def alternative_dataset_processing(
dataset_or_source, suffix, dataset_args, api, args, resume, session_file=None, path=None, log=None
):
"""Creates a dataset. Used in splits to generate train and test datasets
"""
alternative_dataset = None
# if resuming, try to extract dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, alternative_dataset = c.checkpoint(
c.is_dataset_created,
path,
"_%s" % suffix,
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity,
)
if alternative_dataset is None:
alternative_dataset = r.create_dataset(
dataset_or_source, dataset_args, args, api, path, session_file, log, suffix
)
if alternative_dataset:
alternative_dataset = r.get_dataset(alternative_dataset, api, args.verbosity, session_file)
return alternative_dataset, resume
def alternative_dataset_processing(dataset_or_source,
suffix,
dataset_args,
api,
args,
resume,
session_file=None,
path=None,
log=None):
"""Creates a dataset. Used in splits to generate train and test datasets
"""
alternative_dataset = None
# if resuming, try to extract dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, alternative_dataset = c.checkpoint(c.is_dataset_created,
path,
"_%s" % suffix,
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity)
if alternative_dataset is None:
alternative_dataset = r.create_dataset(dataset_or_source, dataset_args,
args, api, path, session_file,
log, suffix)
if alternative_dataset:
alternative_dataset = r.get_dataset(alternative_dataset, api,
args.verbosity, session_file)
return alternative_dataset, resume
def split_processing(dataset, name, description, api, args, resume,
session_file=None, path=None, log=None):
"""Splits a dataset into train and test datasets
"""
train_dataset = None
test_dataset = None
sample_rate = 1 - args.test_split
# if resuming, try to extract train dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, train_dataset = c.checkpoint(
c.is_dataset_created, path, "_train", debug=args.debug,
message=message, log_file=session_file, console=args.verbosity)
if train_dataset is None:
dataset_split_args = r.set_dataset_split_args(
"%s - train (%s %%)" % (name,
int(sample_rate * 100)), description, args,
sample_rate, out_of_bag=False)
train_dataset = r.create_dataset(
dataset, dataset_split_args, args, api, path, session_file,
log, "train")
if train_dataset:
train_dataset = r.get_dataset(train_dataset, api,
args.verbosity, session_file)
# if resuming, try to extract test dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, test_dataset = c.checkpoint(
c.is_dataset_created, path, "_test", debug=args.debug,
message=message, log_file=session_file, console=args.verbosity)
if test_dataset is None:
dataset_split_args = r.set_dataset_split_args(
"%s - test (%s %%)" % (name,
int(args.test_split * 100)), description, args,
sample_rate, out_of_bag=True)
test_dataset = r.create_dataset(
dataset, dataset_split_args, args, api, path, session_file,
log, "test")
if test_dataset:
test_dataset = r.get_dataset(test_dataset, api, args.verbosity,
session_file)
return train_dataset, test_dataset, resume
def dataset_processing(source,
training_set,
test_set,
model_ids,
name,
description,
fields,
dataset_fields,
api,
args,
resume,
csv_properties=None,
session_file=None,
path=None,
log=None):
"""Creating or retrieving dataset from input arguments
"""
dataset = None
if (training_set or args.source or (args.evaluate and test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(c.is_dataset_created,
path,
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.dataset and not args.model and not model_ids
and not args.no_dataset)
or (args.evaluate and args.test_set and not args.dataset)):
dataset_args = r.set_dataset_args(name, description, args, fields,
dataset_fields)
dataset = r.create_dataset(source, dataset_args, args, api, path,
session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if not csv_properties and 'locale' in dataset['object']:
csv_properties = {'data_locale': dataset['object']['locale']}
fields = Fields(dataset['object']['fields'], **csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, api, args, session_file)
return dataset, resume, csv_properties, fields
def dataset_processing(source, training_set, test_set, model_ids, name,
description, fields, dataset_fields, api, args,
resume, csv_properties=None,
session_file=None, path=None, log=None):
"""Creating or retrieving dataset from input arguments
