zhoumeixu204\Desktop\\python語(yǔ)言機(jī)器學(xué)習(xí)\\機(jī)器學(xué)習(xí)實(shí)戰(zhàn)代碼 python\\機(jī)器學(xué)習(xí)實(shí)戰(zhàn)代碼\\machinelearninginaction\\Ch04\\"
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([])
for document in dataset:
vocabSet=vocabSet|set(document)
return list(vocabSet)
def setOfWordseVec(vocabList,inputSet):
returnVec=[0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)]=1 #vocabList.index() 函數(shù)獲取vocabList列表某個(gè)元素的位置，這段代碼得到一個(gè)只包含0和1的列表
else:
print("the word :%s is not in my Vocabulary!"%word)
return returnVec
listOPosts,listClasses=loadDataSet()
myVocabList=createVocabList(listOPosts)
print(len(myVocabList))
print(myVocabList)
print(setOfWordseVec(myVocabList, listOPosts[0]))
print(setOfWordseVec(myVocabList, listOPosts[3]))
#上述代碼是將文本轉(zhuǎn)化為向量的形式，如果出現(xiàn)則在向量中為1，若不出現(xiàn) ，則為0
def trainNB0(trainMatrix,trainCategory): #創(chuàng)建樸素貝葉斯分類(lèi)器函數(shù)
numTrainDocs=len(trainMatrix)
numWords=len(trainMatrix[0])
pAbusive=sum(trainCategory)/float(numTrainDocs)
p0Num=np.ones(numWords);p1Num=np.ones(numWords)
p0Deom=2.0;p1Deom=2.0
for i in range(numTrainDocs):
if trainCategory[i]==1:
p1Num+=trainMatrix[i]
p1Deom+=sum(trainMatrix[i])
else:
p0Num+=trainMatrix[i]
p0Deom+=sum(trainMatrix[i])
p1vect=np.log(p1Num/p1Deom) #change to log
p0vect=np.log(p0Num/p0Deom) #change to log
return p0vect,p1vect,pAbusive
listOPosts,listClasses=loadDataSet()
myVocabList=createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(setOfWordseVec(myVocabList, postinDoc))
p0V,p1V,pAb=trainNB0(trainMat, listClasses)
if __name__!='__main__':
print("p0的概況")
print (p0V)
print("p1的概率")
print (p1V)
print("pAb的概率")
print (pAb)運(yùn)行結(jié)果：
32
['him', 'garbage', 'problems', 'take', 'steak', 'quit', 'so', 'is', 'cute', 'posting', 'dog', 'to', 'love', 'licks', 'dalmation', 'flea', 'I', 'please', 'maybe', 'buying', 'my', 'stupid', 'park', 'food', 'stop', 'has', 'ate', 'help', 'how', 'mr', 'worthless', 'not']
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0]
# -*- coding:utf-8 -*-
#!python2
#構(gòu)建樣本分類(lèi)器testEntry=['love','my','dalmation'] testEntry=['stupid','garbage']到底屬于哪個(gè)類(lèi)別
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):
vocabSet=set([])
for document in dataset:
vocabSet=vocabSet|set(document)
return list(vocabSet)
def setOfWordseVec(vocabList,inputSet):
returnVec=[0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)]=1 #vocabList.index() 函數(shù)獲取vocabList列表某個(gè)元素的位置，這段代碼得到一個(gè)只包含0和1的列表
else:
print("the word :%s is not in my Vocabulary!"%word)
