def buildEventModel(self, keywordsTh, seedURLs):
corpus = Collection(seedURLs)
#NoTFDF
sortedToksTFDF = corpus.getIndicativeWords()
self.toksTFDFDic = dict(sortedToksTFDF)
#print sortedToksTFDF
#sortedImptSents = corpus.getIndicativeSentences(self.topK,self.intersectionTh)
sortedImptSents = corpus.getIndicativeSentences(
keywordsTh, self.intersectionTh)
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
self.entities['LOCATION'] = []
self.entities['DATE'] = []
self.entities['Disaster'] = []
for e in eventModelInstances:
if 'LOCATION' in e:
self.entities['LOCATION'].extend(e['LOCATION'])
elif 'DATE' in e:
self.entities['DATE'].extend(e['DATE'])
self.entities['Disaster'].extend(e['Disaster'])
entitiesFreq = {}
entitiesFreq['LOCATION'] = self.getEntitiesFreq(
self.entities['LOCATION'])
entitiesFreq['DATE'] = self.getEntitiesFreq(self.entities['DATE'])
entitiesFreq['Disaster'] = self.getEntitiesFreq(
self.entities['Disaster'])
filteredDates = []
months = [
'jan', 'feb', 'mar', 'apr', 'aug', 'sept', 'oct', 'nov', 'dec',
'january', 'february', 'march', 'april', 'may', 'june', 'july',
'august', 'september', 'october', 'november', 'december'
]
for d, v in entitiesFreq['DATE']:
if d.isdigit() and len(d) == 4:
filteredDates.append((d, v))
elif d.lower() in months:
filteredDates.append((d, v))
entitiesFreq['DATE'] = filteredDates
llen = 5
dlen = 5
#l = [k for k,_ in entitiesFreq['LOCATION']]
s = len(entitiesFreq['LOCATION'])
if llen < s:
s = llen
t = entitiesFreq['LOCATION'][:s]
print t
self.entities['LOCATION'] = dict(t)
#d = [k for k,_ in entitiesFreq['DATE']]
s = len(entitiesFreq['DATE'])
if dlen < s:
s = dlen
self.entities['DATE'] = dict(entitiesFreq['DATE'][:s])
print entitiesFreq['DATE'][:s]
locDate = [k for k, _ in entitiesFreq['LOCATION']
] + [m for m, _ in entitiesFreq['DATE']]
locDate = eventUtils.getTokens(' '.join(locDate))
'''
ntopToks = []
topToks = [k for k,_ in sortedToksTFDF]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
'''
ntopToks = []
topToks = [k for k, _ in entitiesFreq['Disaster']]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
#print "Disaster: ", topToks
topToksDic = {}
for t in topToks:
topToksDic[t] = self.toksTFDFDic[t]
#self.entities['Disaster'] = set(topToks)
self.entities['Disaster'] = topToksDic
#print self.entities
print topToks
#self.vecs = {}
self.scalars = {}
for k in self.entities:
ekv = self.entities[k]
'''
if k == 'Disaster':
ev = [1+math.log(e*v) for e,v in ekv.values()]
else:
ev = [1+math.log(e) for e in ekv.values()]
'''
#NoTFDF
ev = [1 + math.log(e) for e in ekv.values()]
#self.vecs[k] = ev
self.scalars[k] = self.getScalar(ev)
def buildEventModel_old(self, seedURLs):
corpus = Collection(seedURLs)
#sortedTokensFreqs = corpus.getWordsFrequencies()
sortedToksTFDF = corpus.getIndicativeWords()
print sortedToksTFDF
sortedImptSents = corpus.getIndicativeSentences(
self.topK, self.intersectionTh)
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
#topToks = [k for k,_ in sortedToksTFDF]
#if self.topK < len(topToks):
# topToks = topToks[:self.topK]
#self.entities['Disaster'] = set(topToks)
self.entities['LOCATION'] = []
