def __pretrain_bertnrdj(dataset, n_labels, seq_length, n_steps, batch_size,
dropout, n_layers, load_model_file, dst_model_file):
init_logging('log/{}-pre-bertnrdj-{}-{}.log'.format(
cur_script_name, utils.get_machine_name(), str_today),
mode='a',
to_stdout=True)
dataset_files = config.DATA_FILES[dataset]
print('init robert ...')
bert_config = bertmodel.BertConfig.from_json_file(config.BERT_CONFIG_FILE)
robert_model = robert.Robert(
bert_config,
n_labels=n_labels,
seq_length=config.BERT_SEQ_LEN,
is_train=False,
init_checkpoint=dataset_files['bert_init_checkpoint'])
print('done')
yelp_tv_idxs_file = os.path.join(
config.RES_DIR,
'yelp/eng-part/yelp-rest-sents-r9-tok-eng-p0_04-tvidxs.txt')
amazon_tv_idxs_file = os.path.join(
config.RES_DIR, 'amazon/laptops-reivews-sent-tok-text-tvidxs.txt')
tv_idxs_file = amazon_tv_idxs_file if dataset == 'se14l' else yelp_tv_idxs_file
print('loading data ...')
idxs_train, idxs_valid = datautils.load_train_valid_idxs(tv_idxs_file)
logging.info('{} valid samples'.format(len(idxs_valid)))
# idxs_valid = set(idxs_valid)
valid_aspect_terms_list = __load_terms_list(
idxs_valid, dataset_files['pretrain_aspect_terms_file'])
valid_opinion_terms_list = __load_terms_list(
idxs_valid, dataset_files['pretrain_opinion_terms_file'])
print('done')
bertnrdj_model = BertNRDJ(n_labels,
config.BERT_EMBED_DIM,
hidden_size_lstm=hidden_size_lstm,
batch_size=batch_size,
model_file=load_model_file,
n_lstm_layers=n_layers)
bertnrdj_model.pretrain(
robert_model=robert_model,
train_aspect_tfrec_file=dataset_files[
'pretrain_train_aspect_tfrec_file'],
valid_aspect_tfrec_file=dataset_files[
'pretrain_valid_aspect_tfrec_file'],
train_opinion_tfrec_file=dataset_files[
'pretrain_train_opinion_tfrec_file'],
valid_opinion_tfrec_file=dataset_files[
'pretrain_valid_opinion_tfrec_file'],
valid_tokens_file=dataset_files['pretrain_valid_token_file'],
seq_length=seq_length,
valid_aspect_terms_list=valid_aspect_terms_list,
valid_opinion_terms_list=valid_opinion_terms_list,
n_steps=n_steps,
batch_size=batch_size,
dropout=dropout,
save_file=dst_model_file)
def __train_bertnrdj(dataset, n_labels, batch_size, model_file, dropout,
n_epochs, learning_rate, start_eval_epoch, n_layers):
init_logging('log/{}-bertnrdj-{}-{}.log'.format(cur_script_name,
utils.get_machine_name(),
str_today),
mode='a',
to_stdout=True)
dataset_files = config.DATA_FILES[dataset]
n_train, data_valid = bldatautils.load_train_data_bert_ol(
dataset_files['train_sents_file'],
dataset_files['train_valid_split_file'],
dataset_files['bert_valid_tokens_file'])
data_test = bldatautils.load_test_data_bert_ol(
dataset_files['test_sents_file'],
dataset_files['bert_test_tokens_file'])
bert_config = bertmodel.BertConfig.from_json_file(config.BERT_CONFIG_FILE)
bm = robert.Robert(bert_config,
n_labels=n_labels,
seq_length=config.BERT_SEQ_LEN,
is_train=False,
init_checkpoint=dataset_files['bert_init_checkpoint'])
logging.info('batch_size={}, learning_rate={}, dropout={}'.format(
batch_size, learning_rate, dropout))