return returnVec
def trainNB0(trainMatrix,trainCategory): #創(chuàng)建樸素貝葉斯分類(lèi)器函數(shù)
numTrainDocs=len(trainMatrix)
numWords=len(trainMatrix[0])
pAbusive=sum(trainCategory)/float(numTrainDocs)
p0Num=np.ones(numWords);p1Num=np.ones(numWords)
p0Deom=2.0;p1Deom=2.0
for i in range(numTrainDocs):
if trainCategory[i]==1:
p1Num+=trainMatrix[i]
p1Deom+=sum(trainMatrix[i])
else:
p0Num+=trainMatrix[i]
p0Deom+=sum(trainMatrix[i])
p1vect=np.log(p1Num/p1Deom) #change to log
p0vect=np.log(p0Num/p0Deom) #change to log
return p0vect,p1vect,pAbusive
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
p1=sum(vec2Classify*p1Vec)+np.log(pClass1)
p0=sum(vec2Classify*p0Vec)+np.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(setOfWordseVec(myVocabList, postinDoc))
p0V,p1V,pAb=trainNB0(np.array(trainMat),np.array(listClasses))
print("p0V={0}".format(p0V))
print("p1V={0}".format(p1V))
print("pAb={0}".format(pAb))
testEntry=['love','my','dalmation']
thisDoc=np.array(setOfWordseVec(myVocabList, testEntry))
print(thisDoc)
print("vec2Classify*p0Vec={0}".format(thisDoc*p0V))
print(testEntry,'classified as :',classifyNB(thisDoc, p0V, p1V, pAb))
testEntry=['stupid','garbage']
thisDoc=np.array(setOfWordseVec(myVocabList, testEntry))
print(thisDoc)
print(testEntry,'classified as :',classifyNB(thisDoc, p0V, p1V, pAb))
if __name__=='__main__':
testingNB()運(yùn)行結(jié)果：
p0V=[-3.25809654 -2.56494936 -3.25809654 -3.25809654 -2.56494936 -2.56494936
-3.25809654 -2.56494936 -2.56494936 -3.25809654 -2.56494936 -2.56494936
-2.56494936 -2.56494936 -1.87180218 -2.56494936 -2.56494936 -2.56494936
-2.56494936 -2.56494936 -2.56494936 -3.25809654 -3.25809654 -2.56494936
-2.56494936 -3.25809654 -2.15948425 -2.56494936 -3.25809654 -2.56494936
-3.25809654 -3.25809654]
p1V=[-2.35137526 -3.04452244 -1.94591015 -2.35137526 -1.94591015 -3.04452244
-2.35137526 -3.04452244 -3.04452244 -1.65822808 -3.04452244 -3.04452244
-2.35137526 -3.04452244 -3.04452244 -3.04452244 -3.04452244 -3.04452244
-3.04452244 -3.04452244 -3.04452244 -2.35137526 -2.35137526 -3.04452244
-3.04452244 -2.35137526 -2.35137526 -3.04452244 -2.35137526 -2.35137526
-2.35137526 -2.35137526]
pAb=0.5
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0]
vec2Classify*p0Vec=[-0. -0. -0. -0. -0. -0. -0.
-0. -0. -0. -0. -0. -0. -0.
-1.87180218 -0. -0. -2.56494936 -0. -0. -0.
-0. -0. -0. -0. -0. -0.
-2.56494936 -0. -0. -0. -0. ]
['love', 'my', 'dalmation'] classified as : 0
[0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1]
