def extract_information(self, train_instances):
seqs = []
for train_instance in train_instances:
lemma_sa, lemma_sb = train_instance.get_word(
type='lemma', stopwords=self.stopwords, lower=True)
seqs.append(lemma_sa)
seqs.append(lemma_sb)
self.idf_weight = utils.idf_calculator(seqs)
self.vocab = utils.word2index(self.idf_weight)
def extract_information(self, train_instances):
seqs = []
for train_instance in train_instances:
dep_sa, dep_sb = train_instance.get_dependency()
dep_sa = [(dep[1], dep[2]) for dep in dep_sa]
dep_sb = [(dep[1], dep[2]) for dep in dep_sb]
seqs.append(dep_sa)
seqs.append(dep_sb)
self.idf_weight = utils.idf_calculator(seqs)
self.vocab = utils.word2index(self.idf_weight)
def extract(self, train_instance):
warrant0, warrant1, reason, claim, title, info = train_instance.get_six(
type='word')
_warrant0 = warrant0 + reason + claim
_warrant1 = warrant1 + reason + claim
self.vocab = utils.word2index(self.unigram_dict)
feat0 = utils.vectorize(_warrant0, self.unigram_dict, self.vocab)
feat1 = utils.vectorize(_warrant1, self.unigram_dict, self.vocab)
infos = [len(self.unigram_dict), 'unigram']
return feat0 + feat1, infos
def extract(self, train_instance):
idf_weight = dict_utils.DictLoader().load_dict('global_idf')
vocab = utils.word2index(idf_weight)
sa, sb = train_instance.get_word(type='lemma',
stopwords=True,
lower=True)
features, infos = utils.sentence_vectorize_features(sa,
sb,
idf_weight,
vocab,
convey='idf')
return features, infos
def extract_information(self, train_instances):
seqs = []
for train_instance in train_instances:
word_sa, word_sb = train_instance.get_word(
type=self.word_type,
stopwords=self.stopwords,
lower=self.lower)
seqs.append(word_sa)
seqs.append(word_sb)
self.idf_weight = utils.idf_calculator(seqs)
self.vocab = utils.word2index(self.idf_weight)
self.vocab, self.embeddings = utils.load_word_embedding(
self.vocab, self.emb_file)
def extract_information(self, train_instances):
seqs = []
for train_instance in train_instances:
pos_sa, pos_sb = train_instance.get_pos_tag(stopwords=False)
sa = [w for w, tag in pos_sa if tag == 'n']
sb = [w for w, tag in pos_sb if tag == 'n']
seqs.append(sa)
seqs.append(sb)
idf_weight = utils.idf_calculator(seqs)
vocab = utils.word2index(idf_weight)
self.idf_weight = idf_weight
self.vocab, self.embeddings = utils.load_word_embedding(
vocab, self.emb_file)