def generation(self):
self.tokenized = [nltk.word_tokenize(self.sentences[i]) for i in range(len(self.sentences))]
self.generate_average_position()
self.types = {}
tagger = Tagger(False)
for i in range(len(self.tokenized)):
typess = tagger.tag_sent(self.tokenized[i])
for j in range(len(typess)):
word,val = typess[j]
if(not word in self.types):
self.types[word] = []
self.types[word].append(val)
else:
self.types[word].append(val)
for element in self.types:
most_common,num_most_common = Counter(self.types[element]).most_common(1)[0]
self.types[element] =most_common
num_sent = 1
for sent in self.tokenized:
actual = sent
num_word = 1
last = None
for mot in actual:
actual = None
if(not self.isWordIn(mot)):
tmp = Etiquette(mot,num_sent,num_word)
self.nodes.append(tmp)
actual = tmp
else:
actual = self.get_node_with_value(mot)
actual.add_sid_pid(num_sent,num_word)
if(num_word>1):
last.add_next(actual.get_id())
last = actual
num_word +=1
num_sent +=1
