def summaryGenerator(class_name, tweets, folder_mode, ranker):
tweets=tweetCleaner(tweets) #Some cleaning
#print "Set of Tweets=>", len(tweets)
#tweetlist=[tweet for tweet in tweets]
#print "List of tweets", tweetlist
genSentences=wg.retrieveNewSentences(tweets, stopwords)
wordScores=createDict(mainDatafolder+"/"+folder_mode['Extract']+"/"+class_name+"/"+class_name+"_weight.txt")
#emptysentences=[sent for sent in genSentences if len(sent.strip())==0]
#print "EMPTY::::", len(emptysentences)
'''
This is where the ILP works to select the best sentences and form the summary
'''
finalSentencesRetained=wg.solveILP(genSentences,wordScores,
lm,
stopwords,
ranker,
intraGenSimThreshold=0.25,
l_max=200
)
return finalSentencesRetained
def summaryGenerator(class_name, tweets, folder_mode, ranker):
tweets = tweetCleaner(tweets) #Some cleaning
#print "Set of Tweets=>", len(tweets)
#tweetlist=[tweet for tweet in tweets]
#print "List of tweets", tweetlist
genSentences = wg.retrieveNewSentences(tweets, stopwords)
wordScores = createDict(mainDatafolder + "/" + folder_mode['Extract'] +
"/" + class_name + "/" + class_name +
"_weight.txt")
#emptysentences=[sent for sent in genSentences if len(sent.strip())==0]
#print "EMPTY::::", len(emptysentences)
'''
This is where the ILP works to select the best sentences and form the summary
'''
finalSentencesRetained = wg.solveILP(genSentences,
wordScores,
lm,
stopwords,
ranker,
intraGenSimThreshold=0.25,
l_max=200)
return finalSentencesRetained
#for text in v:
origSentences.append(text)
text=re.sub(p, '', text)
text=text.strip().split('./PUNCT')
for r in text:
if len(r.strip())!=0:
tweets.append(r.strip()+' ./PUNCT')
tweets=set(tweets)
#print len(tweets), tweets
genSentences=WGGraph.retrieveNewSentences(tweets, english_postagger, stopwords)
gengroupList.append(genSentences)
print "Done with ", clustNum
print gengroupList
print 'Num of clusters', len(gengroupList)
finalSentencesRetained=WGGraph.solveILP(gengroupList,lm, stopwords, origSentences, intraGenSimThreshold=0.2, l_max=10)
txtSummary=""
for sent in finalSentencesRetained:
sent=sentenceCapitalize(sent)
txtSummary=txtSummary+"\n"+sent
#print 'Number of tweets', len(tweets) , tweets
txtSummary=txtSummary.strip()
writeAbstracts.write("==========="+eventfile+"~"+str(i)+":========\n"+txtSummary+"\n\n")
writeAbstracts.close()
for r in text:
if len(r.strip()) != 0:
tweets.append(r.strip() + ' ./PUNCT')
tweets = set(tweets)
#print len(tweets), tweets
genSentences = WGGraph.retrieveNewSentences(
tweets, english_postagger, stopwords)
gengroupList.append(genSentences)
print "Done with ", clustNum
print gengroupList
print 'Num of clusters', len(gengroupList)
finalSentencesRetained = WGGraph.solveILP(gengroupList,
lm,
stopwords,
origSentences,
intraGenSimThreshold=0.2,
l_max=10)
txtSummary = ""
for sent in finalSentencesRetained:
sent = sentenceCapitalize(sent)
txtSummary = txtSummary + "\n" + sent
#print 'Number of tweets', len(tweets) , tweets
txtSummary = txtSummary.strip()
writeAbstracts.write("===========" + eventfile + "~" + str(i) +
":========\n" + txtSummary + "\n\n")
writeAbstracts.close()