def create_ensembles(datasets, ensemble_ids, ensemble_args, args,
number_of_ensembles=1,
api=None, path=None, session_file=None, log=None):
"""Create ensembles from input data
"""
if api is None:
api = bigml.api.BigML()
ensembles = ensemble_ids[:]
existing_ensembles = len(ensembles)
model_ids = []
ensemble_args_list = []
if isinstance(ensemble_args, list):
ensemble_args_list = ensemble_args
if args.dataset_off and args.evaluate:
args.test_dataset_ids = datasets[:]
if not args.multi_label:
datasets = datasets[existing_ensembles:]
if number_of_ensembles > 0:
message = dated("Creating %s.\n" %
plural("ensemble", number_of_ensembles))
log_message(message, log_file=session_file,
console=args.verbosity)
inprogress = []
for i in range(0, number_of_ensembles):
wait_for_available_tasks(inprogress, args.max_parallel_ensembles,
api, "ensemble",
wait_step=args.number_of_models)
if ensemble_args_list:
ensemble_args = ensemble_args_list[i]
if args.dataset_off and args.evaluate:
multi_dataset = args.test_dataset_ids[:]
del multi_dataset[i + existing_ensembles]
ensemble = api.create_ensemble(multi_dataset,
ensemble_args,
retries=None)
else:
ensemble = api.create_ensemble(datasets, ensemble_args,
retries=None)
ensemble_id = check_resource_error(ensemble,
"Failed to create ensemble: ")
log_message("%s\n" % ensemble_id, log_file=log)
ensemble_ids.append(ensemble_id)
inprogress.append(ensemble_id)
ensembles.append(ensemble)
log_created_resources("ensembles", path, ensemble_id,
mode='a')
models, model_ids = retrieve_ensembles_models(ensembles, api, path)
if number_of_ensembles < 2 and args.verbosity:
message = dated("Ensemble created: %s\n" %
get_url(ensemble))
log_message(message, log_file=session_file,
console=args.verbosity)
if args.reports:
report(args.reports, path, ensemble)
return ensembles, ensemble_ids, models, model_ids
def create_ensembles(datasets,
ensemble_ids,
ensemble_args,
args,
number_of_ensembles=1,
api=None,
path=None,
session_file=None,
log=None):
"""Create ensembles from input data
"""
if api is None:
api = bigml.api.BigML()
ensembles = ensemble_ids[:]
model_ids = []
ensemble_args_list = []
if isinstance(ensemble_args, list):
ensemble_args_list = ensemble_args
if number_of_ensembles > 0:
message = dated("Creating %s.\n" %
plural("ensemble", number_of_ensembles))
log_message(message, log_file=session_file, console=args.verbosity)
query_string = ALL_FIELDS_QS
inprogress = []
for i in range(0, number_of_ensembles):
wait_for_available_tasks(inprogress,
args.max_parallel_ensembles,
api.get_ensemble,
"ensemble",
query_string=query_string,
wait_step=args.number_of_models)
if ensemble_args_list:
ensemble_args = ensemble_args_list[i]
ensemble = api.create_ensemble(datasets, ensemble_args)
ensemble_id = check_resource_error(ensemble,
"Failed to create ensemble: ")
log_message("%s\n" % ensemble_id, log_file=log)
ensemble_ids.append(ensemble_id)
inprogress.append(ensemble_id)
ensembles.append(ensemble)
log_created_resources("ensembles",
path,
ensemble_id,
open_mode='a')
models, model_ids = retrieve_ensembles_models(ensembles, api, path)
if number_of_ensembles < 2 and args.verbosity:
message = dated("Ensemble created: %s.\n" % get_url(ensemble))
log_message(message, log_file=session_file, console=args.verbosity)
if args.reports:
report(args.reports, path, ensemble)
return ensembles, ensemble_ids, models, model_ids
def create_ensembles(datasets, ensemble_ids, ensemble_args, args,
number_of_ensembles=1,
api=None, path=None, session_file=None, log=None):
"""Create ensembles from input data
"""
if api is None:
api = bigml.api.BigML()
ensembles = ensemble_ids[:]
model_ids = []
ensemble_args_list = []
if isinstance(ensemble_args, list):
ensemble_args_list = ensemble_args
if number_of_ensembles > 0:
message = dated("Creating %s.\n" %
plural("ensemble", number_of_ensembles))
log_message(message, log_file=session_file,
console=args.verbosity)
query_string = ALL_FIELDS_QS
inprogress = []
for i in range(0, number_of_ensembles):
wait_for_available_tasks(inprogress, args.max_parallel_ensembles,
api.get_ensemble, "ensemble",
query_string=query_string,
wait_step=args.number_of_models)
if ensemble_args_list:
