def main():
# getting the customized configurations from the command-line arguments.
args = KGETuneArgParser().get_args(sys.argv[1:])
# initializing bayesian optimizer and prepare data.
bays_opt = BaysOptimizer(args=args)
# perform the golden hyperparameter tuning.
bays_opt.optimize()
def test_hyperparamter_loader(model_name):
knowledge_graph = KnowledgeGraph(dataset="freebase15k")
knowledge_graph.prepare_data()
# getting the customized configurations from the command-line arguments.
args = KGETuneArgParser().get_args([])
hyperparams = HyperparamterLoader(args).load_hyperparameter("freebase15k", model_name)
assert hyperparams["optimizer"] is not None
def tunning_function(name):
"""Function to test the tuning of the models."""
knowledge_graph = KnowledgeGraph(dataset="freebase15k")
knowledge_graph.prepare_data()
# getting the customized configurations from the command-line arguments.
args = KGETuneArgParser().get_args([])
# initializing bayesian optimizer and prepare data.
args.debug = True
args.model = name
bays_opt = BaysOptimizer(args=args)
bays_opt.config_local.test_num = 10
# perform the golden hyperparameter tuning.
bays_opt.optimize()
assert bays_opt.return_best() is not None
def test_return_empty_before_optimization(mocked_fmin):
"""Function to test the tuning of the models."""
knowledge_graph = KnowledgeGraph(dataset="freebase15k")
knowledge_graph.prepare_data()
# getting the customized configurations from the command-line arguments.
args = KGETuneArgParser().get_args([])
# initializing bayesian optimizer and prepare data.
args.debug = True
args.model = 'analogy'
bays_opt = BaysOptimizer(args=args)
bays_opt.config_local.test_num = 10
with pytest.raises(Exception) as e:
bays_opt.return_best()
assert mocked_fmin.called is False
assert e.value.args[0] == 'Cannot find golden setting. Has optimize() been called?'
def main():
model_name = "transe"
dataset_name = "Freebase15k"
# 1. Tune the hyper-parameters for the selected model and dataset.
# p.s. this is using training and validation set.
args = KGETuneArgParser().get_args(
['-mn', model_name, '-ds', dataset_name])
# initializing bayesian optimizer and prepare data.
bays_opt = BaysOptimizer(args=args)
# perform the golden hyperparameter tuning.
bays_opt.optimize()
best = bays_opt.return_best()
# 2. Evaluate final model using the found best hyperparameters on testing set.
args = KGEArgParser().get_args(['-mn', model_name, '-ds', dataset_name])
# Preparing data and cache the data for later usage
knowledge_graph = KnowledgeGraph(dataset=args.dataset_name)
knowledge_graph.prepare_data()
# Extracting the corresponding model config and definition from Importer().
config_def, model_def = Importer().import_model_config(
args.model_name.lower())
config = config_def(args)
# Update the config params with the golden hyperparameter
for k, v in best.items():
config.__dict__[k] = v
model = model_def(**config.__dict__)
# Create, Compile and Train the model.
trainer = Trainer(model, config)
trainer.build_model()
trainer.train_model()