def train_ner(x_train, y_train, x_valid, y_valid, x_test, y_test,
sequence_length, epoch, batch_size, bert_model_path,
model_save_path):
"""
BERT-BiLSTM-CRF 模型训练，提取症状内部特征
"""
bert_embedding = BERTEmbedding(bert_model_path,
task=kashgari.LABELING,
sequence_length=sequence_length)
model = BiLSTM_CRF_Model(bert_embedding)
eval_callback_val = EvalCallBack(kash_model=model,
valid_x=x_valid,
valid_y=y_valid,
step=1)
eval_callback_test = EvalCallBack(kash_model=model,
valid_x=x_test,
valid_y=y_test,
step=1)
model.fit(x_train,
y_train,
x_validate=x_valid,
y_validate=y_valid,
epochs=epoch,
batch_size=batch_size,
callbacks=[eval_callback_val, eval_callback_test])
model.save(model_save_path)
model.evaluate(x_test, y_test)
return model
def build(self):
embed = BERTEmbedding(model_folder=self.folder,
task=kashgari.LABELING,
trainable=self.fine_tune,
sequence_length=self.seq_len)
model = BiLSTM_CRF_Model(embed)
return model
def main():
# train_x, train_y = ChineseDailyNerCorpus.load_data("train")
# valid_x, valid_y = ChineseDailyNerCorpus.load_data("validate")
ChineseDailyNerCorpus.__zip_file__name
test_x, test_y = ChineseDailyNerCorpus.load_data("test")
# print(f"train data count: {len(train_x)}")
# print(f"validate data count: {len(valid_x)}")
print(f"test data count: {len(test_x)}")
bert_embed = BERTEmbedding("models/chinese_L-12_H-768_A-12",
task=kashgari.LABELING,
sequence_length=100)
model = BiLSTM_CRF_Model(bert_embed)
# model.fit(
# train_x,
# train_y,
# x_validate=valid_x,
# y_validate=valid_y,
# epochs=1,
# batch_size=512,
# )
model.save("models/ner.h5")
model.evaluate(test_x, test_y)
predictions = model.predict_classes(test_x)
print(predictions)
def train_BERT_BiLSTM_CRF(
train_test_devide=0.9,
epoch=20,
path='/home/peitian_zhang/data/corpus/labeled_train.txt'):
train_x, train_y = getTrain(path)
x = train_x[:int(len(train_x) * train_test_devide) + 1]
y = train_y[:int(len(train_x) * train_test_devide) + 1]
bert = BERTEmbedding(
model_folder='/home/peitian_zhang/data/chinese_L-12_H-768_A-12',
sequence_length=400,
task=kashgari.LABELING)
model = BiLSTM_CRF_Model(bert)
model.fit(x, y, x, y, epochs=epoch, batch_size=64)
print('---------evaluate on train---------\n{}'.format(
model.evaluate(train_x, train_y)))
print('---------evaluate on test----------\n{}'.format(
model.evaluate(train_x[int(len(train_x) * train_test_devide) + 1:],
train_y[int(len(train_x) * train_test_devide) + 1:])))
try:
model.save('/home/peitian_zhang/models/bert_epoch_{}'.format(epoch))
print('Success in saving!')