"""
dataset = None
if (training_set or args.source or (args.evaluate and test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(
c.is_dataset_created, path, debug=args.debug, message=message,
log_file=session_file, console=args.verbosity)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.dataset and not args.model and not model_ids and
not args.no_dataset) or
(args.evaluate and args.test_set and not args.dataset)):
dataset_args = r.set_dataset_args(name, description, args, fields,
dataset_fields)
dataset = r.create_dataset(source, dataset_args, args, api,
path, session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if not csv_properties and 'locale' in dataset['object']:
csv_properties = {
'data_locale': dataset['object']['locale']}
fields = Fields(dataset['object']['fields'], **csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, api, args, session_file)
return dataset, resume, csv_properties, fields
def dataset_processing(source,
api,
args,
resume,
fields=None,
csv_properties=None,
multi_label_data=None,
session_file=None,
path=None,
log=None):
"""Creating or retrieving dataset from input arguments
"""
datasets = []
dataset = None
if (args.training_set or args.source or
(hasattr(args, "evaluate") and args.evaluate and args.test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(c.is_dataset_created,
path,
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.has_datasets_ and not args.has_models_
and not args.no_dataset)
or (hasattr(args, "evaluate") and args.evaluate and args.test_set
and not args.dataset)):
dataset_args = r.set_dataset_args(args,
fields,
multi_label_data=multi_label_data)
dataset = r.create_dataset(source, dataset_args, args, api, path,
session_file, log)
# If set of datasets is provided, let's check their ids.
elif args.dataset_ids:
for i in range(0, len(args.dataset_ids)):
dataset_id = args.dataset_ids[i]
if isinstance(dataset_id, dict) and "id" in dataset_id:
dataset_id = dataset_id["id"]
datasets.append(bigml.api.get_dataset_id(dataset_id))
dataset = datasets[0]
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if ('object' in dataset and 'objective_field' in dataset['object']
and 'column_number' in dataset['object']['objective_field']):
dataset_objective = dataset['object']['objective_field'][
'column_number']
csv_properties.update(objective_field=dataset_objective,
objective_field_present=True)
fields = get_fields_structure(dataset, csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, args, api, session_file)
if hasattr(args, 'objective_field'):
new_objective = get_new_objective(fields, args.objective_field)
else:
new_objective = None
updated = False
# We'll update the dataset if
# the flag --dataset_attributes is used
# the --multi-label flag is used and there's an --objective-field
# the --max-categories flag is used and there's an --objective-field
# the --impor-fields flag is used
if check_dataset_update(args, dataset):
dataset_args = r.set_dataset_args(args, fields)
if args.shared_flag and r.shared_changed(args.shared, dataset):
dataset_args.update(shared=args.shared)
dataset = r.update_dataset(dataset,
dataset_args,
args,
api=api,
path=path,
session_file=session_file)
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
updated = True
if new_objective is not None:
csv_properties.update(objective_field=args.objective_field,
objective_field_present=True)
updated = True
if updated:
fields = Fields(dataset['object']['fields'], **csv_properties)
if not datasets:
datasets = [dataset]
else:
datasets[0] = dataset
return datasets, resume, csv_properties, fields
def split_processing(dataset,
name,
description,
api,
args,
resume,
session_file=None,
path=None,
log=None):
"""Splits a dataset into train and test datasets
"""
train_dataset = None
test_dataset = None
sample_rate = 1 - args.test_split
# if resuming, try to extract train dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, train_dataset = c.checkpoint(c.is_dataset_created,
path,
"_train",
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity)
if train_dataset is None:
dataset_split_args = r.set_dataset_split_args(
"%s - train (%s %%)" % (name, int(sample_rate * 100)),
description,
args,
sample_rate,
out_of_bag=False)
train_dataset = r.create_dataset(dataset, dataset_split_args, args,
api, path, session_file, log, "train")
if train_dataset:
train_dataset = r.get_dataset(train_dataset, api, args.verbosity,
