def main():
setup_logging()
parser = argparse.ArgumentParser(description='Example on FB15k')
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')
parser.add_argument('--no-filtered', dest='filtered', action='store_false',
help='Run unfiltered eval')
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
fpath = download_url(FB15K_URL, data_dir)
extract_tar(fpath)
print('Downloaded and extracted file.')
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)
input_edge_paths = [data_dir / name for name in FILENAMES]
output_train_path, output_valid_path, output_test_path = config.edge_paths
convert_input_data(
config.entities,
config.relations,
config.entity_path,
config.edge_paths,
input_edge_paths,
lhs_col=0,
rhs_col=2,
rel_col=1,
dynamic_relations=config.dynamic_relations,
)
train_config = attr.evolve(config, edge_paths=[output_train_path])
train(train_config, subprocess_init=subprocess_init)
relations = [attr.evolve(r, all_negs=True) for r in config.relations]
eval_config = attr.evolve(
config, edge_paths=[output_test_path], relations=relations, num_uniform_negs=0)
if args.filtered:
filter_paths = [output_test_path, output_valid_path, output_train_path]
do_eval(
eval_config,
evaluator=FilteredRankingEvaluator(eval_config, filter_paths),
subprocess_init=subprocess_init,
)
else:
do_eval(eval_config, subprocess_init=subprocess_init)
def main():
parser = argparse.ArgumentParser(description='Example on FB15k')
parser.add_argument('--config',
default='./fb15k_config.py',
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')
parser.add_argument('--no-filtered',
dest='filtered',
action='store_false',
help='Run unfiltered eval')
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
#fpath = utils.download_url(FB15K_URL, data_dir)
#utils.extract_tar(fpath)
#print('Downloaded and extracted file.')
edge_paths = [os.path.join(data_dir, name) for name in FILENAMES.values()]
print('edge_paths', edge_paths)
convert_input_data(
args.config,
edge_paths,
lhs_col=0,
rhs_col=2,
rel_col=1,
)
config = parse_config(args.config, overrides)
train_path = [convert_path(os.path.join(data_dir, FILENAMES['train']))]
train_config = attr.evolve(config, edge_paths=train_path)
train(train_config)
eval_path = [convert_path(os.path.join(data_dir, FILENAMES['test']))]
relations = [attr.evolve(r, all_negs=True) for r in config.relations]
eval_config = attr.evolve(config,
edge_paths=eval_path,
relations=relations)
if args.filtered:
filter_paths = [
convert_path(os.path.join(data_dir, FILENAMES['test'])),
convert_path(os.path.join(data_dir, FILENAMES['valid'])),
convert_path(os.path.join(data_dir, FILENAMES['train'])),
]
do_eval(eval_config, FilteredRankingEvaluator(eval_config,
filter_paths))
else:
do_eval(eval_config)
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()
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 run_train_eval():
#将数据转为PBG可读的分区文件
convert_input_data(CONFIG_PATH,
edge_paths,
lhs_col=0,
rhs_col=1,
rel_col=None)
#解析配置
config = parse_config(CONFIG_PATH)
#训练配置，已分区的train_paths路径替换配置文件中的edge_paths
train_config = attr.evolve(config, edge_paths=train_paths)
#传入训练配置文件开始训练
train(train_config)
#测试配置，已分区的eval_paths路径替换配置文件中的edge_paths
eval_config = attr.evolve(config, edge_paths=eval_paths)
#开始验证
do_eval(eval_config)
def run_train_eval():
random_split_file(DATA_PATH)
convert_input_data(
CONFIG_PATH,
edge_paths,
lhs_col=0,
rhs_col=1,
rel_col=None,
)
train_config = parse_config(CONFIG_PATH)
train_config = attr.evolve(train_config, edge_paths=train_path)
train(train_config)
eval_config = attr.evolve(train_config, edge_paths=eval_path)
do_eval(eval_config)
edge_paths = [os.path.join(DATA_DIR, name) for name in FILENAMES.values()]
from torchbiggraph.converters.import_from_tsv import convert_input_data
convert_input_data(
CONFIG_PATH,
edge_paths,
lhs_col=0,
rhs_col=1,
rel_col=None,
)
### SNIPPET 2 ###
def main():
parser = argparse.ArgumentParser(description='Example on FB15k')
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')
parser.add_argument('--no-filtered',
dest='filtered',
action='store_false',
help='Run unfiltered eval')
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
fpath = utils.download_url(FB15K_URL, data_dir)
utils.extract_tar(fpath)
print('Downloaded and extracted file.')
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=2,
rel_col=1,
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']))]
relations = [attr.evolve(r, all_negs=True) for r in config.relations]
eval_config = attr.evolve(config,
edge_paths=eval_path,
relations=relations,
num_uniform_negs=0)
if args.filtered:
filter_paths = [
convert_path(os.path.join(data_dir, FILENAMES['test'])),
convert_path(os.path.join(data_dir, FILENAMES['valid'])),
convert_path(os.path.join(data_dir, FILENAMES['train'])),
]
do_eval(
eval_config,
evaluator=FilteredRankingEvaluator(eval_config, filter_paths),
subprocess_init=partial(add_to_sys_path, loader.config_dir.name),
)
else:
do_eval(
eval_config,
subprocess_init=partial(add_to_sys_path, loader.config_dir.name),
)
0, # to reproduce results, we need to use all training data
workers=1,
distributed_init_method="tpc://localhost:30050",
)
for num_part in args.num_parts:
datadir = "{}_big_{}".format(args.dataset, num_part)
config_dict['entity_path'] = os.path.join(args.root_output,
datadir)
config_dict['entities']['all']['num_partitions'] = num_part
config_dict['edge_paths'] = [
os.path.join(args.root_output, datadir, datadir)
]
config = ConfigSchema.from_dict(config_dict)
convert_input_data(
config.entities,
config.relations,
config.entity_path,
config.edge_paths,
[
Path(
os.path.join(
args.root_output,
"{}_text/edgelist_pybig.txt".format(args.dataset)))
],
lhs_col=0,
rhs_col=2,
rel_col=1,
dynamic_relations=config.dynamic_relations,
)
comparator='dot',
loss_fn='softmax',
lr=0.1,
num_uniform_negs=50,
eval_fraction=
0, # to reproduce results, we need to use all training data
workers=1,
distributed_init_method="tpc://localhost:30050",
)
for num_part in tqdm(args.num_parts.split(","), desc='Run part'):
num_part = int(num_part)
datadir = "{}_big_rw_{}".format(args.dataset, num_part)
config_dict['entity_path'] = os.path.join(args.root_output, datadir)
config_dict['entities']['all']['num_partitions'] = num_part
config_dict['edge_paths'] = [
os.path.join(args.root_output, datadir, datadir)
]
config = ConfigSchema.from_dict(config_dict)
convert_input_data(
config.entities,
config.relations,
config.entity_path,
config.edge_paths,
[Path(edge_file_temp)],
lhs_col=0,
rhs_col=2,
rel_col=1,
dynamic_relations=config.dynamic_relations,
)
