def __init__(self,
model_path,
type_filter=False,
save_label=False,
batch=32,
save_expand_subject=True):
# mention -> entity_json_line
self.subject_id_dict = subject_id_dict
self._model = BLSTMCRFModel.load_model(model_path)
# self._model = DDDDModel.load_model(model_path)
self.type_filter = type_filter
self.batch = batch
self.save_label = save_label
self.save_expand_subject = save_expand_subject
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
model_fold = cp["EVALUATION"].get("model_fold")
output_dir = os.path.join('experiments', model_fold)
test_x, test_y = CoNLL2003Corpus.get_sequence_tagging_data('test')
model_path = os.path.join(output_dir, 'model')
model = BLSTMCRFModel.load_model(model_path)
report_evaluate = model.evaluate(test_x, test_y, debug_info=True)
with open(os.path.join(output_dir, 'report_evaluate.log'), 'w') as f:
f.write(f"The evaluate report is :\n {str(report_evaluate)}\n")
def main():
# parser config
config_file = "./config.ini"
cp = ConfigParser()
cp.read(config_file)
# default config
model_fold = cp["TEST"].get("model_fold")
output_dir = os.path.join('experiments', model_fold)
model_path = os.path.join(output_dir, 'model')
model = BLSTMCRFModel.load_model(model_path)
sentence = 'China and the United States are about the same size'
sentence_list = sentence.split()
result = model.predict(sentence_list)
result_dict = model.predict(sentence_list, output_dict=True)
print(f'the sentence is {sentence}')
print(f'the result is {result}')
print(f'the result of dict is {result_dict}')
logging.info('test predict: {} -> {}'.format(sentence_list, result))
with open(os.path.join(output_dir, 'result_predict.log'), 'w') as f:
f.write(f"The predict result is : {str(result)}\n")
log_filepath = r"D:\data\biendata\ccks2019_el\ner\m0.1log"
# emn_path = r'D:\data\bert\chinese_L-12_H-768_A-12'
emn_path = r'D:\data\bert\chinese-bert_chinese_wwm_L-12_H-768_A-12'
# check_point = ModelCheckpoint(model_path, monitor="val_loss", verbose=1, save_best_only=True, mode="min")
early_stop = EarlyStopping(monitor="val_loss", mode="min", patience=1)
# early_stop = EarlyStopping(monitor="val_crf_accuracy", mode="max", patience=2)
log = TensorBoard(log_dir=log_filepath,
write_images=False,
write_graph=True,
histogram_freq=0)
model = BLSTMCRFModel.load_model(model_path_o)
model.fit(train_x,
train_y,
x_validate=validate_x,
y_validate=validate_y,
epochs=40,
batch_size=512,
labels_weight=True,
fit_kwargs={'callbacks': [early_stop, log]})
model.evaluate(test_x, test_y)
model.save(model_path_n)
"""
继续训练
def __init__(self, model_path, type_filter=False):
# mention -> entity_json_line
self.subject_id_dict = subject_id_dict
self._model = BLSTMCRFModel.load_model(model_path)
self.type_filter = type_filter
def __init__(self, model_path):
# mention -> entity_json_line
self.subject_id_dict = subject_id_dict
self._model = BLSTMCRFModel.load_model(model_path)
x = []
return datas
def model_predict(self, model, text):
x_test = self.build_input(text)
result = model.predict(x_test)
chars = [i for i in text]
tags = []
for i in range(len(result)):
tags = tags + result[i]
res = list(zip(chars, tags))
print(res)
return (res)
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--option', type=str, default='predict')
args = parser.parse_args()
config = Config()
bertner = BERTNER()
if args.option == 'train':
bertner.train_model()
else:
model = BLSTMCRFModel.load_model(bertner.model_path)
while 1:
s = input('enter an sent:').strip()
bertner.model_predict(model, s)
def __init__(self, model_path):
with tf.device('/gpu:0'):
# mention -> entity_json_line
self.subject_dic = super().get_kb_dic()
self._model = BLSTMCRFModel.load_model(model_path)
print('train start')
train_x, train_y = get_train_data('data/train_text.txt')
embedding = BERTEmbedding("bert-base-chinese", sequence_length=512)
model = BLSTMCRFModel(embedding)
length = int(len(train_x) * 0.9)
print(len(train_x[:length]), len(train_y[:length]))
model.fit(train_x[:length], train_y[:length], train_x[length:], train_y[length:], epochs=5, batch_size=20)
# model.fit(train_x[:length], train_y[:length], train_x[length:], train_y[length:], epochs=5, batch_size=128,
# labels_weight=True, default_labels_weight=100)
valid_x = train_x[length:]
valid_y = train_y[length:]
model.save('models')
print('train end')
print('predict start')
try:
model = BLSTMCRFModel.load_model('models')
except Exception:
print('模型加载失败')
newsId_set = set()
try:
with open('data/result_bert.txt', 'r', encoding='utf-8') as file:
for line in file:
newsId_set.add(line.split('\t')[0])
except IOError:
print('文件不存在')
test_data = loadData('data/coreEntityEmotion_test_stage1.txt')
test_data += loadData('data/coreEntityEmotion_train.txt')
with open('data/result_bert.txt', 'a', encoding='utf-8') as file:
for news in tqdm(test_data):
if news['newsId'] in newsId_set:
def eval_crf():
model_path = r"D:\data\biendata\ccks2019_el\ner_model"
model = BLSTMCRFModel.load_model(model_path)
validate_x, validate_y = dload.load_json_data('validate')
model.evaluate(validate_x, validate_y)
## 面向脚本编程
from kashgari.tasks.seq_labeling import BLSTMCRFModel
from util import InputHelper
# 读取模型
new_model = BLSTMCRFModel.load_model('./model')
# 读取测试集数据
with open('./data/test', 'r', encoding='utf-8') as g:
test_data = g.readlines()
# 对测试集进行预测
with open('./keywords_test', 'w', encoding='utf-8') as g_key:
for ids, line in enumerate(test_data):
try:
label = InputHelper().iob_iobes(
new_model.predict(line.replace('\t', '。')))
result = InputHelper().result_to_json(line, label)
line_keys = [entity['word'] for entity in result['entities']]
g_key.write(','.join(line_keys) + '\n')
except Exception as e:
g_key.write('\n')
# “人工智能”
# 清洗一些看得到的错误，取前三个。这里做的很糙
with open('./keywords_test', 'r', encoding='utf-8') as g:
data = g.readlines()
with open('./keywords', 'w', encoding='utf-8') as f:
for line in data: