'''
Created on Oct 19, 2010
@author: Peter
'''
from numpy import *
import jieba
import string
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 = np.ones(numWords); p1Num = np.ones(numWords) #change to ones()
p0Denom = numWords; p1Denom = numWords #change to numWords
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 = np.log(p1Num/p1Denom) #change to log()
p0Vect = np.log(p0Num/p0Denom) #change to log()
return p0Vect,p1Vect,pAbusive
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + np.log(pClass1) #element-wise mult
p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
def bagOfWords2VecMN(vocabList, inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
def testingNB():
listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(bagOfWords2VecMN(myVocabList, postinDoc))
p0V,p1V,pAb = trainNB0(np.array(trainMat),np.array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = np.array(bagOfWords2VecMN(myVocabList, testEntry))
print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
testEntry = ['stupid', 'garbage']
thisDoc = np.array(bagOfWords2VecMN(myVocabList, testEntry))
print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
def textParse(bigString): #input is big string, #output is word list
import re
listOfTokens = re.split(r'\W*', bigString)
return [tok.lower() for tok in listOfTokens if len(tok) > 2]
def textParse2(bigString):
stop_f=open('d:/email/stopwords.txt',encoding='utf8')
stopwords=list()
for line in stop_f.readlines():
line=line.strip()
stopwords.append(line)
stop_f.close()
seg_list=jieba.lcut(bigString,cut_all=False)
outstr=[]
for i in seg_list:
if i not in stopwords and i not in string.punctuation:
outstr.append(i)
return outstr
def spamTest():
docList=[]; classList = []; fullText =[]
for i in range(1,26):
wordList = textParse2(open('d:/email/spam/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = textParse2(open('d:/email/ham/%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList)#create vocabulary
trainingSet = list(range(50)); testSet=[] #create test set
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:#train the classifier (get probs) trainNB0
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
if classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
errorCount += 1
#print("classification error",docList[docIndex])
#print('the error rate is: ',float(errorCount)/len(testSet))
#return vocabList,fullText
return 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) #NY is class 1
wordList = textParse(feed0['entries'][i]['summary'])
docList.append(wordList)
fullText.extend(wordList)
classList.append(0)
vocabList = createVocabList(docList)#create vocabulary
top30Words = calcMostFreq(vocabList,fullText) #remove top 30 words
for pairW in top30Words:
if pairW[0] in vocabList: vocabList.remove(pairW[0])
trainingSet = range(2*minLen); testSet=[] #create test set
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:#train the classifier (get probs) trainNB0
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
errorCount = 0
for docIndex in testSet: #classify the remaining items
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
def getTopWords(ny,sf):
import operator
vocabList,p0V,p1V=localWords(ny,sf)
topNY=[]; topSF=[]
for i in range(len(p0V)):
if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
print "SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**"
for item in sortedSF:
print item[0]
sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
print "NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**"
for item in sortedNY:
print item[0]
运行100次后取平均值:
re=0
for i in range(100):
re+=spamTest()
re/100.0
结果为:0.008