self.entities['DATE'] = []
for e in eventModelInstances:
if 'LOCATION' in e:
self.entities['LOCATION'].extend(e['LOCATION'])
elif 'DATE' in e:
self.entities['DATE'].extend(e['DATE'])
entitiesFreq = {}
entitiesFreq['LOCATION'] = eventUtils.getFreq(
self.entities['LOCATION'])
entitiesFreq['LOCATION'] = eventUtils.getSorted(
entitiesFreq['LOCATION'].items(), 1)
entitiesFreq['DATE'] = eventUtils.getFreq(self.entities['DATE'])
entitiesFreq['DATE'] = eventUtils.getSorted(
entitiesFreq['DATE'].items(), 1)
l = [k for k, _ in entitiesFreq['LOCATION']]
if self.topK < len(l):
#l = l[:self.topK]
l = l[:3]
self.entities['LOCATION'] = set(l)
d = [k for k, _ in entitiesFreq['DATE']]
if self.topK < len(d):
#d = d[:self.topK]
d = d[:3]
self.entities['DATE'] = set(d)
'''
locList = self.entities['LOCATION']
locSet = set(locList)
self.entities['LOCATION'] = [l for l in locSet]
'''
self.entities['LOCATION'] = self.getUniqueEntities(
self.entities['LOCATION'])
'''
dateList = self.entities['DATE']
dateSet = set(dateList)
self.entities['DATE'] = [d for d in dateSet]
'''
self.entities['DATE'] = self.getUniqueEntities(self.entities['DATE'])
locDate = list(self.entities['LOCATION']) + list(self.entities['DATE'])
locDate = eventUtils.getTokens(' '.join(locDate))
ntopToks = []
topToks = [k for k, _ in sortedToksTFDF]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
self.entities['Disaster'] = set(topToks)
self.allEntities = []
for k in self.entities:
self.allEntities.extend(self.entities[k])
print self.allEntities
ntokEntsList.extend(ps) else: ntokEntsList.append(s) print ntokEntsList print '--------------' print toks for k in toksTFDF: if k not in ntokEntsList: filteredToksTFDF.append((k,toksTFDF[k])) ''' # Get Indicative Sentences sortedImptSents = utils.getIndicativeSents(sortedToksTFDF,topK,intersectionTh) # Get Event Model eventModelInstances = utils.getEventModelInsts(sortedImptSents) rs = "<tr>" re = "</tr>" outputs = "<td>" outpute = "</td>" wordsOutput = "<tr><td>Frequent Words (term Frequency)</td><td>Important Words (term Freq * Doc Freq)</td></tr>" for i in range(topK): wordsOutput += rs + outputs + str(sortedTokensFreqs[i]) + outpute + outputs + str(sortedToksTFDF[i]) + outpute + re sents_ents = "<tr><td>Important Sentences</td><td>Named Entities</td></tr>" for i in range(len(sortedImptSents)): sents_ents += rs + outputs + str(sortedImptSents[i]) + outpute + outputs + str(eventModelInstances[i]) + outpute + re print wordsOutput print "<br>============<br>"
def buildEventModel_old(self,seedURLs):
corpus = Collection(seedURLs)
#sortedTokensFreqs = corpus.getWordsFrequencies()
sortedToksTFDF = corpus.getIndicativeWords()
print sortedToksTFDF
sortedImptSents = corpus.getIndicativeSentences(self.topK,self.intersectionTh)
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
#topToks = [k for k,_ in sortedToksTFDF]
#if self.topK < len(topToks):
# topToks = topToks[:self.topK]
#self.entities['Disaster'] = set(topToks)
self.entities['LOCATION']= []
self.entities['DATE'] = []
for e in eventModelInstances:
if 'LOCATION' in e:
self.entities['LOCATION'].extend( e['LOCATION'])
elif 'DATE' in e:
