标签：sub under line amt clist 相互 append 最大 hle
通常，将此公式成为后验概率公式。即在已知观察量A后得出的參数B的分布。当中p(Bi)称为先验概率，是人们依据经验给出的參数Bi的分布。
贝叶斯方法与最大似然法的差别就在于引入了先验概率，通过先验概率能够避免最大似然法所带来的过拟合问题。
故我们做出一个较强的如果，即Bi是相互独立的。这样条件概率能够表示为
当然在实际情况中。这样的相互独立的如果往往是不成立的，然而其还是能够在一定程度上给出对数据的描写叙述。
在训练过程中，须要计算两个概率：
* 先验概率p(Bi)=Num(Bi)Num(B)
* 条件概率p(A|Bi)=Num(A,Bi)Num(Bi)
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]
return postingList, classVec
def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)
return list(vocabSet)
def setOfWord2Vec(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 = ones(numWords)
p1Num = ones(numWords)
p0Denom = 2.0; p1Denom = 2.0
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 =log(p1Num/p1Denom)
p0Vect =log(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(setOfWord2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = trainNB0(array(trainMat), array(listClasses))
testEntry = [‘love‘, ‘my‘, ‘dalmation‘]
thisDoc = array(setOfWord2Vec(myVocabList, testEntry))
print testEntry, ‘classified as:‘, classifyNB(thisDoc, p0V, p1V, pAb)
testEntry=[‘stupid‘, ‘garbage‘]
thisDoc = array(setOfWord2Vec(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(‘email/spam/%d.txt‘ % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(open(‘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(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat=[]; trainClasses=[]
for docIndex in trainingSet:
trainMat.append(setOfWord2Vec(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam=trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = setOfWord2Vec(vocabList, docList[docIndex])
if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print ‘the error rate is: ‘,float(errorCount)/len(testSet)
def calcMostFreq(vocabList, fullText):
import operator
freqDict={}
for token in vocabList:
freqDict[token] = fullText.count(token)
sortedFreq = sorted(freqDict.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedFreq[:30]
def localWords(feed1, feed0):
import feedparser
docList=[]; classList=[]; fullText=[]
minLen = min(len(feed1[‘entries‘]), len(feed0[‘entries‘]))
for i in range(minLen):
wordList = textParse(feed1[‘entries‘][i][‘summary‘])
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse(feed0[‘entries‘][i][‘summary‘])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList)
top30Words = calcMostFreq(vocabList, fullText)
for pairW in top30Words:
if pairW[0] in vocabList:
vocabList.remove(pairW[0])
trainingSet = range(2*minLen)
testSet=[]
for i in range(20):
randIndex = int(random.uniform(0, len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
trainMat=[]; trainClasses=[]
for docIndex in trainingSet:
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet:
wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
errorCount += 1
print ‘the error rate is: ‘, float(errorCount)/len(testSet)
return vocabList, p0V, p1V
if __name__=="__main__":
listOPosts, listClasses = loadDataSet()
print listOPosts, listClasses
myVocabList = createVocabList(listOPosts)
print myVocabList
print setOfWord2Vec(myVocabList, listOPosts[0])
trainMat = []
for postinDoc in listOPosts:
trainMat.append(setOfWord2Vec(myVocabList, postinDoc))
p0V, p1V, pAb = trainNB0(trainMat, listClasses)
print p0V
print testingNB()
spamTest()
import feedparser
ny = feedparser.parse(‘http://newyork.craigslist.org/stp/index.rss‘)
sf = feedparser.parse(‘http://sfbay.craigslist.org/stp/index.rss‘)
vocabList,pSF,pNY=localWords(ny,sf)
标签：sub under line amt clist 相互 append 最大 hle
原文地址：https://www.cnblogs.com/ldxsuanfa/p/10728138.html