session_file)
# if resuming, try to extract test dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, test_dataset = c.checkpoint(c.is_dataset_created,
path,
"_test",
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity)
if test_dataset is None:
dataset_split_args = r.set_dataset_split_args(
"%s - test (%s %%)" % (name, int(args.test_split * 100)),
description,
args,
sample_rate,
out_of_bag=True)
test_dataset = r.create_dataset(dataset, dataset_split_args, args, api,
path, session_file, log, "test")
if test_dataset:
test_dataset = r.get_dataset(test_dataset, api, args.verbosity,
session_file)
return train_dataset, test_dataset, resume
def dataset_processing(source, api, args, resume,
fields=None,
csv_properties=None,
multi_label_data=None,
session_file=None, path=None, log=None):
"""Creating or retrieving dataset from input arguments
"""
datasets = []
dataset = None
if (args.training_set or args.source or (
hasattr(args, "evaluate") and args.evaluate and args.test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(
c.is_dataset_created, path, debug=args.debug, message=message,
log_file=session_file, console=args.verbosity)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.has_datasets_ and not args.has_models_
and not args.no_dataset) or
(hasattr(args, "evaluate") and args.evaluate and
args.test_set and not args.dataset)):
dataset_args = r.set_dataset_args(args, fields,
multi_label_data=multi_label_data)
dataset = r.create_dataset(source, dataset_args, args, api,
path, session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If set of datasets is provided, let's check their ids.
elif args.dataset_ids:
for i in range(0, len(args.dataset_ids)):
datasets.append(bigml.api.get_dataset_id(args.dataset_ids[i]))
dataset = datasets[0]
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if ('object' in dataset and 'objective_field' in dataset['object'] and
'column_number' in dataset['object']['objective_field']):
dataset_objective = dataset[
'object']['objective_field']['column_number']
csv_properties.update(objective_field=dataset_objective,
objective_field_present=True)
fields = get_fields_structure(dataset, csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, args, api, session_file)
if hasattr(args, 'objective_field'):
new_objective = get_new_objective(fields, args.objective_field)
else:
new_objective = None
updated = False
# We'll update the dataset if
# the flag --dataset_attributes is used
# the --multi-label flag is used and there's an --objective-field
# the --max-categories flag is used and there's an --objective-field
if check_dataset_update(args, dataset):
dataset_args = r.set_dataset_args(args, fields)
if args.shared_flag and r.shared_changed(args.shared, dataset):
dataset_args.update(shared=args.shared)
dataset = r.update_dataset(dataset, dataset_args, args,
api=api, path=path,
session_file=session_file)
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
updated = True
if new_objective is not None:
csv_properties.update(objective_field=args.objective_field,
objective_field_present=True)
updated = True
if updated:
fields = Fields(dataset['object']['fields'], **csv_properties)
if not datasets:
datasets = [dataset]
else:
datasets[0] = dataset
return datasets, resume, csv_properties, fields
def dataset_processing(
source,
training_set,
test_set,
fields,
objective_field,
api,
args,
resume,
name=None,
description=None,
dataset_fields=None,
multi_label_data=None,
csv_properties=None,
session_file=None,
path=None,
log=None,
):
"""Creating or retrieving dataset from input arguments
"""
datasets = []
dataset = None
if training_set or args.source or (args.evaluate and test_set):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(
c.is_dataset_created,
path,
debug=args.debug,
message=message,
log_file=session_file,
console=args.verbosity,
)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if (source and not has_datasets(args) and not has_models(args) and not args.no_dataset) or (
args.evaluate and args.test_set and not args.dataset
):
dataset_args = r.set_dataset_args(
name,
description,
args,
fields,
dataset_fields,
objective_field=objective_field,
multi_label_data=multi_label_data,
)
dataset = r.create_dataset(source, dataset_args, args, api, path, session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If set of datasets is provided, let's check their ids.
