def test_exception_on_search_space_file_not_exist():
with pytest.raises(FileNotFoundError) as e:
hp_loader = HyperparameterLoader(KGEArgParser().get_args(
["-ssf", "not_exist_file"]))
hp_loader.load_search_space("analogy")
assert str(e.value) == "Cannot find configuration file not_exist_file"
def test_exception_on_search_space_file_with_wrong_extension():
custom_hyperparamter_file = os.path.join(os.path.dirname(__file__), "resource", "custom_hyperparams", "custom.txt")
with pytest.raises(ValueError) as e:
hp_loader = HyperparameterLoader(KGEArgParser().get_args(["-ssf", custom_hyperparamter_file]))
hp_loader.load_search_space("analogy")
assert str(e.value) == "Configuration file must have .yaml or .yml extension: %s" % custom_hyperparamter_file
def __init__(self, args):
"""store the information of database"""
if args.model_name.lower() in [
"tucker", "conve", "convkb", "proje_pointwise"
]:
raise Exception(
"Model %s has not been supported in tuning hyperparameters!" %
args.model)
self.model_name = args.model_name
self.knowledge_graph = KnowledgeGraph(
dataset=args.dataset_name, custom_dataset_path=args.dataset_path)
self.kge_args = KGEArgParser().get_args([])
self.kge_args.dataset_name = args.dataset_name
self.kge_args.debug = args.debug
self.kge_args.device = args.device
self.max_evals = args.max_number_trials if not args.debug else 3
self.config_obj, self.model_obj = Importer().import_model_config(
self.model_name.lower())
self.config_local = self.config_obj(self.kge_args)
self.search_space = HyperparameterLoader(args).load_search_space(
self.model_name.lower())
self._best_result = None
self.trainer = None
def test_load_default_hyperparameter_file():
hp_loader = HyperparameterLoader(KGEArgParser().get_args([]))
hyperparams = hp_loader.load_hyperparameter("freebase15k", "analogy")
search_space = hp_loader.load_search_space("analogy")
assert hyperparams["learning_rate"] == 0.1
assert hyperparams["hidden_size"] == 200
assert str(search_space["epochs"].inputs()[1]) == "0 Literal{10}"
def test_load_custom_hyperparameter_file():
custom_hyperparamter_file = os.path.join(os.path.dirname(__file__), "resource", "custom_hyperparams", "custom.yaml")
hp_loader = HyperparameterLoader(KGEArgParser().get_args(["-hpf", custom_hyperparamter_file, "-ssf", custom_hyperparamter_file]))
hyperparams = hp_loader.load_hyperparameter("freebase15k", "analogy")
search_space = hp_loader.load_search_space("analogy")
assert hyperparams["learning_rate"] == 0.01
assert hyperparams["hidden_size"] == 200
assert str(search_space["epochs"].inputs()[1]) == "0 Literal{100}"
def test_search_space_loader(model_name):
knowledge_graph = KnowledgeGraph(dataset="freebase15k")
knowledge_graph.prepare_data()
# getting the customized configurations from the command-line arguments.
args = KGEArgParser().get_args([])
hyperparams = HyperparameterLoader(args).load_search_space(model_name)
assert hyperparams["epochs"] is not None
def __init__(self, args):
for arg_name in vars(args):
self.__dict__[arg_name] = getattr(args, arg_name)
# Training and evaluating related variables
self.hits = [1, 3, 5, 10]
self.disp_result = False
self.patience = 3 # should make this configurable as well.
# Visualization related,
# p.s. the visualizer is disable for most of the KGE methods for now.
self.disp_triple_num = 20
self.plot_training_result = True
self.plot_testing_result = True
# Knowledge Graph Information
self.knowledge_graph = KnowledgeGraph(
dataset=args.dataset_name, custom_dataset_path=args.dataset_path)
for key in self.knowledge_graph.kg_meta.__dict__:
self.__dict__[key] = self.knowledge_graph.kg_meta.__dict__[key]