['stupid', 'garbage'] classified as : 1
# -*- coding:utf-8 -*-
#! python2
#使用樸素貝葉斯過(guò)濾垃圾郵件
# 1.收集數(shù)據(jù)：提供文本文件
# 2.準(zhǔn)備數(shù)據(jù)：講文本文件見(jiàn)習(xí)成詞條向量
# 3.分析數(shù)據(jù)：檢查詞條確保解析的正確性
# 4.訓(xùn)練算法：使用我們之前簡(jiǎn)歷的trainNB0()函數(shù)
# 5.測(cè)試算法：使用classifyNB()，并且對(duì)建一個(gè)新的測(cè)試函數(shù)來(lái)計(jì)算文檔集的錯(cuò)誤率
# 6.使用算法，構(gòu)建一個(gè)完整的程序?qū)σ唤M文檔進(jìn)行分類(lèi)，將錯(cuò)分的文檔輸出到屏幕上
# import re
# mySent='this book is the best book on python or M.L. I hvae ever laid eyes upon.'
# print(mySent.split())
# regEx=re.compile('\\W*')
# print(regEx.split(mySent))
# emailText=open(path+"email\\ham\\6.txt").read()
import numpy as np
path=u"C:\\py\\jb51PyDemo\\src\\Demo\\Ch04\\"
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([])
for document in dataset:
vocabSet=vocabSet|set(document)
return list(vocabSet)
def setOfWordseVec(vocabList,inputSet):
returnVec=[0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)]=1 #vocabList.index() 函數(shù)獲取vocabList列表某個(gè)元素的位置，這段代碼得到一個(gè)只包含0和1的列表
else:
print("the word :%s is not in my Vocabulary!"%word)
return returnVec
def trainNB0(trainMatrix,trainCategory): #創(chuàng)建樸素貝葉斯分類(lèi)器函數(shù)
numTrainDocs=len(trainMatrix)
numWords=len(trainMatrix[0])
pAbusive=sum(trainCategory)/float(numTrainDocs)
p0Num=np.ones(numWords);p1Num=np.ones(numWords)
p0Deom=2.0;p1Deom=2.0
for i in range(numTrainDocs):
if trainCategory[i]==1:
p1Num+=trainMatrix[i]
p1Deom+=sum(trainMatrix[i])
else:
p0Num+=trainMatrix[i]
p0Deom+=sum(trainMatrix[i])
p1vect=np.log(p1Num/p1Deom) #change to log
p0vect=np.log(p0Num/p0Deom) #change to log
return p0vect,p1vect,pAbusive
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
p1=sum(vec2Classify*p1Vec)+np.log(pClass1)
p0=sum(vec2Classify*p0Vec)+np.log(1.0-pClass1)
if p1>p0:
return 1
else:
return 0
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(path+"email\\spam\\%d.txt"%i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList=textParse(open(path+"email\\ham\\%d.txt"%i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList=createVocabList(docList)
trainingSet=range(50);testSet=[]
for i in range(10):
randIndex=int(np.random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del (trainingSet[randIndex])
trainMat=[];trainClasses=[]
for docIndex in trainingSet:
trainMat.append(setOfWordseVec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam=trainNB0(np.array(trainMat),np.array(trainClasses))
errorCount=0
for docIndex in testSet:
wordVector=setOfWordseVec(vocabList, docList[docIndex])
if classifyNB(np.array(wordVector), p0V, p1V, pSpam)!=classList[docIndex]:
errorCount+=1
print 'the error rate is :',float(errorCount)/len(testSet)
if __name__=='__main__':
spamTest()運(yùn)行結(jié)果：
the error rate is : 0.0
上述內(nèi)容就是怎么在Python中實(shí)現(xiàn)一個(gè)樸素貝葉斯算法，你們學(xué)到知識(shí)或技能了嗎？如果還想學(xué)到更多技能或者豐富自己的知識(shí)儲(chǔ)備，歡迎關(guān)注創(chuàng)新互聯(lián)行業(yè)資訊頻道。
名稱(chēng)欄目：怎么在Python中實(shí)現(xiàn)一個(gè)樸素貝葉斯算法-創(chuàng)新互聯(lián)
文章位置：http://jinyejixie.com/article20/djsdco.html
成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供自適應(yīng)網(wǎng)站、建站公司、網(wǎng)站改版、網(wǎng)站設(shè)計(jì)公司、標(biāo)簽優(yōu)化、App開(kāi)發(fā)
聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶(hù)投稿、用戶(hù)轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請(qǐng)盡快告知，我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng)，如需處理請(qǐng)聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時(shí)需注明來(lái)源： 創(chuàng)新互聯(lián)
猜你還喜歡下面的內(nèi)容
- Centos下Yum安裝PHP5.5,5.6-創(chuàng)新互聯(lián)
- 怎么使用python的f-string格式化輸出-創(chuàng)新互聯(lián)
- 在Mac上刪除自己安裝的Python方法-創(chuàng)新互聯(lián)
- xyz域名可以投資嗎-創(chuàng)新互聯(lián)
- 怎么在.NET中使用Dapper操作mysql數(shù)據(jù)庫(kù)-創(chuàng)新互聯(lián)
- windows10專(zhuān)業(yè)版的遠(yuǎn)程服務(wù)器管理工具下載-創(chuàng)新互聯(lián)
- jquery比較兩個(gè)數(shù)字大小的示例-創(chuàng)新互聯(lián)
- 如何進(jìn)行正確的電子商務(wù)網(wǎng)站建設(shè)設(shè)計(jì) 2013-11-09
- 電子商務(wù)的一般框架 2022-05-07
- 電子商務(wù)之電子物流體系的建設(shè)與發(fā)展分析 2022-05-19
- 電子商務(wù)微博推廣的歧途有哪些 2022-06-24
- 將您的電子商務(wù)營(yíng)銷(xiāo)策略提升到新的水平 2022-08-06
- 值得期待的5個(gè)電子商務(wù)發(fā)展趨勢(shì) 2021-02-10
- 電子商務(wù)網(wǎng)站建設(shè)的必要性 2021-04-14
- 電子商務(wù)所提供的服務(wù)，保證包您滿(mǎn)意！ 2021-02-01
- 新聞動(dòng)態(tài)新媒體之于電子商務(wù)發(fā)展的意義 2022-05-09
- 成功電子商務(wù)網(wǎng)站的主要特征有哪些？ 2022-02-01
- 電子商務(wù)的未來(lái)發(fā)展的模擬模式 2014-02-24
- 關(guān)于電子商務(wù)商城網(wǎng)站建站的全局考慮 2022-06-20