# model_file = dataset_files['pretrained_bertnrdj_file']
# model_file = None
bertnrdj_model = BertNRDJ(n_labels,
config.BERT_EMBED_DIM,
hidden_size_lstm=hidden_size_lstm,
batch_size=batch_size,
model_file=model_file,
n_lstm_layers=n_layers)
bertnrdj_model.train(
robert_model=bm,
train_tfrec_file=dataset_files['train_tfrecord_file'],
valid_tfrec_file=dataset_files['valid_tfrecord_file'],
test_tfrec_file=dataset_files['test_tfrecord_file'],
seq_length=config.BERT_SEQ_LEN,
n_train=n_train,
data_valid=data_valid,
data_test=data_test,
dropout=dropout,
start_eval_spoch=start_eval_epoch,
n_epochs=n_epochs,
lr=learning_rate,
)
def __train_bertlstm_ol(dataset):
str_today = datetime.date.today().strftime('%y-%m-%d')
init_logging('log/{}-bertlstmcrfol-{}.log'.format(cur_script_name,
str_today),
mode='a',
to_stdout=True)
n_labels = 5
hidden_size_lstm = 200
batch_size = 16
n_epochs = 100
dropout = 0.5
dataset_files = config.DATA_FILES[dataset]
n_train, data_valid = bldatautils.load_train_data_bert_ol(
dataset_files['train_sents_file'],
dataset_files['train_valid_split_file'],
dataset_files['bert_valid_tokens_file'])
data_test = bldatautils.load_test_data_bert_ol(
dataset_files['test_sents_file'],
dataset_files['bert_test_tokens_file'])
bert_config = bertmodel.BertConfig.from_json_file(config.BERT_CONFIG_FILE)
bm = robert.Robert(bert_config,
n_labels=n_labels,
seq_length=config.BERT_SEQ_LEN,
is_train=False,
init_checkpoint=dataset_files['bert_init_checkpoint'])
lstmcrf = BertLSTMCRF(n_labels,
config.BERT_EMBED_DIM,
hidden_size_lstm=hidden_size_lstm,
batch_size=batch_size)
lstmcrf.train_ol(robert_model=bm,
train_tfrec_file=dataset_files['train_tfrecord_file'],
valid_tfrec_file=dataset_files['valid_tfrecord_file'],
test_tfrec_file=dataset_files['test_tfrecord_file'],
seq_length=config.BERT_SEQ_LEN,
n_train=n_train,
data_valid=data_valid,
data_test=data_test,
n_epochs=n_epochs,
dropout=dropout)
def __train_bertlstm_ol():
str_today = datetime.date.today().strftime('%y-%m-%d')
init_logging('log/bertlstmcrfol3-{}.log'.format(str_today),
mode='a',
to_stdout=True)
# dataset = 'se14r'
dataset = 'se15r'
n_labels = 5
dataset_files = config.DATA_FILES[dataset]
n_train, data_valid = bldatautils.load_train_data_bert_ol(
dataset_files['train_sents_file'],
dataset_files['train_valid_split_file'],
dataset_files['bert_valid_tokens_file'])
data_test = bldatautils.load_test_data_bert_ol(
dataset_files['test_sents_file'],
dataset_files['bert_test_tokens_file'])
bert_config = bertmodel.BertConfig.from_json_file(config.BERT_CONFIG_FILE)
bm = robert.Robert(bert_config,
n_labels=n_labels,
seq_length=config.BERT_SEQ_LEN,
is_train=False,
init_checkpoint=dataset_files['bert_init_checkpoint'])
lstmcrf = BertLSTMCRF(n_labels,
config.BERT_EMBED_DIM,
hidden_size_lstm=500,
batch_size=5)
lstmcrf.train_ol(robert_model=bm,
train_tfrec_file=dataset_files['train_tfrecord_file'],
valid_tfrec_file=dataset_files['valid_tfrecord_file'],
test_tfrec_file=dataset_files['test_tfrecord_file'],
seq_length=config.BERT_SEQ_LEN,
n_train=n_train,
data_valid=data_valid,
data_test=data_test)