except:
pass
return model
def train_it2(train_path, checkpoint_filepath, model_path, start, span):
data_generator = BIODataGenerator(train_path, 100000000)
Xs, ys = data_generator.forfit().__next__()
train_x, train_y = [], []
valid_x, valid_y = [], []
rng = np.random.RandomState(0)
k = 0
for x, y in zip(Xs, ys):
# x = [str(i, 'utf-8') for i in x]
# y = [str(i, 'utf-8') for i in y]
rnum = rng.rand()
k += 1
if rnum < start or rnum >= start + span:
train_x += [x]
train_y += [y]
else:
valid_x += [x]
valid_y += [y]
# dataset = dataset.batch(32)
print('====' * 8)
print('total = ', k)
print('start , span = ', (start, span))
print('len train = ', len(train_x))
# checkpoint_filepath = './checkpoint'
if not os.path.exists(os.path.dirname(checkpoint_filepath)):
os.mkdir(os.path.dirname(checkpoint_filepath))
# train_x, train_y = ChineseDailyNerCorpus.load_data('train')
# test_x, test_y = ChineseDailyNerCorpus.load_data('test')
# valid_x, valid_y = ChineseDailyNerCorpus.load_data('valid')
# model_checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(
# filepath=checkpoint_filepath,
# save_weights_only=True,
# monitor='val_accuracy',
# mode='max',
# save_best_only=True)
#train_x, train_y = train_x[:1000], train_y[:1000]
#valid_x, valid_y = valid_x[:200], valid_y[:200]
model = BiLSTM_CRF_Model(bert_embed, sequence_length=128)
eval_callback = Evaluator(model, checkpoint_filepath, valid_x, valid_y)
early_stop = keras.callbacks.EarlyStopping(patience=10)
reduse_lr_callback = keras.callbacks.ReduceLROnPlateau(factor=0.1,
patience=5)
# eval_callback = EvalCallBack(kash_model=model,
# x_data=valid_x,
# y_data=valid_y,
# step=1)
model.fit(train_x,
train_y,
valid_x,
valid_y,
batch_size=64,
epochs=20,
callbacks=[early_stop, eval_callback, reduse_lr_callback])
model.save(model_path)
def train(self, tokens, tags):
x, y = self.prepare_data_fit(tokens, tags, chunk_size=self.chunk_size)
text_embedding = BareEmbedding(task=kashgari.LABELING,
sequence_length=self.chunk_size)
first_of_p_embedding = NumericFeaturesEmbedding(
feature_count=2,
feature_name='first_of_p',
sequence_length=self.chunk_size)
stack_embedding = StackedEmbedding(
[text_embedding, first_of_p_embedding])
stack_embedding.analyze_corpus(x, y)
from kashgari.tasks.labeling import BiLSTM_Model, BiLSTM_CRF_Model
self.model = BiLSTM_CRF_Model(embedding=stack_embedding)
self.model.fit(x, y, batch_size=1, epochs=20)
def train_it(train_path, checkpoint_filepath, model_path, start, span):
dataset = build_dataset(train_path)
train_x, train_y = [], []
valid_x, valid_y = [], []
rng = np.random.RandomState(0)
k = 0
for x, y in dataset.as_numpy_iterator():
x = [str(i, 'utf-8') for i in x]
y = [str(i, 'utf-8') for i in y]
rnum = rng.rand()
k += 1
if rnum < start or rnum >= start + span:
train_x += [x]
train_y += [y]
else:
valid_x += [x]
valid_y += [y]
# dataset = dataset.batch(32)
print('====' * 8)
print('total = ', k)
print('start , span = ', (start, span))
print('len train = ', len(train_x))
# checkpoint_filepath = './checkpoint'
if not os.path.exists(os.path.dirname(checkpoint_filepath)):
os.mkdir(os.path.dirname(checkpoint_filepath))
# model_checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(
# filepath=checkpoint_filepath,
# save_weights_only=True,
# monitor='val_accuracy',
# mode='max',
# save_best_only=True)
model = BiLSTM_CRF_Model(bert_embed, sequence_length=100)
evaluator = Evaluator(model, checkpoint_filepath, valid_x, valid_y)
model.fit(train_x,
train_y,
valid_x,
valid_y,
batch_size=64,
epochs=20,
callbacks=[evaluator])
model.save(model_path)
def initial_model(self, bert_model_path, psd_model_path):
print('=============init bert model=========================')
print("bert model path:", bert_model_path)
print("crf model path:", psd_model_path)
self.sess = tf.Session()
