def predict(input_path, output_path):
df_i = pd.read_excel(input_path)
corpus_i = df_i.iloc[:, [1]]
corpus_i = np.array(corpus_i).tolist()
corpus = reader.preprocess(reader.read_excel(input_path, text_column=1),
seq_lenth=FLAGS.seq_lenth,
seq_num=1,
overlap_lenth=0,
input_label=False,
output_index=True)
# vocab, word2id = reader.read_glossary()
test_inputs = []
test_lenths = []
test_num = 0
for item in corpus:
test_inputs.append(item[0])
test_lenths.append(item[1])
test_num += 1
with tf.Graph().as_default(), tf.Session() as sess:
model = em_sent(seq_size=FLAGS.seq_lenth,
glossary_size=FLAGS.glossary_size,
embedding_size=FLAGS.embedding_size,
hidden_size=FLAGS.hidden_size,
attn_lenth=FLAGS.attn_lenth,
is_training=False)
model.buildTrainGraph()
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=10)
if reader.restore_from_checkpoint(sess, saver, FLAGS.ckpt_dir):
total_expection = []
print(test_num)
for piece_inputs, piece_lenths in get_test_batch(
test_inputs, test_lenths, None, test_num,
input_label=False):
test_feed_dict = {
model.inputs:
piece_inputs,
model.lenths:
piece_lenths,
model.lenths_weight:
padded_ones_list_like(piece_lenths, FLAGS.seq_lenth),
}
expection = sess.run(model.expection, feed_dict=test_feed_dict)
total_expection.extend(expection)
zipped = []
for index in range(test_num):
zipped.append([
corpus_i[corpus[index][2]],
'T' if total_expection[index][0] == 0 else 'F'
])
df_o = pd.DataFrame(zipped)
writer = pd.ExcelWriter(output_path)
df_o.to_excel(writer, 'Sheet1')
writer.save()
def test_onesent(text):
corpus = reader.preprocess([[text]],
seq_lenth=FLAGS.seq_lenth,
seq_num=1,
overlap_lenth=0,
input_label=False,
output_index=False)
vocab, word2id = reader.read_glossary()
print(corpus)
test_inputs = []
test_lenths = []
test_num = 0
for item in corpus:
test_inputs.append(item[0])
test_lenths.append(item[1])
test_num += 1
with tf.Graph().as_default(), tf.Session() as sess:
model = em_sent(seq_size=FLAGS.seq_lenth,
glossary_size=FLAGS.glossary_size,
embedding_size=FLAGS.embedding_size,
hidden_size=FLAGS.hidden_size,
attn_lenth=FLAGS.attn_lenth,
is_training=False)
model.buildTrainGraph()
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=10)
if reader.restore_from_checkpoint(sess, saver, FLAGS.ckpt_dir):
test_feed_dict = {
model.inputs:
test_inputs,
model.lenths:
test_lenths,
model.lenths_weight:
padded_ones_list_like(test_lenths, FLAGS.seq_lenth),
}
expection, alpha, logits = sess.run(
[model.expection, model.alpha, model.logits],
feed_dict=test_feed_dict)
print([vocab[i] for i in test_inputs[0]])
for i in range(len(test_inputs[0])):
print(vocab[test_inputs[0][i]], alpha[0][i], logits[0][i])
# print([vocab[word] for word in test_inputs])
if (expection[0][0] == 1):
print('负面')
else:
print('正面')
return expection[0]
def test_for_lime(text):
corpus = reader.preprocess([[i] for i in text],
seq_lenth=FLAGS.seq_lenth,
seq_num=1,
overlap_lenth=0,
input_label=False,
output_index=False,
split_func=lambda x: x.split(' '),
de_duplicated=False)
# vocab, word2id = reader.read_glossary()
test_inputs = []
test_lenths = []
test_num = 0
for item in corpus:
test_inputs.append(item[0])
test_lenths.append(item[1])
test_num += 1
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=10)
if reader.restore_from_checkpoint(SESS, saver, FLAGS.ckpt_dir):
total_expection = []
for piece_inputs, piece_lenths in get_test_batch(test_inputs,
test_lenths,
None,
test_num,
input_label=False):
test_feed_dict = {
model.inputs:
piece_inputs,
model.lenths:
piece_lenths,
model.lenths_weight:
padded_ones_list_like(piece_lenths, FLAGS.seq_lenth),
}
expection = SESS.run(model.raw_expection, feed_dict=test_feed_dict)
total_expection.extend([[round(i[0], 4),
round(1 - i[0], 4)] for i in expection])
return np.array(total_expection)
print('负面')
temp.append('负面')
elif (expection[index][0] == 0):
print('非负面')
temp.append('非负面')
sp.append(temp)
return sp
if __name__ == '__main__':
text = ['康宝莱】河南郑州', '花季少女死于康宝莱']
corpus = reader.preprocess(reader.read_excel(
'../data/corpus/check/yxcd.xlsx', text_column=1, label_column=0),
seq_lenth=FLAGS.seq_lenth,
seq_num=1,
overlap_lenth=0,
input_label=True,
output_index=False,
de_duplicated=True)
# with open('../data/corpus/latest/test.pickle', 'rb') as fp:
# corpus = pickle.load(fp)
test(corpus)
# predict(input_path='../data/corpus/check/klb.xlsx', output_path='out/x.xlsx')
# test_onesent('【康宝莱】河南郑州花季少女死于康宝莱传销相关部门难逃其咎： 我叫张云成，男，汉族，现年47岁，家住河南省淮阳县冯塘乡蔡李庄村。2017年6月5日,我的儿子张旭(17岁)从郑州回到家里,向家里要钱,...文字版>> http://t.cn/RonRbWK （新浪长微博>> http://t.cn/zOXAaic）')
# test_onesent('走进康宝莱之前，我听到了台上的分享嘉宾说了这句话：“也许做康宝莱这件事不是你的梦想，但做好康宝莱能实现你所有的梦想！” 我信了。 果然这是真的。 同时，在这个过程中，帮助更多人获得好身材、健康、财富、和精彩人生，也一并成为了我的梦想！和我其他的梦想一起实现了！——肖珂宇 网页链接')
# vocab, word2id = reader.read_glossary()
# sp = get_word_sentiment_polarity(vocab)
#
# import pandas as pd
#