def predict_(sentence):
words = extract_cn_jd(sentence).split(' ')
seq = doc2matrix(words, maxlen)
arr = np.array(seq)
arr = arr.reshape((1, maxlen, word2vec_dim))
return model.predict(arr)
pos = pd.read_table(path.join(path.dirname(__file__), '..', 'data',
'pos_sim.txt'),
header=None,
sep='\n',
encoding='utf8')
pos['label'] = 1
neg = pd.read_table(path.join(path.dirname(__file__), '..', 'data',
'neg_sim.txt'),
header=None,
sep='\n',
encoding='utf8')
neg['label'] = 0
all_ = pos.append(neg, ignore_index=True)
all_['words'] = all_[0].apply(lambda s: extract_cn_jd(s).split(' ')) #调用结巴分词
print(all_['words'])
w2v_model = KeyedVectors.load_word2vec_format(path.join(
path.dirname(__file__), '..', 'data', 'w2v_onlycn_100_c_2.bin'),
binary=True,
unicode_errors='ignore')
word2vec_dim = 100
maxlen = 100 #截断词数
content = []
for word_list in all_['words']:
for word in word_list:
try:
vec = w2v_model[word]
content.append(word)
