def main():
"""
This is used as the entry point for fitting.
"""
parser = argparse.ArgumentParser()
parser.add_argument("--database-analysis",
"-d",
dest="database_analysis",
help="analysis database to be used",
required=True)
parser.add_argument("--analysis",
"-a",
dest="type_ana",
help="choose type of analysis",
required=True)
parser.add_argument("--period-number", "-p", dest="period_number", type=int,
help="choose type of analysis (0: 2016, 1: 2017, 2: 2018, " \
"-1: all merged (default))", default=-1)
parser.add_argument("--output",
"-o",
default="simple_fit",
help="result output directory")
args = parser.parse_args()
configure_logger(False, None)
# Extract database as dictionary
data = parse_yaml(args.database_analysis)
data = data[list(data.keys())[0]]
# Run the chain
do_simple_fit(data, args.type_ana, args.period_number, args.output)
def main():
"""
This is used as the entry point for ml-analysis.
Read optional command line arguments and launch the analysis.
"""
parser = argparse.ArgumentParser()
parser.add_argument("--debug",
action="store_true",
help="activate debug log level")
parser.add_argument("--log-file",
dest="log_file",
help="file to print the log to")
parser.add_argument("--run-config",
"-r",
dest="run_config",
help="the run configuration to be used")
parser.add_argument("--database-analysis",
"-d",
dest="database_analysis",
help="analysis database to be used")
parser.add_argument("--database-ml-models",
dest="database_ml_models",
help="ml model database to be used")
parser.add_argument("--database-run-list",
dest="database_run_list",
help="run list database to be used")
parser.add_argument("--analysis",
"-a",
dest="type_ana",
help="choose type of analysis")
args = parser.parse_args()
configure_logger(args.debug, args.log_file)
# Extract which database and run config to be used
pkg_data = "machine_learning_hep.data"
pkg_data_run_config = "machine_learning_hep.submission"
run_config = load_config(args.run_config,
(pkg_data_run_config, "default_complete.yml"))
case = run_config["case"]
if args.type_ana is not None:
run_config["analysis"]["type"] = args.type_ana
db_analysis_default_name = f"database_ml_parameters_{case}.yml"
print(args.database_analysis)
db_analysis = load_config(args.database_analysis,
(pkg_data, db_analysis_default_name))
db_ml_models = load_config(args.database_ml_models,
(pkg_data, "config_model_parameters.yml"))
db_run_list = load_config(args.database_run_list,
(pkg_data, "database_run_list.yml"))
# Run the chain
do_entire_analysis(run_config, db_analysis, db_ml_models, db_run_list)
def main():
"""
Parse and handle arguments and dispatch to central function doclassification_regression.
This includes following steps:
1) Configure the logger
2) Dump default configuration YAMLs if requested (exit afterwards assuming the user wants
to edit and use them later)
3) Steer doclassification_regression with extracted configuration
"""
parser = argparse.ArgumentParser()
# Require a config file with some plotting info
parser.add_argument("--dump-default-config",
dest="dump_default_config",
help="get default run parameters as YAML config file")
parser.add_argument(
"--dump-default-models",
dest="dump_default_models",
help="get default model parameters as YAML config file")
parser.add_argument(
"-c",
"--load-run-config",
help="specify YAML file with run configuration to be loaded")
parser.add_argument(
"-m",
"--load-model-config",
help="specify YAML file with model configuration to be loaded")
parser.add_argument("--debug",
action="store_true",
help="turn in debug information")
parser.add_argument("--logfile", help="specify path to log file")
args = parser.parse_args()
configure_logger(args.debug, args.logfile)
immediate_exit = False
for k, v in {
"run": args.dump_default_config,
"models": args.dump_default_models
}.items():
if v is not None:
Configuration.dump_default_config(k, v)
immediate_exit = True
if immediate_exit:
sys.exit(0)
#model_config = assert_model_config(args.load_model_config, run_config)
conf = Configuration(args.load_run_config, args.load_model_config)
conf.configure()
conf.print_configuration()
# Pass config dictionary
doclassification_regression(conf)
