def compareDomains(files):
domains = []
for bf in files:
doms = {}
f = open(bf)
#ls = f.readlines()
#ls = [l.strip() for l in ls]
for l in f:
l = l.strip()
p = l.split(" ")
if int(p[1]) > 1:
doms[p[0]] = int(p[1])
'''
if p[0] in doms:
doms[p[0]]+= int(p[1])
else:
doms[p[0]] = int(p[1])
'''
domains.append(doms)
f.close()
comps = []
sets = []
for d in domains:
s = set(d.keys())
sets.append(s)
for i in range(len(sets)):
for j in range(i+1,len(sets)):
comps.append(len(getIntersection(sets[i],sets[j])))
print comps
ks = [len(s) for s in sets]
print ks
return comps
def getIndicativeSentences(self, topK, intersectionTh):
if len(self.indicativeSentences) > 0:
return self.indicativeSentences
else:
topToksTuples = self.indicativeWords[:topK]
#topToksTuples = self.indicativeWords
topToks = [k for k, _ in topToksTuples]
for d in self.documents:
sents = d.getSentences()
if sents and len(sents) > 0:
self.sentences.extend(sents)
impSents = {}
for sent in self.sentences:
if sent not in impSents:
sentToks = utils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = utils.getIntersection(topToks, sentToks)
if len(intersect) >= intersectionTh:
#impSents[sent] = len(intersect)
impSents[sent] = intersect
#print intersect
#if sent not in impSentsF:
# impSentsF[sent] = len(intersect)
#allImptSents.append(impSents)
if impSents:
#self.indicativeSentences = utils.getSorted(impSents.items(),1)
self.indicativeSentences = sorted(impSents.items(),
key=lambda x: len(x[1]),
reverse=True)
#sortedToksTFDF = sorted(toksTFDF.items(), key=lambda x: x[1][0], reverse=True)
return self.indicativeSentences
def getIndicativeSentences(self, topK, intersectionTh):
if len(self.indicativeSentences) > 0:
return self.indicativeSentences
else:
topToksTuples = self.indicativeWords[:topK]
topToks = [k for k, _ in topToksTuples]
for d in self.documents:
sents = d.getSentences()
self.sentences.extend(sents)
impSents = {}
for sent in self.sentences:
if sent not in impSents:
sentToks = utils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = utils.getIntersection(topToks, sentToks)
if len(intersect) > intersectionTh:
impSents[sent] = len(intersect)
#if sent not in impSentsF:
# impSentsF[sent] = len(intersect)
#allImptSents.append(impSents)
self.indicativeSentences = utils.getSorted(impSents.items(), 1)
return self.indicativeSentences
def getIndicativeSentences(self,topK,intersectionTh):
if len(self.indicativeSentences) > 0:
return self.indicativeSentences
else:
topToksTuples = self.indicativeWords[:topK]
#topToksTuples = self.indicativeWords
topToks = [k for k,_ in topToksTuples]
for d in self.documents:
sents = d.getSentences()
if sents and len(sents)>0:
self.sentences.extend(sents)
impSents ={}
for sent in self.sentences:
if sent not in impSents:
sentToks = utils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = utils.getIntersection(topToks, sentToks)
if len(intersect) > intersectionTh:
#impSents[sent] = len(intersect)
impSents[sent] = intersect
#print intersect
#if sent not in impSentsF:
# impSentsF[sent] = len(intersect)
#allImptSents.append(impSents)
if impSents:
#self.indicativeSentences = utils.getSorted(impSents.items(),1)
self.indicativeSentences = sorted(impSents.items(),key=lambda x: len(x[1]), reverse=True)
#sortedToksTFDF = sorted(toksTFDF.items(), key=lambda x: x[1][0], reverse=True)
return self.indicativeSentences
def getIndicativeSentences(self,topK,intersectionTh):
if len(self.indicativeSentences) > 0:
return self.indicativeSentences
else:
topToksTuples = self.indicativeWords[:topK]
topToks = [k for k,_ in topToksTuples]
for d in self.documents:
sents = d.getSentences()
self.sentences.extend(sents)
impSents ={}
for sent in self.sentences:
if sent not in impSents:
sentToks = utils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = utils.getIntersection(topToks, sentToks)
if len(intersect) > intersectionTh:
impSents[sent] = len(intersect)
#if sent not in impSentsF:
# impSentsF[sent] = len(intersect)
#allImptSents.append(impSents)
