def objective_function(config_dict=None, config_file_list=None, saved=True):
r""" The default objective_function used in HyperTuning
Args:
config_dict (dict): parameters dictionary used to modify experiment parameters
config_file_list (list): config files used to modify experiment parameters
saved (bool): whether to save the model
"""
config = Config(config_dict=config_dict, config_file_list=config_file_list)
init_seed(config['seed'], config['reproducibility'])
logging.basicConfig(level=logging.ERROR)
dataset = create_dataset(config)
train_data, valid_data, test_data = data_preparation(config, dataset)
model = get_model(config['model'])(config, train_data).to(config['device'])
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
best_valid_score, best_valid_result = trainer.fit(train_data, valid_data, verbose=False, saved=saved)
test_result = trainer.evaluate(test_data, load_best_model=saved)
return {
'best_valid_score': best_valid_score,
'valid_score_bigger': config['valid_metric_bigger'],
'best_valid_result': best_valid_result,
'test_result': test_result
}
def save_example():
# configurations initialization
config_dict = {'checkpoint_dir': '../saved'}
config = Config(model='BPR', dataset='ml-100k', config_dict=config_dict)
init_seed(config['seed'], config['reproducibility'])
init_logger(config)
# dataset filtering
dataset = create_dataset(config)
dataset.save('../saved/')
# dataset splitting
train_data, valid_data, test_data = data_preparation(config, dataset)
save_split_dataloaders(config,
dataloaders=(train_data, valid_data, test_data))
model = get_model(config['model'])(config, train_data).to(config['device'])
# trainer loading and initialization
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
# model training
# the best model will be saved in here
best_valid_score, best_valid_result = trainer.fit(
train_data,
valid_data,
saved=True,
show_progress=config['show_progress'])
def run_recbole(model=None, dataset=None, config_file_list=None, config_dict=None, saved=True):
r""" A fast running api, which includes the complete process of
training and testing a model on a specified dataset
Args:
model (str): model name
dataset (str): dataset name
config_file_list (list): config files used to modify experiment parameters
config_dict (dict): parameters dictionary used to modify experiment parameters
saved (bool): whether to save the model
"""
# configurations initialization
config = Config(model=model, dataset=dataset, config_file_list=config_file_list, config_dict=config_dict)
init_seed(config['seed'], config['reproducibility'])
# logger initialization
init_logger(config)
logger = getLogger()
logger.info(config)
# dataset filtering
dataset = create_dataset(config)
logger.info(dataset)
# dataset splitting
train_data, valid_data, test_data = data_preparation(config, dataset)
print(train_data.dataset.item_feat)
print(valid_data.dataset.item_feat)
# model loading and initialization
model = get_model(config['model'])(config, train_data).to(config['device'])
logger.info(model)
# trainer loading and initialization
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
# model training
with profiler.profile(enabled=config["monitor"], with_stack=True, profile_memory=True, use_cuda=True) as prof:
best_valid_score, best_valid_result = trainer.fit(
train_data, valid_data, saved=saved, show_progress=config['show_progress']
)
if prof is not None:
print(prof.key_averages(group_by_stack_n=5).table(sort_by='self_cpu_time_total'))
# model evaluation
with profiler.profile(enabled=config["monitor_eval"], with_stack=True, profile_memory=True, use_cuda=True) as prof:
test_result = trainer.evaluate(test_data, load_best_model=saved, show_progress=config['show_progress'], cold_warm_distinct_eval=True)
if prof is not None:
print(prof.key_averages(group_by_stack_n=5).table(sort_by='self_cpu_time_total'))
logger.info(set_color('best valid ', 'yellow') + f': {best_valid_result}')
logger.info(set_color('test result', 'yellow') + f': {test_result}')
return {
'best_valid_score': best_valid_score,
'valid_score_bigger': config['valid_metric_bigger'],
'best_valid_result': best_valid_result,
'test_result': test_result
}
def run_recbole(model=None,
dataset=None,
config_file_list=None,
config_dict=None,
saved=True):
