def baseline_predict(instances):
predictions = []
with open(Config.raw_test_set(), "w") as fp:
for instance in instances:
fp.write("%s\n" % json.dumps(instance))
pipeline.main()
with open(Config.submission_file(), "r") as fp:
for line in fp:
predictions.append(json.loads(line.strip()))
return predictions
def main(args=NullArgs()):
LogHelper.setup()
logger = LogHelper.get_logger(
os.path.splitext(os.path.basename(__file__))[0])
args.mode = Mode.PREDICT
if args.config is not None:
Config.load_config(args.config)
if args.out_file is not None:
Config.relative_path_submission = args.out_file
if args.in_file is not None:
Config.relative_path_test_file = args.in_file
if args.database is not None:
Config.relative_path_db = args.database
print("relative_path_db " + Config.relative_path_db)
print("raw_test_set " + Config.raw_test_set())
if os.path.exists(Config.test_doc_file):
os.remove(Config.test_doc_file)
if os.path.exists(Config.test_set_file):
os.remove(Config.test_set_file)
if args.mode in {Mode.PIPELINE, Mode.PREDICT, Mode.PREDICT_ALL_DATASETS}:
logger.info(
"=========================== Sub-task 1. Document Retrieval =========================================="
)
document_retrieval(logger, args.mode)
if args.mode in {
Mode.PIPELINE_NO_DOC_RETR, Mode.PIPELINE, Mode.PREDICT,
Mode.PREDICT_NO_DOC_RETR, Mode.PREDICT_ALL_DATASETS,
Mode.PREDICT_NO_DOC_RETR_ALL_DATASETS
}:
logger.info(
"=========================== Sub-task 2. Sentence Retrieval =========================================="
)
sentence_retrieval_ensemble(logger, args.mode)
logger.info(
"=========================== Sub-task 3. Claim Validation ============================================"
)
rte(logger, args, args.mode)