self.entities['DATE'].extend( e['DATE'])
entitiesFreq = {}
entitiesFreq['LOCATION'] = eventUtils.getFreq(self.entities['LOCATION'])
entitiesFreq['LOCATION'] = eventUtils.getSorted(entitiesFreq['LOCATION'].items(), 1)
entitiesFreq['DATE'] = eventUtils.getFreq(self.entities['DATE'])
entitiesFreq['DATE'] = eventUtils.getSorted(entitiesFreq['DATE'].items(), 1)
l = [k for k,_ in entitiesFreq['LOCATION']]
if self.topK < len(l):
#l = l[:self.topK]
l = l[:3]
self.entities['LOCATION'] = set(l)
d = [k for k,_ in entitiesFreq['DATE']]
if self.topK < len(d):
#d = d[:self.topK]
d = d[:3]
self.entities['DATE'] = set(d)
self.entities['LOCATION'] = self.getUniqueEntities(self.entities['LOCATION'])
self.entities['DATE'] = self.getUniqueEntities(self.entities['DATE'])
locDate = list(self.entities['LOCATION']) + list(self.entities['DATE'])
locDate = eventUtils.getTokens(' '.join(locDate))
ntopToks = []
topToks = [k for k,_ in sortedToksTFDF]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
self.entities['Disaster'] = set(topToks)
self.allEntities = []
for k in self.entities:
self.allEntities.extend(self.entities[k])
print self.allEntities
def buildEventModel(self,keywordsTh, seedURLs):
corpus = Collection(seedURLs)
#NoTFDF
sortedToksTFDF = corpus.getIndicativeWords()
self.toksTFDFDic = dict(sortedToksTFDF)
print sortedToksTFDF
#sortedImptSents = corpus.getIndicativeSentences(self.topK,self.intersectionTh)
sortedImptSents = corpus.getIndicativeSentences(keywordsTh,self.intersectionTh)
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
self.entities['LOCATION']= []
self.entities['DATE'] = []
self.entities['Disaster']=[]
for e in eventModelInstances:
if 'LOCATION' in e:
self.entities['LOCATION'].extend( e['LOCATION'])
elif 'DATE' in e:
self.entities['DATE'].extend( e['DATE'])
self.entities['Disaster'].extend(e['Disaster'])
entitiesFreq = {}
entitiesFreq['LOCATION'] = self.getEntitiesFreq(self.entities['LOCATION'])
entitiesFreq['DATE'] = self.getEntitiesFreq(self.entities['DATE'])
entitiesFreq['Disaster'] = self.getEntitiesFreq(self.entities['Disaster'])
filteredDates = []
months = ['january','february','march','april','may','june','july','august','september','october','november','december']
for d,v in entitiesFreq['DATE']:
if d.isdigit() and len(d) == 4:
filteredDates.append((d,v))
elif d.lower() in months:
filteredDates.append((d,v))
entitiesFreq['DATE']=filteredDates
llen = 5
dlen = 5
#l = [k for k,_ in entitiesFreq['LOCATION']]
s = len(entitiesFreq['LOCATION'])
if llen < s:
s = llen
t = entitiesFreq['LOCATION'][:s]
print t
self.entities['LOCATION'] = dict(t)
#d = [k for k,_ in entitiesFreq['DATE']]
s = len(entitiesFreq['DATE'])
if dlen < s:
s = dlen
self.entities['DATE'] = dict(entitiesFreq['DATE'][:s])
print entitiesFreq['DATE'][:s]
locDate = [k for k,_ in entitiesFreq['LOCATION'][:2]] + [m for m,_ in entitiesFreq['DATE']]
locDate = eventUtils.getTokens(' '.join(locDate))
ntopToks = []
topToks = [k for k,_ in entitiesFreq['Disaster']]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
#print "Disaster: ", topToks
topToksDic = {}
for t in topToks:
