from numpy import *
def loadDataSet():
postingList = [['my', 'dog', 'has', 'flea', 'problem', '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 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 = ones(numWords); p1Num = ones(numWords)
p0Demon = 2.0; p1Demon = 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i]
p1Demon += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Demon += sum(trainMatrix[i])
p1Vect = log(p1Num/p1Demon)
p0Vect = log(p0Num/p0Demon)
return p0Vect, p1Vect, pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1)
p0 = sum(vec2Classify * p0Vec) + log(1 - 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('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(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)
**总结**
1. 使用概率有时比使用硬规则更为有效,贝叶斯概率及贝叶斯准则提供了一种利用已知值来估计未知概率的有效方法
2. 可以通过特征之间对条件独立性假设,降低对数据量的需要。尽管条件独立性假设并不正确,但是朴素贝叶斯仍然是一种有效的分类器
3. 利用现代编程语言实现朴素贝叶斯时需要考虑很多实际因素。下溢就是其中一个问题,它可以通过对概率取对数来解决。词袋模型在解决文档分类问题上比词集模型有所提高。还有其他一些方面的改进,比如说移除停用词,当然也可以花大量事件对切分器进行优化。