elif args.dataset_ids:
for i in range(0, len(args.dataset_ids)):
datasets.append(bigml.api.get_dataset_id(args.dataset_ids[i]))
dataset = datasets[0]
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if (
"object" in dataset
and "objective_field" in dataset["object"]
and "column_number" in dataset["object"]["objective_field"]
):
dataset_objective = dataset["object"]["objective_field"]["column_number"]
csv_properties.update(objective_field=dataset_objective, objective_field_present=True)
fields = get_fields_structure(dataset, csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, args, api, session_file)
new_objective = get_new_objective(fields, args.objective_field, dataset)
if (
new_objective is not None
or args.dataset_attributes
or (args.shared_flag and r.shared_changed(args.shared, dataset))
):
dataset_args = r.set_dataset_args(name, description, args, fields, dataset_fields, objective_field)
if args.shared_flag and r.shared_changed(args.shared, dataset):
dataset_args.update(shared=args.shared)
dataset = r.update_dataset(dataset, dataset_args, args, api=api, path=path, session_file=session_file)
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
csv_properties.update(objective_field=objective_field, objective_field_present=True)
fields = Fields(dataset["object"]["fields"], **csv_properties)
if not datasets:
datasets = [dataset]
else:
datasets[0] = dataset
return datasets, resume, csv_properties, fields
def dataset_processing(source, training_set, test_set, fields, objective_field,
api, args, resume, name=None, description=None,
dataset_fields=None, multi_label_data=None,
csv_properties=None,
session_file=None, path=None, log=None):
"""Creating or retrieving dataset from input arguments
"""
datasets = []
dataset = None
if (training_set or args.source or (args.evaluate and test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
message = u.dated("Dataset not found. Resuming.\n")
resume, args.dataset = c.checkpoint(
c.is_dataset_created, path, debug=args.debug, message=message,
log_file=session_file, console=args.verbosity)
# If we have a source but no dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not has_datasets(args) and not has_models(args)
and not args.no_dataset) or
(args.evaluate and args.test_set and not args.dataset)):
dataset_args = r.set_dataset_args(name, description, args, fields,
dataset_fields,
objective_field=objective_field,
multi_label_data=multi_label_data)
dataset = r.create_dataset(source, dataset_args, args, api,
path, session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If set of datasets is provided, let's check their ids.
elif args.dataset_ids:
for i in range(0, len(args.dataset_ids)):
datasets.append(bigml.api.get_dataset_id(args.dataset_ids[i]))
dataset = datasets[0]
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if ('object' in dataset and 'objective_field' in dataset['object'] and
'column_number' in dataset['object']['objective_field']):
dataset_objective = dataset[
'object']['objective_field']['column_number']
csv_properties.update(objective_field=dataset_objective,
objective_field_present=True)
fields = get_fields_structure(dataset, csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, args, api, session_file)
new_objective = get_new_objective(fields, args.objective_field,
dataset)
if (new_objective is not None or args.dataset_attributes or
r.shared_changed(args.shared, dataset)):
dataset_args = r.set_dataset_args(name, description, args, fields,
dataset_fields, objective_field)
dataset_args.update(shared=args.shared)
dataset = r.update_dataset(dataset, dataset_args, args,
api=api, path=path,
session_file=session_file)
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
csv_properties.update(objective_field=objective_field,
objective_field_present=True)
fields = Fields(dataset['object']['fields'], **csv_properties)
if not datasets:
datasets = [dataset]
else:
datasets[0] = dataset
return datasets, resume, csv_properties, fields
def compute_output(api, args, training_set, test_set=None, output=None,
objective_field=None,
description=None,
field_attributes=None,
types=None,
dataset_fields=None,
model_fields=None,
name=None, training_set_header=True,
test_set_header=True, model_ids=None,
votes_files=None, resume=False, fields_map=None):
""" Creates one or more models using the `training_set` or uses the ids
of previously created BigML models to make predictions for the `test_set`.