r""" A fast running api, which includes the complete process of
training and testing a model on a specified dataset
Args:
model (str): model name
dataset (str): dataset name
config_file_list (list): config files used to modify experiment parameters
config_dict (dict): parameters dictionary used to modify experiment parameters
saved (bool): whether to save the model
"""
# configurations initialization
config = Config(model=model,
dataset=dataset,
config_file_list=config_file_list,
config_dict=config_dict)
init_seed(config['seed'], config['reproducibility'])
# logger initialization
init_logger(config)
logger = getLogger()
logger.info(config)
# dataset filtering
dataset = create_dataset(config)
logger.info(dataset)
# dataset splitting
train_data, valid_data, test_data = data_preparation(config, dataset)
# model loading and initialization
model = get_model(config['model'])(config, train_data).to(config['device'])
logger.info(model)
# trainer loading and initialization
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
# model training
best_valid_score, best_valid_result = trainer.fit(train_data,
valid_data,
saved=saved)
# model evaluation
test_result = trainer.evaluate(test_data, load_best_model=saved)
logger.info('best valid result: {}'.format(best_valid_result))
logger.info('test result: {}'.format(test_result))
return {
'best_valid_score': best_valid_score,
'valid_score_bigger': config['valid_metric_bigger'],
'best_valid_result': best_valid_result,
'test_result': test_result
}
def run_recbole(model=None, dataset=None, config_file_list=None, config_dict=None, saved=True):
r""" A fast running api, which includes the complete process of
training and testing a model on a specified dataset
Args:
model (str, optional): Model name. Defaults to ``None``.
dataset (str, optional): Dataset name. Defaults to ``None``.
config_file_list (list, optional): Config files used to modify experiment parameters. Defaults to ``None``.
config_dict (dict, optional): Parameters dictionary used to modify experiment parameters. Defaults to ``None``.
saved (bool, optional): Whether to save the model. Defaults to ``True``.
"""
# configurations initialization
config = Config(model=model, dataset=dataset, config_file_list=config_file_list, config_dict=config_dict)
init_seed(config['seed'], config['reproducibility'])
# logger initialization
init_logger(config)
logger = getLogger()
logger.info(config)
# dataset filtering
dataset = create_dataset(config)
if config['save_dataset']:
dataset.save()
logger.info(dataset)
# dataset splitting
train_data, valid_data, test_data = data_preparation(config, dataset)
if config['save_dataloaders']:
save_split_dataloaders(config, dataloaders=(train_data, valid_data, test_data))
# model loading and initialization
model = get_model(config['model'])(config, train_data.dataset).to(config['device'])
logger.info(model)
# trainer loading and initialization
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
# model training
best_valid_score, best_valid_result = trainer.fit(
train_data, valid_data, saved=saved, show_progress=config['show_progress']
)
# model evaluation
test_result = trainer.evaluate(test_data, load_best_model=saved, show_progress=config['show_progress'])
logger.info(set_color('best valid ', 'yellow') + f': {best_valid_result}')
logger.info(set_color('test result', 'yellow') + f': {test_result}')
return {
'best_valid_score': best_valid_score,
'valid_score_bigger': config['valid_metric_bigger'],
'best_valid_result': best_valid_result,
'test_result': test_result
}
test_data = get_dataloader(config, 'test')(config,
new_test_dataset,
None,
shuffle=False)
else:
train_data = get_dataloader(config, 'train')(config,
train_dataset,
None,
shuffle=True)
test_data = get_dataloader(config, 'test')(config,
test_dataset,
None,
shuffle=False)
# model loading and initialization
model = get_model(config['model'])(config,
train_data.dataset).to(config['device'])
logger.info(model)
# trainer loading and initialization
trainer = get_trainer(config['MODEL_TYPE'], config['model'])(config, model)
# model training and evaluation
test_score, test_result = trainer.fit(
train_data,
test_data,
saved=True,
show_progress=config['show_progress'])
logger.info(set_color('test result', 'yellow') + f': {test_result}')
