def ensemble_per_label(labels,
dataset,
api,
args,
resume,
fields=None,
multi_label_data=None,
session_file=None,
path=None,
log=None):
"""Creates an ensemble per label for multi-label datasets
"""
ensemble_ids = []
ensembles = []
model_ids = []
models = []
number_of_ensembles = len(labels)
if resume:
resume, ensemble_ids = c.checkpoint(c.are_ensembles_created,
path,
number_of_ensembles,
debug=args.debug)
ensembles = ensemble_ids
if not resume:
message = u.dated("Found %s ensembles out of %s."
" Resuming.\n" %
(len(ensemble_ids), number_of_ensembles))
u.log_message(message,
log_file=session_file,
console=args.verbosity)
# erase models' info that will be rebuilt
u.log_created_resources("models", path, None, mode='w')
number_of_ensembles = len(labels) - len(ensemble_ids)
ensemble_args_list = r.set_label_ensemble_args(args, labels,
multi_label_data,
number_of_ensembles, fields)
# create ensembles changing the input_field to select
# only one label at a time
(ensembles, ensemble_ids, models,
model_ids) = r.create_ensembles(dataset, ensemble_ids, ensemble_args_list,
args, number_of_ensembles, api, path,
session_file, log)
return ensembles, ensemble_ids, models, model_ids, resume
def ensemble_per_label(labels, dataset, fields,
objective_field, api, args, resume, name=None,
description=None, model_fields=None,
multi_label_data=None,
session_file=None, path=None, log=None):
"""Creates an ensemble per label for multi-label datasets
"""
ensemble_ids = []
ensembles = []
model_ids = []
models = []
number_of_ensembles = len(labels)
if resume:
resume, ensemble_ids = c.checkpoint(
c.are_ensembles_created, path, number_of_ensembles,
debug=args.debug)
ensembles = ensemble_ids
if not resume:
message = u.dated("Found %s ensembles out of %s."
" Resuming.\n"
% (len(ensemble_ids),
number_of_ensembles))
u.log_message(message, log_file=session_file,
console=args.verbosity)
# erase models' info that will be rebuilt
u.log_created_resources("models", path, None,
open_mode='w')
number_of_ensembles = len(labels) - len(ensemble_ids)
ensemble_args_list = r.set_label_ensemble_args(
name, description, args,
labels, multi_label_data, number_of_ensembles,
fields, model_fields, objective_field)
# create ensembles changing the input_field to select
# only one label at a time
(ensembles, ensemble_ids,
models, model_ids) = r.create_ensembles(
dataset, ensemble_ids, ensemble_args_list, args,
number_of_ensembles, api,
path, session_file, log)
return ensembles, ensemble_ids, models, model_ids, resume