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))
spamTest()
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)
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:
errorCount += 1
print('the error rate is:', float(errorCount)/len(testSet))
return vocabList, p0V, p1V
import feedparser
ny=feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
sf=feedparser.parse('http://sfbay.craigslist.org/stp/index.rss')
def getTopWords(ny,sf):
import operator
vocabList, p0V, p1V = localWords(ny, sf)
topNY=[]; topSF=[]
for i in range(len(p0V)):
if p0V > -6.0 :topSF.append((vocabList[i], p0V[i]))
if p1V > -6.0 :topNY.append((vocabList[i], p1V[i]))
sortedSF = sorted(topSF, key=lambda pair: pair[i], reverse=True)
print('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**')
for item in sortedNY:
print(item[0])
getTopWords(ny, sf)
localWords(ny, sf)