# The results of training will be stored in the following folders
# which are relative to the parent folder (the path of the dataset).
dataset_path = self.knowledge_graph.dataset.dataset_path
self.path_tmp = dataset_path / 'intermediate'
self.path_tmp.mkdir(parents=True, exist_ok=True)
self.path_result = dataset_path / 'results'
self.path_result.mkdir(parents=True, exist_ok=True)
self.path_figures = dataset_path / 'figures'
self.path_figures.mkdir(parents=True, exist_ok=True)
self.path_embeddings = dataset_path / 'embeddings'
self.path_embeddings.mkdir(parents=True, exist_ok=True)
if args.exp is True:
paper_params = HyperparameterLoader(args).load_hyperparameter(
args.dataset_name, args.model_name)
for key, value in paper_params.items():
self.__dict__[
key] = value # copy all the setting from the paper.
class BaysOptimizer:
"""Bayesian optimizer class for tuning hyperparameter.
This class implements the Bayesian Optimizer for tuning the
hyper-parameter.
Args:
args (object): The Argument Parser object providing arguments.
name_dataset (str): The name of the dataset.
sampling (str): sampling to be used for generating negative triples
Examples:
>>> from pykg2vec.common import KGEArgParser
>>> from pykg2vec.utils.bayesian_optimizer import BaysOptimizer
>>> model = Complex()
>>> args = KGEArgParser().get_args(sys.argv[1:])
>>> bays_opt = BaysOptimizer(args=args)
>>> bays_opt.optimize()
"""
_logger = Logger().get_logger(__name__)
def __init__(self, args):
"""store the information of database"""
if args.model_name.lower() in [
"conve", "convkb", "proje_pointwise", "interacte", "hyper",
"acre"
]:
raise Exception(
"Model %s has not been supported in tuning hyperparameters!" %
args.model)
self.model_name = args.model_name
self.knowledge_graph = KnowledgeGraph(
dataset=args.dataset_name, custom_dataset_path=args.dataset_path)
self.kge_args = args
self.max_evals = args.max_number_trials if not args.debug else 3
self.config_obj, self.model_obj = Importer().import_model_config(
self.model_name.lower())
self.config_local = self.config_obj(self.kge_args)
self.search_space = HyperparameterLoader(args).load_search_space(
self.model_name.lower())
self._best_result = None
self.trainer = None
def optimize(self):
"""Function that performs bayesian optimization"""
trials = Trials()
self._best_result = fmin(fn=self._get_loss,
space=self.search_space,
trials=trials,
algo=tpe.suggest,
max_evals=self.max_evals)
columns = list(self.search_space.keys())
results = pd.DataFrame(columns=['iteration'] + columns + ['loss'])
for idx, trial in enumerate(trials.trials):
row = [idx]
translated_eval = space_eval(
self.search_space,
{k: v[0]
for k, v in trial['misc']['vals'].items()})
for k in columns:
row.append(translated_eval[k])
row.append(trial['result']['loss'])
results.loc[idx] = row
path = self.config_local.path_result / self.model_name
path.mkdir(parents=True, exist_ok=True)
results.to_csv(str(path / "trials.csv"), index=False)
self._logger.info(results)
self._logger.info('Found golden setting:')
self._logger.info(space_eval(self.search_space, self._best_result))
def return_best(self):
"""Function to return the best hyper-parameters"""
assert self._best_result is not None, 'Cannot find golden setting. Has optimize() been called?'
return space_eval(self.search_space, self._best_result)
def _get_loss(self, params):
"""Function that defines and acquires the loss"""
# copy the hyperparameters to trainer config and hyperparameter set.
for key, value in params.items():
self.config_local.__dict__[key] = value
self.config_local.__dict__['device'] = self.kge_args.device
model = self.model_obj(**self.config_local.__dict__)
self.trainer = Trainer(model, self.config_local)
# configure common setting for a tuning training.
self.config_local.disp_result = False
self.config_local.disp_summary = False
self.config_local.save_model = False
# do not overwrite test numbers if set
if self.config_local.test_num is None:
self.config_local.test_num = 1000
if self.kge_args.debug:
self.config_local.epochs = 1
# start the trial.
self.trainer.build_model()
loss = self.trainer.tune_model()
return {'loss': loss, 'status': STATUS_OK}
