def create_model(self, ):
self.bert_embedding.processor.add_bos_eos = False
model = BLSTMModel(embedding=self.bert_embedding)
model.fit(valid_x, valid_y, epochs=1)
res = model.predict(valid_x[:20])
print(res)
return model
def train(self):
x_items, train_y, valid_x, valid_y = self.read_message('car/train.csv')
# 获取bert字向量
model = BLSTMModel(bert)
# 输入模型训练数据 标签 步数
model.fit(x_items,
train_y,
valid_x,
valid_y,
batch_size=64,
epochs=12,
callbacks=[tf_board_callback])
# 保存模型
file = pd.read_csv("car/test.csv", encoding='utf-8').values.tolist()
test_data = []
id_list = []
for i in file:
test_data.append(list(str(i[1]) + str(i[2])))
id_list.append(i[0])
predict_answers = model.predict(x_data=test_data)
file = open("data/test_predict_bert_car.csv", 'w', encoding='utf-8')
file.write("id,flag\n")
for i, j in zip(id_list, predict_answers):
i = i.strip()
file.write(str(i) + "," + str(j) + "\n")
model.save("../model/news-classification-bert-model")
def test_classification_eval_callback(self):
train_x, train_y = SMP2018ECDTCorpus.load_data()
test_x, test_y = SMP2018ECDTCorpus.load_data('test')
train_x = train_x[:1000]
train_y = train_y[:1000]
model = BLSTMModel()
eval_callback = callbacks.EvalCallBack(model, test_x, test_y, step=1)
model.fit(train_x, train_y, callbacks=[eval_callback], epochs=1)
def train(self):
# filepath = "saved-model-{epoch:02d}-{acc:.2f}.hdf5"
# checkpoint_callback = ModelCheckpoint(filepath,
# monitor='acc',
# verbose=1)
x_items, train_y = self.read_message('../data/yingyangshi/train.txt')
x_dev, dev_y = self.read_message('../data/yingyangshi/dev.txt')
# 获取bert字向量
bert = BERTEmbedding('textclassfation/input0/chinese_L-12_H-768_A-12')
model = BLSTMModel(bert)
# model.build_multi_gpu_model(gpus=2)
model.fit(x_items, train_y, x_dev, dev_y, epochs=2, batch_size=64)
# 保存模型
model.save("../健康管理师单选分字BERT-model")
def test_word2vec_embedding(self):
embedding = WordEmbeddings('sgns.weibo.bigram',
sequence_length=30,
limit=5000)
self.prepare_model(embedding)
self.model = BLSTMModel(embedding=embedding)
self.model.fit(self.x_data,
self.y_data,
x_validate=self.x_eval,
y_validate=self.y_eval)
sentence = list('语言学包含了几种分支领域。')
logging.info(self.model.embedding.tokenize(sentence))
logging.info(self.model.predict(sentence))
self.assertTrue(isinstance(self.model.predict(sentence), str))
self.assertTrue(isinstance(self.model.predict([sentence]), list))
def test_bert_model(self):
embedding = BERTEmbedding(bert_path,
task=kashgari.CLASSIFICATION,
sequence_length=100)
model = BLSTMModel(embedding=embedding)
model.fit(valid_x, valid_y, epochs=1)
res = model.predict(valid_x[:20])
assert True
model_path = os.path.join(tempfile.gettempdir(), str(time.time()))
model.save(model_path)
new_model = kashgari.utils.load_model(model_path)
new_res = new_model.predict(valid_x[:20])
assert np.array_equal(new_res, res)
def train(self):
x_items, train_y = self.read_message('../data/Chinese medicine licensed pharmacist/train.txt')
x_dev, dev_y = self.read_message('../data/Chinese medicine licensed pharmacist/dev.txt')
# 获取bert字向量
model = BLSTMModel()
# 输入模型训练数据 标签 步数
model.fit(x_items,
train_y,
x_dev,
dev_y,
batch_size=32,
epochs=20,
