default=1)
parser.add_argument('--method', help='code for method to test')
parser.add_argument('--method-path',
help='path to JSON config for method to test')
args = parser.parse_args()
sql_config, run_config, aws_config = load_config(sql_path=SQL_CONFIG,
run_path=RUN_CONFIG)
db = Database(**vars(sql_config))
print('creating dataruns...')
datarun_ids = []
for ds in DATASETS:
run_config.train_path = join(DATA_DIR, ds)
run_config.methods = [args.method]
dataset = enter_dataset(db, run_config, aws_config)
datarun_ids.extend(
enter_datarun(sql_config,
run_config,
aws_config,
run_per_partition=True))
print('computing on dataruns', datarun_ids)
work_parallel(db=db,
datarun_ids=datarun_ids,
aws_config=aws_config,
n_procs=args.processes)
print('workers finished.')
for rid in datarun_ids:
parser = argparse.ArgumentParser(description='''
Run a single end-to-end test with 10 sample datasets.
The script will create a datarun for each dataset, then run a worker until the
jobs are finished.
''')
parser.add_argument('--processes',
help='number of processes to run concurrently',
type=int,
default=4)
args = parser.parse_args()
sql_config, run_config, _ = load_config(sql_path=SQL_CONFIG,
run_path=RUN_CONFIG)
db = Database(**vars(sql_config))
print('creating dataruns...')
datarun_ids = []
for ds in DATASETS:
run_config.train_path = join(DATA_DIR, ds)
dataset = enter_dataset(db=db, run_config=run_config)
datarun_ids.append(
enter_datarun(sql_config=sql_config, run_config=run_config))
work_parallel(db=db, datarun_ids=datarun_ids, n_procs=args.processes)
print('workers finished.')
for rid in datarun_ids:
print_summary(db, rid)