def load_data_and_model(model_file):
r"""Load filtered dataset, split dataloaders and saved model.
Args:
model_file (str): The path of saved model file.
Returns:
tuple:
- config (Config): An instance object of Config, which record parameter information in :attr:`model_file`.
- model (AbstractRecommender): The model load from :attr:`model_file`.
- dataset (Dataset): The filtered dataset.
- train_data (AbstractDataLoader): The dataloader for training.
- valid_data (AbstractDataLoader): The dataloader for validation.
- test_data (AbstractDataLoader): The dataloader for testing.
"""
checkpoint = torch.load(model_file)
config = checkpoint['config']
init_seed(config['seed'], config['reproducibility'])
init_logger(config)
logger = getLogger()
logger.info(config)
dataset = create_dataset(config)
logger.info(dataset)
train_data, valid_data, test_data = data_preparation(config, dataset)
init_seed(config['seed'], config['reproducibility'])
model = get_model(config['model'])(config,
train_data.dataset).to(config['device'])
model.load_state_dict(checkpoint['state_dict'])
model.load_other_parameter(checkpoint.get('other_parameter'))
return config, model, dataset, train_data, valid_data, test_data
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
}
def load_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)
logger = getLogger()
with open('../saved/ml-100k-dataset.pth',
'rb') as f: # You can use your filtered data path here.
dataset = pickle.load(f)
train_data, valid_data, test_data = load_split_dataloaders(
'../saved/ml-100k-for-BPR-dataloader.pth')
# You can use your split data path here.
model = get_model(config['model'])(config, train_data).to(config['device'])
checkpoint = torch.load('../saved/BPR-Mar-20-2021_17-11-05.pth'
) # Here you can replace it by your model path.
model.load_state_dict(checkpoint['state_dict'])
logger.info(model)
logger.info(train_data.dataset)
logger.info(valid_data.dataset)
logger.info(test_data.dataset)
# configurations initialization
config_dict = {
'USER_ID_FIELD': 'session_id',
'load_col': None,
'neg_sampling': None,
'benchmark_filename': ['train', 'test'],
'alias_of_item_id': ['item_id_list'],
'topk': [20],
'metrics': ['Recall', 'MRR'],
'valid_metric': 'MRR@20'
}
config = Config(model=args.model,
dataset=f'{args.dataset}',
config_dict=config_dict)
init_seed(config['seed'], config['reproducibility'])
# logger initialization
init_logger(config)
logger = getLogger()
logger.info(args)
logger.info(config)
# dataset filtering
dataset = create_dataset(config)
logger.info(dataset)
# dataset splitting
train_dataset, test_dataset = dataset.build()
if args.validation:
def new_dataset(config_dict=None, config_file_list=None):
config = Config(config_dict=config_dict, config_file_list=config_file_list)
init_seed(config['seed'], config['reproducibility'])
logging.basicConfig(level=logging.ERROR)
return create_dataset(config)
def new_dataloader(config_dict=None, config_file_list=None):
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)
return data_preparation(config, dataset)
def run_trial(model_name , dataset_name , hp_config = None , save_flag = False):
if not hp_config:
hp_config = {}
tuning = False
else:
tuning = True
commons.init_seeds()
verbose = True
verbose = (not tuning)
model_class = statics.model_name_map[model_name]
try:
default_config = model_class.default_params
except AttributeError:
default_config = {}
assert model_name in statics.recbole_models
default_config.update(statics.datasets_params[dataset_name])
default_config.update(hp_config)
config = Config(model=model_class, dataset=dataset_name, config_dict=default_config)
init_seed(config['seed'], config['reproducibility'])
init_logger(config)
logger = logging.getLogger()
# logger initialization
if verbose:
logger.info(config)
# dataset filtering
dataset = create_dataset(config)
train_data, valid_data, test_data = data_preparation(config, dataset)
train_data = add_graph(train_data)
if verbose:
logger.info(dataset)
model = model_class(config, train_data).to(commons.device)
trainer = utils.get_trainer(config)(config, model)
best_valid_score, best_valid_result = trainer.fit(train_data, valid_data , verbose= verbose , show_progress=verbose)
test_result = trainer.evaluate(test_data)
if verbose:
logger.info(set_color('best valid ', 'yellow') + f': {best_valid_result}')
logger.info(set_color('test result', 'yellow') + f': {test_result}')
metric = str.lower(config['valid_metric'])
if save_flag:
os.makedirs(os.path.join("bestmodels" , dataset_name , str(config["topk"])) , exist_ok=True)
save_path = os.path.join("bestmodels" , dataset_name , str(config["topk"]) , "{}.pth".format(model_name))
else:
save_path = None
if save_path:
shutil.copyfile(trainer.saved_model_file , save_path)
return {
'metric' : config['valid_metric'],
'best_valid_score': best_valid_score,
'valid_score_bigger': config['valid_metric_bigger'],
'best_valid_result': best_valid_result,
'test_score': test_result[metric]
}
def run_evaluation(model_name, dataset_name, model_path):
global_dict[model_name] = OrderedDict()
for metric in all_metrics:
global_dict[model_name][metric] = OrderedDict()
kvals = [10, 20, 30]
dataset_initialized = False
train_data = None
adj_sets = None
for K in kvals:
commons.init_seeds()
model_class = statics.model_name_map[model_name]
model_path = os.path.join("bestmodels", dataset_name, str(K),
"{}.pth".format(model_name))
loaded_file = torch.load(model_path)
config = loaded_file['config']
config['data_path'] = os.path.join('dataset', dataset_name)
config['topk'] = K
config['valid_metric'] = 'Recall@{}'.format(K)
config['eval_batch_size'] = 500000
init_seed(config['seed'], config['reproducibility'])
init_logger(config)
logger = logging.getLogger()
if not dataset_initialized:
# dataset filtering
dataset = create_dataset(config)
train_data, valid_data, test_data = data_preparation(
config, dataset)
train_data = add_graph(train_data)
item_degrees = train_data.graph.in_degrees()[train_data.num_users:]
adj_sets = construct_sets(train_data)
dataset_initialized = True
assert adj_sets
assert train_data
model = model_class(config, train_data).to(commons.device)
trainer = utils.get_trainer(config)(config, model)
test_result = trainer.evaluate(test_data,
load_best_model=True,
model_file=model_path)
custom_evaluator = CustomEvaluator(trainer, config, config['metrics'])
novelty, diversity = custom_evaluator.div_nov(train_data.num_users,
train_data.num_items,
item_degrees, test_data,
adj_sets)
novelty = round(novelty, 4)
diversity = round(diversity, 4)
for metric in all_metrics:
if metric not in ['novelty', 'diversity']:
global_dict[model_name][metric][K] = test_result[
"{}@{}".format(metric, K)]
global_dict[model_name]['novelty'][K] = novelty
global_dict[model_name]['diversity'][K] = diversity