self.indicativeSentences = utils.getSorted(impSents.items(),1)
return self.indicativeSentences
def getDocsVecs(self):
n= len(self.docs_bow)
indexWordsSet = self.index.keys()
self.docsVecs = []
for doc_bow in self.docs_bow:
docVec = {}
docWordsSet = set(doc_bow.keys())
commWords = eventUtils.getIntersection(indexWordsSet, docWordsSet)
for w in commWords:
idf = math.log(n/self.index[w]['docFreq'])
tf_idf = doc_bow[w] * idf
docVec[w]=tf_idf
self.docsVecs.append(docVec)
def webpageEntities(self, docText=""):
disasters = set(self.entities["Disaster"].keys())
sentences = eventUtils.getSentences(docText)
webpageEnts = []
for sent in sentences:
sentToks = eventUtils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = eventUtils.getIntersection(disasters, sentToks)
if len(intersect) > self.intersectionTh:
#print intersect
sentEnts = eventUtils.getEntities(sent)[0]
if sentEnts.has_key('LOCATION') or sentEnts.has_key('DATE'):
sentEnts['Disaster'] = intersect
webpageEnts.append((sent, sentEnts))
return webpageEnts
def webpageEntities(self,docText=""):
disasters=set(self.entities["Disaster"].keys())
sentences = eventUtils.getSentences(docText)
webpageEnts =[]
for sent in sentences:
sentToks = eventUtils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = eventUtils.getIntersection(disasters, sentToks)
if len(intersect) > self.intersectionTh:
#print intersect
sentEnts = eventUtils.getEntities(sent)[0]
if sentEnts.has_key('LOCATION') or sentEnts.has_key('DATE'):
sentEnts['Disaster'] = intersect
webpageEnts.append((sent,sentEnts))
return webpageEnts
def getEM_Sents(wps):
docsEntities=[]
docsEntitiesFreq = []
entitiesProb = {}
collSents = []
#for i,wp in enumerate(wps):
for wp in wps:
if 'text' not in wp:
continue
wpContent = wp['text']+wp['title']
wpSplit = wpContent.split('\n')
wpFiltered = filter(None,wpSplit)
wpContentf = '\n'.join(wpFiltered)
sents = eventUtils.getSentences(wpContentf)
collSents.append(sents)
allSents = []
for sents in collSents:
allSents.extend(sents)
fw = eventUtils.getFreqTokens(allSents)
fw = [w[0] for w in fw]
#collFilteredSents = []
collEventModelInsts=[]
for sents in collSents:
filtEvtModelInsts = []
for s in sents:
sentToks = eventUtils.getTokens(s)
cw = eventUtils.getIntersection(fw, sentToks)
if len(cw) >= 2:
emi = {}
emi['TOPIC'] = list(cw)
ents = eventUtils.getEntities(s)[0]
if ents.has_key('LOCATION'):
emi['LOCATION'] = ents['LOCATION']
#filtEvtModelInsts.append(emi)
if ents.has_key('DATE'):
#emi['TOPIC'] = cw
emi['DATE']=ents['DATE']
filtEvtModelInsts.append(emi)
collEventModelInsts.append(filtEvtModelInsts)
'''
def webpageEntities_old(self, docText=""):
disasters = self.entities["Disaster"]
sentences = eventUtils.getSentences(docText)
#impSentences = getIndicativeSents(sentences, disasters, len(disasters), 0)
#impSentences = []
webpageEnts = []
for sent in sentences:
sentToks = eventUtils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = eventUtils.getIntersection(disasters, sentToks)
if len(intersect) > self.intersectionTh:
#impSentences.append(sent)
sentEnts = eventUtils.getEntities(sent)[0]
if sentEnts.has_key('LOCATION') or sentEnts.has_key('DATE'):
sentEnts['Disaster'] = intersect
webpageEnts.append((sent, sentEnts))
#entities = getEntities(impSentences)
#webpageEnts = zip(impSentences,entities)
return webpageEnts
def webpageEntities_old(self,docText=""):
disasters=self.entities["Disaster"]
sentences = eventUtils.getSentences(docText)
#impSentences = getIndicativeSents(sentences, disasters, len(disasters), 0)
#impSentences = []
webpageEnts =[]
for sent in sentences:
sentToks = eventUtils.getTokens(sent)
if len(sentToks) > 100:
continue
intersect = eventUtils.getIntersection(disasters, sentToks)
if len(intersect) > self.intersectionTh:
#impSentences.append(sent)
sentEnts = eventUtils.getEntities(sent)[0]
if sentEnts.has_key('LOCATION') or sentEnts.has_key('DATE'):
sentEnts['Disaster'] = intersect
webpageEnts.append((sent,sentEnts))
#entities = getEntities(impSentences)
#webpageEnts = zip(impSentences,entities)
return webpageEnts
