def main_for_args(arg_path, dataset, division):
t = time.time()
args = load_args(arg_path)
args.training_data = args.training_data + dataset + "/"
args.dataset_division = division
print(args.embedding_module)
print(args)
remove_unlinked = False
if args.embedding_module == "RSN4EA":
remove_unlinked = True
kgs = read_kgs_from_folder(
args.training_data,
args.dataset_division,
args.alignment_module,
args.ordered,
remove_unlinked=remove_unlinked,
)
import tensorflow as tf
tf.keras.backend.clear_session()
model = get_model(args.embedding_module)()
model.set_args(args)
model.set_kgs(kgs)
model.init()
model.run()
model.test()
model.save()
print("Total run time = {:.3f} s.".format(time.time() - t))
def loaded_kgs():
path = "data/OpenEA/D_W_15K_V1/"
if not os.path.exists(path):
path = os.path.join("..", path)
return read_kgs_from_folder(
path, "721_5fold/1/", "mapping", True, remove_unlinked=False,
)
def __init__(self, args):
self.args = args
self.session = load_session()
self.kgs = read_kgs_from_folder(args.training_data,
args.dataset_division,
args.alignment_module, False)
self.entities = self.kgs.kg1.entities_set | self.kgs.kg2.entities_set
self.word2vec_path = args.word2vec_path
self.entity_local_name_dict = read_local_name(
args.training_data, set(self.kgs.kg1.entities_id_dict.keys()),
set(self.kgs.kg2.entities_id_dict.keys()))
self._generate_literal_vectors()
self._generate_name_vectors_mat()
self._generate_attribute_value_vectors()
def __init__(self, data_folder: str, division: str, args_path: str):
args = load_args(args_path)
self._data_folder = data_folder
self.download_and_unzip()
self._kgs = read_kgs_from_folder(data_folder, division,
args.alignment_module, args.ordered)
train_links = [(e[0], e[1], 1) for e in self._kgs.train_links]
valid_links = [(e[0], e[1], 1) for e in self._kgs.valid_links]
test_links = [(e[0], e[1], 1) for e in self._kgs.test_links]
super().__init__(
kg1=self._kgs.kg1,
kg2=self._kgs.kg2,
rnd=random.Random(),
labelled_pairs=train_links,
labelled_val_pairs=valid_links,
labelled_test_pairs=test_links,
)
self._name = data_folder.split("/")[-2] + "/" + division[:-1]
def __init__(self,
data_folder: str,
division: str,
args_path: str,
random_seed=0):
args = load_args(args_path)
self._data_folder = data_folder
self.download_and_unzip()
self._kgs = read_kgs_from_folder(data_folder, division,
args.alignment_module, args.ordered)
train_links = [(e[0], e[1], 1) for e in self._kgs.train_links]
valid_links = [(e[0], e[1], 1) for e in self._kgs.valid_links]
test_links = [(e[0], e[1], 1) for e in self._kgs.test_links]
super().__init__(
kg1=self._kgs.kg1,
kg2=self._kgs.kg2,
rnd=random.Random(random_seed),
labelled_pairs=train_links + valid_links + test_links,
# throw them together because of possible inbalance
# due to removal of inner links
)
self._name = data_folder.split("/")[-2] + "/" + division[:-1]
args.dataset_division = sys.argv[
3] # This is the fold used among the k (5) available.
if len(sys.argv) < 5:
args.gpu = "0"
else:
if sys.argv[4] == "CPU":
args.gpu = None
else:
args.gpu = sys.argv[4]
print(args.embedding_module)
print(args)
remove_unlinked = False
if args.embedding_module == "RSN4EA":
remove_unlinked = True
# load the kgs and put them in a class (see inner classes for more details)
kgs = read_kgs_from_folder(args.training_data,
args.dataset_division,
args.alignment_module,
args.ordered,
args.extra_entities_percentage_valid,
remove_unlinked=remove_unlinked)
model = get_model(
args.embedding_module)() # Get the current model class from args
model.set_args(args)
model.set_kgs(kgs)
model.init()
model.run()
model.test()
model.test_new()
model.save()
print("Total run time = {:.3f} s.".format(time.time() - t))
args.alignment_module = sys.argv[9]
args.rel_inp_dropout = float(sys.argv[10])
args.rel_hid_dropout = float(sys.argv[11])
args.rel_hidden_dim = float(sys.argv[12])
args.train_module = sys.argv[13]
args.exist_attr = False
print("load arguments:", vars(args))
remove_unlinked = False
if args.embedding_module == "RSN4EA":
remove_unlinked = True
kgs = read_kgs_from_folder(args.training_data,
args.dataset_division,
args.alignment_module,
args.ordered,
remove_unlinked=remove_unlinked,
exist_attr=args.exist_attr,
train_kg=args.train_kg)
model = get_model(args.embedding_module)()
model.set_args(args)
model.set_kgs(kgs)
model.init()
print("Model Parameters:")
for v in tf.compat.v1.trainable_variables():
print(v)
model.run()
model.eval_test()
model.save()
print("Total run time = {:.3f} s.".format(time.time() - t))
RSN4EA = RSN4EA
SEA = SEA
MTransE = MTransE
IPTransE = IPTransE
Attr2Vec = Attr2Vec
JAPE = JAPE
AlignE = AlignE
BootEA = BootEA
GCN_Align = GCN_Align
GMNN = GMNN
KDCoE = KDCoE
RDGCN = RDGCN
AliNet = AliNet
def get_model(model_name):
return getattr(ModelFamily, model_name)
if __name__ == '__main__':
kgs = read_kgs_from_folder(args.training_data, args.dataset_division,
args.alignment_module, args.ordered)
model = get_model(args.embedding_module)()
model.set_args(args)
model.set_kgs(kgs)
model.init()
model.run()
model.test()
model.save()
