def main():
#doc = "/home/daniel/data/Ciclo6/Tesis2/stompol-tweets-train-tagged.xml"
doc = "/home/daniel/data/Ciclo6/Tesis2/xmlSampleFile.xml"
#doc = "/home/daniel/data/Ciclo6/Tesis2/xmlSampleFile2.xml"
#doc = "/home/daniel/data/Ciclo6/Tesis2/xmlStandardFile.xml"
xmlparser = XML.XmlParser(doc)
tweets = xmlparser.root
corpus = COR.Corpus()
for tweet in tweets:
tweetEntities = xmlparser.extractEntity(tweet)
corpus.addNewEntities(tweetEntities)
for tweetEntity in tweetEntities:
entity = corpus.getEntity(tweetEntity)
entity.addReview(tweet)
lsa = LAT.LSA(tweets)
lsa.singularValueDecomposition()
lsa.reduceDimension()
lsa.reconstructMatrix()
corpus.assignSemanticSimilarity(lsa)
sentiStrength = SENSTR.sentiStrength()
corpus.assignPolaritySimilarity(sentiStrength)
for entity in corpus.entities:
entity.obtainLeaders()
entity.obtainCommunities()
entity.assignOrder()
entity.fullParsing()
print(entity.generateSummary())
print()
def m_button1OnButtonClick(self, event):
xml = xmlparser.XmlParser().parse()
patient = Patient(xml)
karkinos = Karkinos(patient)
self.text_indice.SetValue(self.__index_case(karkinos, patient))
self.text_informativo.SetValue(self.__informativo(karkinos))
self.text_asociados.SetValue(self.__casos_asociados(karkinos))
self.text_diagnostico.SetValue(self.__diagnosis(karkinos))
self.label_evaluation.SetLabel("Evaluación completada con éxito")
def __init__(self, id):
self.xml = xmlparser.XmlParser('expo.xml')
self.id = id
self.zones = []
for i in range(self.getLargeur()):
tmp = []
for j in range(self.getHauteur()):
z = zone.Zone(i, j, self.xml.isZone(j, i))
tmp.append(z)
self.zones.append(tmp)
class extractEntityMethod(unittest.TestCase):
doc = r"D:\Ciclo 6\Tesis 2\Tesis\source\test\xmltestfile.xml"
xmlparser = XML.XmlParser(doc)
tweets = xmlparser.root
def testEntityExtractionSingle(self):
self.assertEqual(self.xmlparser.extractEntity(self.tweets[0]),
['Partido_Popular'])
def testEntityExtractionMultiple(self):
self.assertEqual(
self.xmlparser.extractEntity(self.tweets[1]),
['Partido_Socialista_Obrero_Espanol', 'Partido_Popular'])
def testEntityExtractionMultipleOnOneEntity(self):
self.assertEqual(self.xmlparser.extractEntity(self.tweets[2]), [
'Partido_Popular', 'Podemos', 'Partido_Socialista_Obrero_Espanol',
'Izquierda_Unida', 'Ciudadanos'
])
class addNewEntitiesMethod(unittest.TestCase):
doc = r"D:\Ciclo 6\Tesis 2\Tesis\source\test\xmltestfile.xml"
xmlparser = XML.XmlParser(doc)
tweets = xmlparser.root
def setUp(self):
self.corpus = COR.Corpus()
def testAddNewEntitiesSingle(self):
tweetEntities = self.xmlparser.extractEntity(self.tweets[0])
self.corpus.addNewEntities(tweetEntities)
self.assertEqual(self.corpus.asEntityList(), ['Partido_Popular'])
del self.corpus.entities[:]
def testAddNewEntitiesMultiple(self):
tweetEntities = self.xmlparser.extractEntity(self.tweets[1])
self.corpus.addNewEntities(tweetEntities)
self.assertEqual(
self.corpus.asEntityList(),
['Partido_Socialista_Obrero_Espanol', 'Partido_Popular'])
del self.corpus.entities[:]
continue
else:
zonesDejaComptees.append([x+1, y])
#Si on se rend ici, on ajoute un kiosque
self.nbKiosques += 1
def aDejaEteComptee(self, zonesDejaComptees, x, y):
for i in (zonesDejaComptees):
if (i == [x, y]):
return True
return False
if __name__ == '__main__':
import xmlparser
xml = xmlparser.XmlParser('expo.xml')
app = QApplication([])
qdb = db.Database()
qdb.openSqlConnection("QSQLITE", "db.sqlite")
zones = []
for i in range(xml.getLargeur()):
tmp = []
for j in range(xml.getHauteur()):
z = zone.Zone(i, j, xml.isZone(j, i))
tmp.append(z)
zones.append(tmp)
v = VueRapportExposant(100, zones)
#~ v = VueRapportGeneral(zones)
import xmlparser
import nlp
from gensim import corpora, models, similarities
from gensim.models import Phrases
import os
import re
import logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
document_start = 11
document_end = 500
parser = xmlparser.XmlParser("snowflakethesis.xml")
document = parser.refactorAllText(7, 10)
doc_paragraphs = []
mode = 0
min_sent_len_paragraph = 0
#We only want to work with paragraphs that have more than two sentences
for paragraph in document.paragraphs:
if (paragraph.page >= document_start and paragraph.page <= document_end):
if len(paragraph.paragraph.split('. ')) > min_sent_len_paragraph:
doc_paragraphs.append(paragraph)
#If we have saved files, just use them
#else create them
if (os.path.exists('snowflakethesisa.dict')
and os.path.exists('snowflakethesisa.mm')):
dictionary = corpora.Dictionary.load('snowflakethesis.dict')
corpus = corpora.MmCorpus('snowflakethesis.mm')
print('Used saved files')