def main():
setup_logging()
parser = argparse.ArgumentParser(description='Example on Livejournal')
parser.add_argument('--config',
default=DEFAULT_CONFIG,
help='Path to config file')
parser.add_argument('-p', '--param', action='append', nargs='*')
parser.add_argument('--data_dir',
type=Path,
default='data',
help='where to save processed data')
args = parser.parse_args()
if args.param is not None:
overrides = chain.from_iterable(args.param) # flatten
else:
overrides = None
# download data
data_dir = args.data_dir
data_dir.mkdir(parents=True, exist_ok=True)
fpath = download_url(URL, data_dir)
fpath = extract_gzip(fpath)
print('Downloaded and extracted file.')
# random split file for train and test
random_split_file(fpath)
loader = ConfigFileLoader()
config = loader.load_config(args.config, overrides)
set_logging_verbosity(config.verbose)
subprocess_init = SubprocessInitializer()
subprocess_init.register(setup_logging, config.verbose)
subprocess_init.register(add_to_sys_path, loader.config_dir.name)
edge_paths = [data_dir / name for name in FILENAMES.values()]
convert_input_data(
config.entities,
config.relations,
config.entity_path,
edge_paths,
lhs_col=0,
rhs_col=1,
rel_col=None,
dynamic_relations=config.dynamic_relations,
)
train_path = [str(convert_path(data_dir / FILENAMES['train']))]
train_config = attr.evolve(config, edge_paths=train_path)
train(train_config, subprocess_init=subprocess_init)
eval_path = [str(convert_path(data_dir / FILENAMES['test']))]
eval_config = attr.evolve(config, edge_paths=eval_path)
do_eval(eval_config, subprocess_init=subprocess_init)
def main():
parser = argparse.ArgumentParser(description='Example on Livejournal')
parser.add_argument('--config',
default=DEFAULT_CONFIG,
help='Path to config file')
parser.add_argument('-p', '--param', action='append', nargs='*')
parser.add_argument('--data_dir',
default='data',
help='where to save processed data')
args = parser.parse_args()
if args.param is not None:
overrides = chain.from_iterable(args.param) # flatten
else:
overrides = None
# download data
data_dir = args.data_dir
os.makedirs(data_dir, exist_ok=True)
fpath = utils.download_url(URL, data_dir)
fpath = utils.extract_gzip(fpath)
print('Downloaded and extracted file.')
# random split file for train and test
random_split_file(fpath)
loader = ConfigFileLoader()
config = loader.load_config(args.config, overrides)
edge_paths = [os.path.join(data_dir, name) for name in FILENAMES.values()]
convert_input_data(
config.entities,
config.relations,
config.entity_path,
edge_paths,
lhs_col=0,
rhs_col=1,
rel_col=None,
dynamic_relations=config.dynamic_relations,
)
train_path = [convert_path(os.path.join(data_dir, FILENAMES['train']))]
train_config = attr.evolve(config, edge_paths=train_path)
train(
train_config,
subprocess_init=partial(add_to_sys_path, loader.config_dir.name),
)
eval_path = [convert_path(os.path.join(data_dir, FILENAMES['test']))]
eval_config = attr.evolve(config, edge_paths=eval_path)
do_eval(
eval_config,
subprocess_init=partial(add_to_sys_path, loader.config_dir.name),
)
def main():
setup_logging()
parser = argparse.ArgumentParser(description='Example on Livejournal')
parser.add_argument('--config',
default=DEFAULT_CONFIG,
help='Path to config file')
parser.add_argument('-p', '--param', action='append', nargs='*')
parser.add_argument('--data_dir',
type=Path,
default='data',
help='where to save processed data')
args = parser.parse_args()
# download data
data_dir = args.data_dir
data_dir.mkdir(parents=True, exist_ok=True)
fpath = download_url(URL, data_dir)
fpath = extract_gzip(fpath)
print('Downloaded and extracted file.')
# random split file for train and test
random_split_file(fpath)
loader = ConfigFileLoader()
config = loader.load_config(args.config, args.param)
set_logging_verbosity(config.verbose)
subprocess_init = SubprocessInitializer()
subprocess_init.register(setup_logging, config.verbose)
subprocess_init.register(add_to_sys_path, loader.config_dir.name)
input_edge_paths = [data_dir / name for name in FILENAMES]
output_train_path, output_test_path = config.edge_paths
convert_input_data(
config.entities,
config.relations,
config.entity_path,
config.edge_paths,
input_edge_paths,
TSVEdgelistReader(lhs_col=0, rhs_col=1, rel_col=None),
dynamic_relations=config.dynamic_relations,
)
train_config = attr.evolve(config, edge_paths=[output_train_path])
train(train_config, subprocess_init=subprocess_init)
eval_config = attr.evolve(config, edge_paths=[output_test_path])
do_eval(eval_config, subprocess_init=subprocess_init)