set_session(self.sess)
self.model_dir = os.path.dirname(os.path.dirname(psd_model_path))
self.model_path = psd_model_path
data_path = os.path.join(self.model_dir, "feature_psd.pkl")
train_data, train_label, test_data, test_label = \
pickle.load(open(data_path, 'rb'))
bert_embed = BERTEmbedding(bert_model_path, task=kashgari.LABELING,
sequence_length=50)
self.model = BiLSTM_CRF_Model(bert_embed)
self.model.build_model(x_train=train_data, y_train=train_label,
x_validate=test_data, y_validate=test_label)
self.model.compile_model()
self.model.tf_model.load_weights(psd_model_path)
print('=============bert model loaded=========================')
return
def train_BiLSTM_CRF(train_test_devide=0.9,
epoch=100,
path='/home/peitian_zhang/data/corpus/labeled_train.txt'):
train_x, train_y = getTrain(path)
model = BiLSTM_CRF_Model()
x = train_x[:int(len(train_x) * train_test_devide) + 1]
y = train_y[:int(len(train_x) * train_test_devide) + 1]
model.fit(x, y, x, y, epochs=epoch, batch_size=64)
print('---------evaluate on train---------\n{}'.format(
model.evaluate(train_x, train_y)))
print('---------evaluate on test----------\n{}'.format(
model.evaluate(train_x[int(len(train_x) * train_test_devide) + 1:],
train_y[int(len(train_x) * train_test_devide) + 1:])))
try:
model.save('/home/peitian_zhang/models/bert_epoch_{}'.format(epoch))
print('Success in saving!')
except:
pass
return model
# -*- coding: utf-8 -*-
# time: 2019-08-09 16:47
# place: Zhichunlu Beijing
import kashgari
from kashgari.corpus import DataReader
from kashgari.embeddings import BERTEmbedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
train_x, train_y = DataReader().read_conll_format_file('./data/time.train')
valid_x, valid_y = DataReader().read_conll_format_file('./data/time.dev')
test_x, test_y = DataReader().read_conll_format_file('./data/time.test')
bert_embedding = BERTEmbedding('chinese_wwm_ext_L-12_H-768_A-12',
task=kashgari.LABELING,
sequence_length=128)
model = BiLSTM_CRF_Model(bert_embedding)
model.fit(train_x, train_y, valid_x, valid_y, batch_size=16, epochs=10)
model.save('time_ner.h5')
model.evaluate(test_x, test_y)
text = [[0.9, 0.1, 0.1], [0.9, 0.1, 0.1], [0.1, 0.8, 0.1], [0.1, 0.8, 0.1],
[0.1, 0.8, 0.1]]
label = [
'B-Category', 'I-Category', 'B-ProjectName', 'I-ProjectName',
'I-ProjectName'
]
text_list = [text] * 100
label_list = [label] * 100
SEQUENCE_LEN = 80
# You can use WordEmbedding or BERTEmbedding for your text embedding
bare_embedding = DirectEmbedding(task=kashgari.RAW_LABELING,
sequence_length=SEQUENCE_LEN,
embedding_size=3)
#bare_embedding = BareEmbedding(task=kashgari.LABELING, sequence_length=SEQUENCE_LEN)
x = (text_list)
y = label_list
bare_embedding.analyze_corpus(x, y)
# Now we can embed with this stacked embedding layer
# We can build any labeling model with this embedding
from kashgari.tasks.labeling import BiLSTM_Model, BiLSTM_CRF_Model
model = BiLSTM_CRF_Model(embedding=bare_embedding)
model.fit(x, y, batch_size=1, epochs=3)
print(model.predict(x))
#print(model.predict_entities(x))
test_x = list(test_x)
test_y = list(test_y)
''' BERT Embedding '''
#embedding = BERTEmbedding('./chinese_L-12_H-768_A-12',
# task = kashgari.LABELING,
# sequence_length = 150)
''' Word2Vec Embeddings '''
word2vec_embedding = kashgari.embeddings.WordEmbedding(
w2v_path="word2vec.model",
task=kashgari.LABELING,
w2v_kwargs={
'binary': True,
'unicode_errors': 'ignore'
},
sequence_length='auto')
model = BiLSTM_CRF_Model(word2vec_embedding)
#model = BiLSTM_CRF_Model(embedding)
tf_board_callback = keras.callbacks_v1.TensorBoard(log_dir='.\\logs',
update_freq=1000)
eval_callback = EvalCallBack(kash_model=model,
valid_x=test_x,
valid_y=test_y,
step=4)
model.fit(train_x,
train_y,
test_x,
test_y,
batch_size=20,
epochs=4,
callbacks=[eval_callback, tf_board_callback])
