def models_processing(datasets, models, model_ids, objective_field, fields,
api, args, resume,
name=None, description=None, model_fields=None,
session_file=None, path=None,
log=None, labels=None, multi_label_data=None,
other_label=None):
"""Creates or retrieves models from the input data
"""
ensemble_ids = []
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (has_models(args) or args.no_model):
dataset = datasets[0]
model_ids = []
models = []
if args.multi_label:
# If --number-of-models is not set or is 1, create one model per
# label. Otherwise, create one ensemble per label with the required
# number of models
if args.number_of_models < 2:
models, model_ids, resume = model_per_label(
labels, datasets, fields,
objective_field, api, args, resume, name, description,
model_fields, multi_label_data, session_file, path, log)
else:
(ensembles, ensemble_ids,
models, model_ids, resume) = ensemble_per_label(
labels, dataset, fields,
objective_field, api, args, resume, name, description,
model_fields, multi_label_data, session_file, path, log)
elif args.number_of_models > 1:
ensembles = []
# Ensemble of models
(ensembles, ensemble_ids,
models, model_ids, resume) = ensemble_processing(
datasets, objective_field, fields, api, args, resume,
name=name, description=description, model_fields=model_fields,
session_file=session_file, path=path, log=log)
ensemble = ensembles[0]
args.ensemble = bigml.api.get_ensemble_id(ensemble)
else:
# Set of partial datasets created setting args.max_categories
if len(datasets) > 1 and args.max_categories:
args.number_of_models = len(datasets)
# Cross-validation case: we create 2 * n models to be validated
# holding out an n% of data
if args.cross_validation_rate > 0:
if args.number_of_evaluations > 0:
args.number_of_models = args.number_of_evaluations
else:
args.number_of_models = int(MONTECARLO_FACTOR *
args.cross_validation_rate)
if resume:
resume, model_ids = c.checkpoint(
c.are_models_created, path, args.number_of_models,
debug=args.debug)
if not resume:
message = u.dated("Found %s models out of %s. Resuming.\n"
% (len(model_ids),
args.number_of_models))
u.log_message(message, log_file=session_file,
console=args.verbosity)
models = model_ids
args.number_of_models -= len(model_ids)
if args.max_categories > 0:
objective_field = None
model_args = r.set_model_args(name, description, args,
objective_field, fields,
model_fields, other_label)
models, model_ids = r.create_models(datasets, models,
model_args, args, api,
path, session_file, log)
# If a model is provided, we use it.
elif args.model:
model_ids = [args.model]
models = model_ids[:]
elif args.models or args.model_tag:
models = model_ids[:]
if args.ensemble:
ensemble = r.get_ensemble(args.ensemble, api, args.verbosity,
session_file)
ensemble_ids = [ensemble]
model_ids = ensemble['object']['models']
models = model_ids[:]
if args.ensembles or args.ensemble_tag:
model_ids = []
ensemble_ids = []
# Parses ensemble/ids if provided.
if args.ensemble_tag:
ensemble_ids = (ensemble_ids +
u.list_ids(api.list_ensembles,
"tags__in=%s" % args.ensemble_tag))
else:
ensemble_ids = u.read_resources(args.ensembles)
for ensemble_id in ensemble_ids:
ensemble = r.get_ensemble(ensemble_id, api)
if args.ensemble is None:
args.ensemble = ensemble_id
model_ids.extend(ensemble['object']['models'])
models = model_ids[:]
# If we are going to predict we must retrieve the models
if model_ids and args.test_set and not args.evaluate:
models, model_ids = r.get_models(models, args, api, session_file)
return models, model_ids, ensemble_ids, resume
def models_processing(datasets,
models,
model_ids,
api,
args,
resume,
fields=None,
session_file=None,
path=None,
log=None,
labels=None,
multi_label_data=None,
other_label=None):
"""Creates or retrieves models from the input data
"""
ensemble_ids = []
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (args.has_models_ or args.no_model):
dataset = datasets[0]
model_ids = []
models = []
if args.multi_label:
# If --number-of-models is not set or is 1, and there's
# no boosting options on, create one model per
# label. Otherwise, create one ensemble per label with the required
# number of models
if args.number_of_models < 2 and not args.boosting:
models, model_ids, resume = model_per_label(
labels,
datasets,
api,
args,
resume,
fields=fields,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
else:
(ensembles, ensemble_ids, models, model_ids,
resume) = ensemble_per_label(
labels,
dataset,
api,
args,
resume,
fields=fields,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
elif args.number_of_models > 1 or args.boosting:
ensembles = []
# Ensembles of models
(ensembles, ensemble_ids, models, model_ids,
resume) = ensemble_processing(datasets,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log)
ensemble = ensembles[0]
args.ensemble = bigml.api.get_ensemble_id(ensemble)
else:
# Set of partial datasets created setting args.max_categories
if len(datasets) > 1 and args.max_categories:
args.number_of_models = len(datasets)
if ((args.test_datasets and args.evaluate)
or (args.datasets and args.evaluate and args.dataset_off)):
args.number_of_models = len(args.dataset_ids)
# Cross-validation case: we create 2 * n models to be validated
# holding out an n% of data
if args.cross_validation_rate > 0:
if args.number_of_evaluations > 0:
args.number_of_models = args.number_of_evaluations
else:
args.number_of_models = int(MONTECARLO_FACTOR *
args.cross_validation_rate)
if resume:
resume, model_ids = c.checkpoint(c.are_models_created,
path,
args.number_of_models,
debug=args.debug)
if not resume:
message = u.dated(
"Found %s models out of %s. Resuming.\n" %
(len(model_ids), args.number_of_models))
u.log_message(message,
log_file=session_file,
console=args.verbosity)
models = model_ids
args.number_of_models -= len(model_ids)
model_args = r.set_model_args(args,
fields=fields,
objective_id=args.objective_id_,
model_fields=args.model_fields_,
other_label=other_label)
models, model_ids = r.create_models(datasets, models, model_args,
args, api, path, session_file,
log)
# If a model is provided, we use it.
elif args.model:
model_ids = [args.model]
models = model_ids[:]
elif args.models or args.model_tag:
models = model_ids[:]
if args.ensemble:
if not args.ensemble in ensemble_ids:
ensemble_ids.append(args.ensemble)
if not args.evaluate:
ensemble = r.get_ensemble(args.ensemble, api, args.verbosity,
session_file)
model_ids = ensemble['object']['models']
models = model_ids[:]
if args.ensembles or args.ensemble_tag:
model_ids = []
ensemble_ids = []
# Parses ensemble/ids if provided.
if args.ensemble_tag:
ensemble_ids = (ensemble_ids + u.list_ids(
api.list_ensembles, "tags__in=%s" % args.ensemble_tag))
else:
ensemble_ids = u.read_resources(args.ensembles)
for ensemble_id in ensemble_ids:
ensemble = r.get_ensemble(ensemble_id, api)
if args.ensemble is None:
args.ensemble = ensemble_id
model_ids.extend(ensemble['object']['models'])
models = model_ids[:]
# If we are going to predict we must retrieve the models
if model_ids and args.test_set and not args.evaluate:
models, model_ids = r.get_models(models, args, api, session_file)
return models, model_ids, ensemble_ids, resume