fit_kwargs={'callbacks': [tf_board_callback]})
# 保存模型
model.save("../model/中医执业药师char-model")
def train(self):
x_xiyao, xiyao_y = self.read_message('../data/西药执业药师/train.txt')
x_dev, dev_y = self.read_message('../data/西药执业药师/dev.txt')
# 获取bert字向量
bert = BERTEmbedding('bert-base-chinese', sequence_length=200)
model = BLSTMModel(bert)
# 输入模型训练数据 标签 步数
model.fit(x_xiyao,
xiyao_y,
x_dev,
dev_y,
epochs=8,
batch_size=256,
fit_kwargs={'callbacks': [tf_board_callback]})
# 保存模型
model.save("../西药执业药师-model")
def train(self):
x_items, train_y = self.read_message('../data/健康管理师分类数据集/train.txt')
x_xiyao, xiyao_y = self.read_message('../data/西药执业药师/train.txt')
x_yingyangshi, yingyangshi_y = self.read_message(
'../data/yingyangshi/train.txt')
x_items.extend(x_xiyao)
train_y.extend(xiyao_y)
x_items.extend(x_yingyangshi)
train_y.extend(yingyangshi_y)
x_dev, dev_y = self.read_message('../data/健康管理师分类数据集/valid.txt')
# 获取bert字向量
bert = BERTEmbedding('bert-base-chinese', sequence_length=200)
model = BLSTMModel(bert)
# 输入模型训练数据 标签 步数
model.fit(x_items,
train_y,
x_dev,
dev_y,
epochs=8,
batch_size=128,
fit_kwargs={'callbacks': [tf_board_callback]})
# 保存模型
model.save("../健康管理师分字BERT-model")
log_filepath = r"D:\data\biendata\ccks2019_el\clf_log"
early_stop = EarlyStopping(monitor="val_loss", mode="min", patience=2)
# early_stop = EarlyStopping(monitor="val_acc", mode="max", patience=2)
log = TensorBoard(log_dir=log_filepath,
write_images=False,
write_graph=True,
histogram_freq=0)
emn_path = r'D:\data\bert\chinese_L-12_H-768_A-12'
embedding = BERTEmbedding(emn_path, sequence_length=1024)
emn_path = r'D:/data/word2vec/zh/sgns.target.word-word.dynwin5.thr10.neg5.dim300.iter5/sgns.target.word-word.dynwin5.thr10.neg5.dim300.iter5.utf8.txt'
embedding = WordEmbeddings(emn_path, sequence_length=1024)
# model = DropoutBGRUModel(embedding)
model = BLSTMModel(embedding)
model.fit(train_x[:100000],
train_y[:100000],
x_validate=validate_x[:20000],
y_validate=validate_y[:20000],
epochs=20,
batch_size=256,
labels_weight=True,
fit_kwargs={'callbacks': [early_stop, log]})
model.evaluate(test_x, test_y)
model.save(model_path)
def setUpClass(cls):
cls.epochs = 3
cls.model = BLSTMModel()
def setUpClass(cls):
cls.epochs = 3
embedding = EmbeddingManager.get_w2v()
cls.model = BLSTMModel(embedding)
def predict_each_line(args, model):
import codecs
fout = codecs.open(args.output_file, 'w')
test_x, test_y = fetch_data_set(args.test_set_path)
for line, y in zip(test_x, test_y):
result = model.predict(text_processor(''.join(line)), batch_size=1, debug_info=False)
if result != ''.join(y):
str_message = ''.join(line) + "\t" + ''.join(y) +"\t" + result
print(str_message)
fout.write(str_message+'\n')
fout.close()
if __name__ == '__main__':
# initialize parameter
args = params_setup()
logging.basicConfig(filename=args.log_path, level=logging.DEBUG)
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu_id
bert_embedding = BERTEmbedding('bert-base-chinese', sequence_length=30)
model = BLSTMModel(bert_embedding)
model = model.load_model(args.model_path)
if (args.predict_mode == "from_input"):
predict_from_user_input(model)
else:
predict_from_test_set(args, model)