# ou o GloVE-300 do http://nilc.icmc.usp.br/embeddings se não der certo
# 2 - Ver como fazer o Predict. Temos que processar a frase para ficar igual a deles.
# Eles usam um PunktSentenceTokenizer com um abbrev_list. Esses scripts estao na pasta leNer-dataset.
# 3 - Ver como integrar esse codigo com o webstruct atual
# 4 - Seria uma boa ideia ter uma interface tipo o Broka. Para que existesse a lista de arquivos, e que
# pudesse abrir para re-treinar, abrindo com o plugin de Ramon.
# Uma ideia seria ate converter o dataset deles atual para o formato do broka hoje em Html ( pode ser algo simples, como colocar cada paragrafo como um p)
# 5 - Fazer a persistencia ( O kashgari tem um metodo save/load)
# 2 - Aumentar epochs para treinar
# You can use WordEmbedding or BERTEmbedding for your text embedding
text_embedding = BareEmbedding(task=kashgari.LABELING)
text_embedding.analyze_corpus(tokens, labels)
# Now we can embed with this stacked embedding layer
# We can build any labeling model with this embedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
model = BiLSTM_CRF_Model(embedding=text_embedding)
model.fit(tokens, labels, batch_size=8, epochs=10)
print(model.predict(tokens))
# print(model.predict_entities(x))
from kashgari.embeddings import BERTEmbedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
from kashgari.corpus import ChineseDailyNerCorpus
train_x, train_y = ChineseDailyNerCorpus.load_data('train')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('validate')
test_x, test_y = ChineseDailyNerCorpus.load_data('test')
# 还可以选择 `CNN_LSTM_Model`, `BiLSTM_Model`, `BiGRU_Model` 或 `BiGRU_CRF_Model`
bert = BERTEmbedding('wwm', task="classification", sequence_length=300)
model = BiLSTM_CRF_Model(bert)
model.fit(train_x,
train_y,
x_validate=valid_x,
y_validate=valid_y,
epochs=20,
batch_size=512)
# 下面我们用 Bi_LSTM 模型实现一个命名实体识别任务：
from kashgari.corpus import ChineseDailyNerCorpus
from kashgari.tasks.labeling import BiLSTM_Model, BiLSTM_CRF_Model
# 加载内置数据集，此处可以替换成自己的数据集，保证格式一致即可
train_x, train_y = ChineseDailyNerCorpus.load_data('train')
test_x, test_y = ChineseDailyNerCorpus.load_data('test')
valid_x, valid_y = ChineseDailyNerCorpus.load_data('valid')
model = BiLSTM_CRF_Model()
model.fit(train_x, train_y, valid_x, valid_y, epochs=1)
model.save("BiLSTM_CRF_Model")
import pickle
import kashgari
from kashgari.embeddings import BertEmbedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
import tensorflow as tf
with open('data.pickle', 'rb') as f:
data_dic = pickle.load(f)
x_train = data_dic[0]
x_validation = data_dic[1]
y_train = data_dic[2]
y_validation = data_dic[3]
embedding = BertEmbedding('bert-base-chinese',
sequence_length = 128)
model = BiLSTM_CRF_Model(embedding)
model.fit( x_train = x_train,
x_validate = x_validation,
y_train = y_train,
y_validate = y_validation,
epochs=5,
batch_size=32,
)
model.save('Model')
model.evaluate(x_data=x_validation,y_data=y_validation)