def read_database(path, overwrite_path=None):
data_param = None
with open(path, 'r') as param_config:
data_param = yaml.load(param_config, Loader=yaml.FullLoader)
case = list(data_param.keys())[0]
data_param = data_param[case]
if overwrite_path:
overwrite_db = None
with open(overwrite_path, 'r') as param_config:
overwrite_db = yaml.load(param_config, Loader=yaml.FullLoader)
modify_dictionary(data_param, overwrite_db)
return case, data_param
def update_config(database: dict, run_config: dict, database_overwrite=None): # pylint: disable=unused-argument
"""Update database before usage
1. overwrite with potential additional user configuration
2. adjust paths
This adjusts database inline ==> no return value
Args:
database: dict
input database as read from YAML
run_config: dict
input run configuration as read from default_<stage>.yaml
database_overwrite: dict (optional)
substructured corresponding to database used to overwrite
corresponding fields in database
"""
logger = get_logger()
# Extract the case
case = list(database.keys())[0]
database = database[case]
# First overwrite as required by the user
# To be implemented
if database_overwrite:
logger.info("Updating database fields with custom user input")
modify_dictionary(database, database_overwrite, True)
# If not an ML analysis...
if not database["doml"]:
logger.info(
"Not an ML analysis, adjust paths and settings accordingly")
# ...append "_std" to paths where necessary
data_mc = ("data", "mc")
pkl_keys = ("pkl_skimmed_dec", "pkl_skimmed_decmerged")
for keys in product(data_mc, pkl_keys):
database["mlapplication"][keys[0]][keys[1]][:] = \
[f"{path}_std" for path in database["mlapplication"][keys[0]][keys[1]]]
# ...set the ML working point all to 0
for k in data_mc:
database["mlapplication"]["probcutpresel"][k][:] = \
[0] * len(database["mlapplication"]["probcutpresel"][k])
database["mlapplication"]["probcutoptimal"][:] \
= [0] * len(database["mlapplication"]["probcutoptimal"])