topToksDic[t] = self.toksTFDFDic[t]
#self.entities['Disaster'] = set(topToks)
self.entities['Disaster'] = topToksDic
#print self.entities
print topToks
#self.vecs = {}
self.scalars = {}
for k in self.entities:
ekv = self.entities[k]
#NoTFDF
ev = [1+math.log(e) for e in ekv.values()]
#self.vecs[k] = ev
self.scalars[k] = self.getScalar(ev)
def buildEventModel(self, seedURLs):
corpus = Collection(seedURLs)
#NoTFDF
corpus.getIndicativeWords('TF')
self.toksDic= dict(corpus.indicativeWords)
#self.toksTFIDFDic = dict(sortedToksTFIDF)
#print sortedToksTFDF
sortedImptSents = corpus.getIndicativeSentences(3 * self.topK,self.intersectionTh)
#sortedImptSents = corpus.getIndicativeSentences(keywordsTh,self.intersectionTh)
for s in sortedImptSents[:self.topK]:
print s
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
#print eventModelInstances[:self.topK]
self.entities['LOCATION']= []
self.entities['DATE'] = []
self.entities['Topic']=[]
for e in eventModelInstances:
if 'LOCATION' in e:
self.entities['LOCATION'].extend( e['LOCATION'])
if 'DATE' in e:
self.entities['DATE'].extend( e['DATE'])
self.entities['Topic'].extend(e['Topic'])
entitiesFreq = {}
entitiesFreq['LOCATION'] = self.getEntitiesFreq(self.entities['LOCATION'])
entitiesFreq['DATE'] = self.getEntitiesFreq(self.entities['DATE'])
entitiesFreq['Topic'] = self.getEntitiesFreq(self.entities['Topic'])
#entitiesFreq['Topic'] = [(t,self.toksTFIDFDic[t]) for t,f in tf ]
'''
if self.topK < len(entitiesFreq['Topic']):
entitiesFreq['Topic'] = entitiesFreq['Topic'][:self.topK]
self.entities['Topic'] = dict(entitiesFreq['Topic'])
print entitiesFreq['Topic']
'''
filteredDates = []
months = ['jan','feb','mar','apr','aug','sept','oct','nov','dec','january','february','march','april','may','june','july','august','september','october','november','december']
for d,v in entitiesFreq['DATE']:
if d.isdigit() and len(d) == 4:
filteredDates.append((d,v))
elif d.lower() in months:
filteredDates.append((d,v))
entitiesFreq['DATE']=filteredDates
llen = self.topK
dlen = self.topK
#l = [k for k,_ in entitiesFreq['LOCATION']]
s = len(entitiesFreq['LOCATION'])
if llen < s:
s = llen
t = entitiesFreq['LOCATION'][:s]
print t
self.entities['LOCATION'] = dict(t)
#locDate = [k for k,_ in entitiesFreq['LOCATION']] + [m for m,_ in entitiesFreq['DATE']]
locDate = self.entities['LOCATION'].keys() + [m for m,_ in entitiesFreq['DATE']]#self.entities['DATE'].keys()
locDate = eventUtils.getTokens(' '.join(locDate))
#d = [k for k,_ in entitiesFreq['DATE']]
s = len(entitiesFreq['DATE'])
if dlen < s:
s = dlen
self.entities['DATE'] = dict(entitiesFreq['DATE'][:s])
print entitiesFreq['DATE'][:s]
ntopToks = []
topToks = [k for k,_ in entitiesFreq['Topic']]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
#print "Disaster: ", topToks
topToksDic = {}
for t in topToks:
topToksDic[t] = self.toksDic[t]
#self.entities['Disaster'] = set(topToks)
self.entities['Topic'] = topToksDic
#print self.entities
print topToksDic
#Calculate weights
self.calculateWeights()
newents = {}
for k in self.entities:
ed = self.entities[k].iteritems()
ned = [(k,1) for k,_ in ed]
newents[k] = dict(ned)
