from common.dataset.qald_7_ml import Qald_7_ml
from common.kb.dbpedia import DBpedia
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Generate one hop ')
parser.add_argument('--dataset',
default='lc_quad',
help='`lc_quad` or `qald_7_ml`')
parser.add_argument('--max_length', default=3, type=int)
args = parser.parse_args()
dataset_name = args.dataset
if dataset_name == 'lc_quad':
file_name = config['lc_quad']['entity_one_hop']
dataset = LC_QuAD(config['lc_quad']['train'],
config['lc_quad']['test'],
config['lc_quad']['vocab'], False, True)
elif dataset_name == 'qald_7_ml':
file_name = config['qald_7_ml']['entity_one_hop']
dataset = Qald_7_ml(config['qald_7_ml']['train'],
config['qald_7_ml']['test'],
config['qald_7_ml']['vocab'], False, False)
kb = DBpedia()
if os.path.exists(file_name):
with open(file_name, 'rb') as f:
one_hop = pk.load(f)
else:
one_hop = {}
for qa_row in tqdm(dataset.test_set + dataset.train_set):
for entity in qa_row.sparql.entities:
bounds=dict(min=0.0000001, max=0.1)),
# dict(name='positive_reward', type='int', bounds=dict(min=1, max=10)),
dict(name='negetive_reward',
type='int',
bounds=dict(min=-10, max=0)),
],
metrics=[dict(name='function_value')],
parallel_bandwidth=1,
# Define an Observation Budget for your experiment
observation_budget=100,
)
print("Created experiment: https://app.sigopt.com/experiment/" +
experiment.id)
args = parse_args()
lc_quad = LC_QuAD(config['lc_quad']['train'], config['lc_quad']['test'],
config['lc_quad']['vocab'], args.remove_entity,
args.remove_stop_words)
# Run the Optimization Loop until the Observation Budget is exhausted
while experiment.progress.observation_count < experiment.observation_budget:
suggestion = conn.experiments(experiment.id).suggestions().create()
value = evaluate_model(lc_quad, args, suggestion.assignments)
conn.experiments(experiment.id).observations().create(
suggestion=suggestion.id,
value=value,
)
# Update the experiment object
experiment = conn.experiments(experiment.id).fetch()
except RuntimeError as expt:
logger.error(expt)
return flask.jsonify({'error': str(expt)}), 408
except Exception as expt:
logger.error(expt)
return flask.jsonify({'error': str(expt)}), 422
@app.errorhandler(404)
def not_found(error):
return flask.make_response(flask.jsonify({'error': 'Command Not found'}), 404)
if __name__ == '__main__':
logger = logging.getLogger(__name__)
Utils.setup_logging()
args = parse_args()
dataset = LC_QuAD(config['lc_quad']['train'], config['lc_quad']['test'], config['lc_quad']['vocab'],
False, args.remove_stop_words)
runner = Runner(dataset, args)
runner.load_checkpoint()
runner.environment.entity_linker = None
runner.environment.relation_linker = None
print(runner.link("Who has been married to both Penny Lancaster and Alana Stewart?", k=10, e=0.1))
logger.info("Starting the HTTP server")
http_server = WSGIServer(('', args.port), app)
http_server.serve_forever()
from config import config
from common.vocab import Vocab
from common.word_vectorizer.glove import Glove
from common.dataset.lc_quad import LC_QuAD
from common.dataset.qald_7_ml import Qald_7_ml
from common.dataset.qald_6_ml import Qald_6_ml
from common.dataset.simple_dbpedia_qa import SimpleDBpediaQA
if __name__ == '__main__':
print('Create Vocab')
datasets = [
Qald_7_ml(config['qald_7_ml']['train'], config['qald_7_ml']['test'],
config['qald_7_ml']['vocab'], False, False),
Qald_6_ml(config['qald_6_ml']['train'], config['qald_6_ml']['test'],
config['qald_6_ml']['vocab'], False, False),
LC_QuAD(config['lc_quad']['train'], config['lc_quad']['test'],
config['lc_quad']['vocab'], False, False)
]
if not os.path.exists(config['vocab']):
# SimpleDBpediaQA(config['SimpleDBpediaQA']['train'], config['SimpleDBpediaQA']['test'],
# config['SimpleDBpediaQA']['vocab'],
# False, False)]
vocab = set()
for dataset in tqdm(datasets):
lines = dataset.corpus
for tokens in lines:
vocab |= set(tokens)
if dataset.one_hop is not None:
for entity, uris in dataset.one_hop.items():
for idx in range(len(uris)):
uri = URI(uris[idx][0])
vocab |= set(uri.tokens)