ensemble_args = ensemble_args_list[i]
ensemble = api.create_ensemble(datasets, ensemble_args)
ensemble_id = check_resource_error(ensemble,
"Failed to create ensemble: ")
log_message("%s\n" % ensemble_id, log_file=log)
ensemble_ids.append(ensemble_id)
inprogress.append(ensemble_id)
ensembles.append(ensemble)
log_created_resources("ensembles", path, ensemble_id,
open_mode='a')
models, model_ids = retrieve_ensembles_models(ensembles, api, path)
if number_of_ensembles < 2 and args.verbosity:
message = dated("Ensemble created: %s.\n" %
get_url(ensemble))
log_message(message, log_file=session_file,
console=args.verbosity)
if args.reports:
report(args.reports, path, ensemble)
return ensembles, ensemble_ids, models, model_ids
def create_ensemble(dataset, ensemble_args, args, api=None, path=None,
session_file=None, log=None):
"""Create ensemble from input data
"""
if api is None:
api = bigml.api.BigML()
message = dated("Creating ensemble.\n")
log_message(message, log_file=session_file,
console=args.verbosity)
ensemble = api.create_ensemble(dataset, ensemble_args)
log_created_resources("ensemble", path,
bigml.api.get_ensemble_id(ensemble))
check_resource_error(ensemble, "Failed to create ensemble: ")
log_message("%s\n" % ensemble['resource'], log_file=log)
return ensemble
def create_ensembles(dataset, ensemble_ids, ensemble_args, args,
number_of_ensembles=1,
api=None, path=None, session_file=None, log=None):
"""Create ensembles from input data
"""
if api is None:
api = bigml.api.BigML()
ensembles = ensemble_ids[:]
model_ids = []
ensemble_args_list = []
if isinstance(ensemble_args, list):
ensemble_args_list = ensemble_args
if number_of_ensembles > 0:
message = dated("Creating %s.\n" %
plural("ensemble", number_of_ensembles))
log_message(message, log_file=session_file,
console=args.verbosity)
query_string = ALL_FIELDS_QS
for i in range(0, number_of_ensembles):
if i % args.max_parallel_ensembles == 0 and i > 0:
try:
ensembles[i - 1] = check_resource(
ensembles[i - 1], api.get_ensemble,
query_string=query_string)
except ValueError, exception:
sys.exit("Failed to get a finished ensemble: %s" %
str(exception))
if ensemble_args_list:
ensemble_args = ensemble_args_list[i]
ensemble = api.create_ensemble(dataset, ensemble_args)
ensemble_id = check_resource_error(ensemble,
"Failed to create ensemble: ")
log_message("%s\n" % ensemble_id, log_file=log)
ensemble_ids.append(ensemble_id)
ensembles.append(ensemble)
log_created_resources("ensembles", path, ensemble_id,
open_mode='a')
models, model_ids = retrieve_ensembles_models(ensembles, api, path)
if number_of_ensembles < 2 and args.verbosity:
message = dated("Ensemble created: %s.\n" %
get_url(ensemble))
log_message(message, log_file=session_file,
console=args.verbosity)
def create_ensemble(dataset,
ensemble_args,
args,
api=None,
path=None,
session_file=None,
log=None):
"""Create ensemble from input data
"""
if api is None:
api = bigml.api.BigML()
message = dated("Creating ensemble.\n")
log_message(message, log_file=session_file, console=args.verbosity)
ensemble = api.create_ensemble(dataset, ensemble_args)
log_created_resources("ensemble", path,
bigml.api.get_ensemble_id(ensemble))
check_resource_error(ensemble, "Failed to create ensemble: ")
log_message("%s\n" % ensemble['resource'], log_file=log)
return ensemble
source_test = api.create_source('test.csv')
# DATASET CREATION
dataset_train = api.create_dataset(source_train)
datatest_test = api.create_dataset(source_test)
# TRAIN / VAL SPLIT CREATION
trainset = api.create_dataset(dataset_train, {"name": "Train 80% ", "sample_rate": 0.8})
valset = api.create_dataset(dataset_train, {"name": "Validation 20% ", "sample_rate": 0.8, "out_of_bag": True})
# MODEL ENSEMBLE
ensemble_args = {"objective_field": "SeriousDlqin2yrs"}
ensemble = api.create_ensemble(trainset, ensemble_args)
# EVALUATION ENSEMBLE
evaluation = api.create_evaluation(ensemble, valset)
# BATCH PREDICTION ON VAL
prediction_args = {"name": "prediction"}
batch_prediction = api.create_batch_prediction(ensemble, valset, {
"header": True,
"all_fields": True,
"probabilities": True})
# BATCH PREDICTION ON TEST
prediction_args = {"name": "prediction"}