def show_instances(class_name=''):
name = 'train'
if name == 'train':
filename = Const.origin_all_train_filename
elif name == 'dev':
filename = Const.origin_all_dev_filename
f = open(filename, 'r')
content = f.readlines()
html_doc = ' '.join(content)
sentences_string, triples_string = utils.parse(html_doc)
sentences_words = utils.sentence_tokenize(sentences_string)
position_triples = utils.find_entity_position(sentences_words,
triples_string)
sentences_word_id, sentence_triples_id = utils.turn2id(
sentences_words, position_triples)
utils.triples_type(sentence_triples_id)
if class_name == 'normal':
func = utils.is_normal_triple
elif class_name == 'single_entity_overlap':
func = utils.is_over_lapping
else:
func = utils.is_multi_label
words2id = utils.load_words2id()
id2words = {v: k for k, v in words2id.items()}
for sent_words_id, triples_id in zip(sentences_word_id,
sentence_triples_id):
if func(triples_id, is_relation_first=False):
print ' '.join([id2words[x] for x in sent_words_id])
print triples_id
print '-----------------------------------'
def run_word_vectors():
print 'reading nyt_vec.bin'
all_w2vec = utils.read_vec_bin()
words2id = utils.load_words2id()
print 'prepare w2vec'
w2vec = utils.word_vectors(words2id, all_w2vec)
print 'dumping'
json.dump(w2vec, open(Const.words_id2vector_filename, 'w'))
def run_word_vectors():
print('reading nyt_vec.bin')
all_w2vec = utils.read_vec_bin()
words2id = utils.load_words2id()
print('prepare w2vec')
w2vec = utils.word_vectors(words2id, all_w2vec)
print('dumping')
json.dump(w2vec, open(Const.words_id2vector_filename, 'w', encoding='utf-8'))