for k in newents:
self.entities[k] = newents[k]
#self.vecs = {}
self.scalars = {}
for k in self.entities:
ekv = self.entities[k]
'''
if k == 'Disaster':
ev = [1+math.log(e*v) for e,v in ekv.values()]
else:
ev = [1+math.log(e) for e in ekv.values()]
'''
#NoTFDF
ev = [1+math.log(e) for e in ekv.values()]
#self.vecs[k] = ev
self.scalars[k] = self.getScalar(ev)
def buildEventModel(self, keywordsTh, seedURLs):
corpus = Collection(seedURLs)
# NoTFDF
sortedToksTFDF = corpus.getIndicativeWords()
self.toksTFDFDic = dict(sortedToksTFDF)
# print sortedToksTFDF
# sortedImptSents = corpus.getIndicativeSentences(self.topK,self.intersectionTh)
sortedImptSents = corpus.getIndicativeSentences(keywordsTh, self.intersectionTh)
# Get Event Model
eventModelInstances = eventUtils.getEventModelInsts(sortedImptSents)
self.entities["LOCATION"] = []
self.entities["DATE"] = []
self.entities["Disaster"] = []
for e in eventModelInstances:
if "LOCATION" in e:
self.entities["LOCATION"].extend(e["LOCATION"])
elif "DATE" in e:
self.entities["DATE"].extend(e["DATE"])
self.entities["Disaster"].extend(e["Disaster"])
entitiesFreq = {}
entitiesFreq["LOCATION"] = self.getEntitiesFreq(self.entities["LOCATION"])
entitiesFreq["DATE"] = self.getEntitiesFreq(self.entities["DATE"])
entitiesFreq["Disaster"] = self.getEntitiesFreq(self.entities["Disaster"])
filteredDates = []
months = [
"jan",
"feb",
"mar",
"apr",
"aug",
"sept",
"oct",
"nov",
"dec",
"january",
"february",
"march",
"april",
"may",
"june",
"july",
"august",
"september",
"october",
"november",
"december",
]
for d, v in entitiesFreq["DATE"]:
if d.isdigit() and len(d) == 4:
filteredDates.append((d, v))
elif d.lower() in months:
filteredDates.append((d, v))
entitiesFreq["DATE"] = filteredDates
llen = 5
dlen = 5
# l = [k for k,_ in entitiesFreq['LOCATION']]
s = len(entitiesFreq["LOCATION"])
if llen < s:
s = llen
t = entitiesFreq["LOCATION"][:s]
print t
self.entities["LOCATION"] = dict(t)
# d = [k for k,_ in entitiesFreq['DATE']]
s = len(entitiesFreq["DATE"])
if dlen < s:
s = dlen
self.entities["DATE"] = dict(entitiesFreq["DATE"][:s])
print entitiesFreq["DATE"][:s]
locDate = [k for k, _ in entitiesFreq["LOCATION"]] + [m for m, _ in entitiesFreq["DATE"]]
locDate = eventUtils.getTokens(" ".join(locDate))
"""
ntopToks = []
topToks = [k for k,_ in sortedToksTFDF]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[:self.topK]
"""
ntopToks = []
topToks = [k for k, _ in entitiesFreq["Disaster"]]
for tok in topToks:
if tok not in locDate:
ntopToks.append(tok)
topToks = ntopToks
if self.topK < len(topToks):
topToks = topToks[: self.topK]
# print "Disaster: ", topToks
topToksDic = {}
for t in topToks:
topToksDic[t] = self.toksTFDFDic[t]
# self.entities['Disaster'] = set(topToks)
self.entities["Disaster"] = topToksDic
# print self.entities
print topToks
# self.vecs = {}
self.scalars = {}
for k in self.entities:
ekv = self.entities[k]
"""
if k == 'Disaster':
ev = [1+math.log(e*v) for e,v in ekv.values()]
else:
ev = [1+math.log(e) for e in ekv.values()]
"""
# NoTFDF
ev = [1 + math.log(e) for e in ekv.values()]
# self.vecs[k] = ev
self.scalars[k] = self.getScalar(ev)