"""
source = None
dataset = None
model = None
models = None
fields = None
# It is compulsory to have a description to publish either datasets or
# models
if (not description and
(args.black_box or args.white_box or args.public_dataset)):
raise Exception("You should provide a description to publish.")
path = u.check_dir(output)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
csv_properties = {}
# If logging is required, open the file for logging
log = None
if args.log_file:
u.check_dir(args.log_file)
log = args.log_file
# If --clear_logs the log files are cleared
if args.clear_logs:
try:
open(log, 'w', 0).close()
except IOError:
pass
# Starting source processing
if (training_set or (args.evaluate and test_set)):
# If resuming, try to extract args.source form log files
if resume:
resume, args.source = u.checkpoint(u.is_source_created, path,
debug=args.debug)
if not resume:
message = u.dated("Source not found. Resuming.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
# If neither a previous source, dataset or model are provided.
# we create a new one. Also if --evaluate and test data are provided
# we create a new dataset to test with.
data_set, data_set_header = r.data_to_source(training_set, test_set,
training_set_header,
test_set_header, args)
if data_set is not None:
source_args = r.set_source_args(data_set_header, name, description,
args)
source = r.create_source(data_set, source_args, args, api,
path, session_file, log)
# If a source is provided either through the command line or in resume
# steps, we use it.
elif args.source:
source = bigml.api.get_source_id(args.source)
# If we already have source, we check that is finished, extract the
# fields, and update them if needed.
if source:
source = r.get_source(source, api, args.verbosity, session_file)
if 'source_parser' in source['object']:
source_parser = source['object']['source_parser']
if 'missing_tokens' in source_parser:
csv_properties['missing_tokens'] = (
source_parser['missing_tokens'])
if 'data_locale' in source_parser:
csv_properties['data_locale'] = source_parser['locale']
fields = Fields(source['object']['fields'], **csv_properties)
if field_attributes:
source = r.update_source_fields(source, field_attributes, fields,
api, args.verbosity,
session_file)
if types:
source = r.update_source_fields(source, types, fields, api,
args.verbosity, session_file)
# End of source processing
# Starting dataset processing
if (training_set or args.source or (args.evaluate and test_set)):
# if resuming, try to extract args.dataset form log files
if resume:
resume, args.dataset = u.checkpoint(u.is_dataset_created, path,
debug=args.debug)
if not resume:
message = u.dated("Dataset not found. Resuming.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
# If we have a source but not dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.dataset and not args.model and not model_ids and
not args.no_dataset) or
(args.evaluate and args.test_set and not args.dataset)):
dataset_args = r.set_dataset_args(name, description, args, fields,
dataset_fields)
dataset = r.create_dataset(source, dataset_args, args, api,
path, session_file, log)
# If a dataset is provided, let's retrieve it.
elif args.dataset:
dataset = bigml.api.get_dataset_id(args.dataset)
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
dataset = r.get_dataset(dataset, api, args.verbosity, session_file)
if not csv_properties and 'locale' in dataset['object']:
csv_properties = {
'data_locale': dataset['object']['locale']}
fields = Fields(dataset['object']['fields'], **csv_properties)
if args.public_dataset:
r.publish_dataset(dataset, api, args, session_file)
#end of dataset processing
#start of model processing
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if (dataset and not args.model and not model_ids and not args.no_model):
model_ids = []
models = []
if resume:
resume, model_ids = u.checkpoint(u.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(name, description, args,
objective_field, fields, model_fields)
models, model_ids = r.create_models(dataset, models,
model_args, args, api,
path, session_file, log)
model = models[0]
# If a model is provided, we use it.
elif args.model:
model = args.model
model_ids = [model]
models = [model]
elif args.models or args.model_tag:
models = model_ids[:]
model = models[0]
# If we are going to predict we must retrieve the models
if model_ids and test_set and not args.evaluate:
models, model_ids = r.get_models(models, args, api, session_file)
model = models[0]
# We get the fields of the model if we haven't got
# them yet and update its public state if needed
if model and not args.evaluate and (test_set or args.black_box
or args.white_box):
if args.black_box or args.white_box:
model = r.publish_model(model, args, api, session_file)
models[0] = model
if not csv_properties:
csv_properties = {}
csv_properties.update(verbose=True)
if args.user_locale is None:
args.user_locale = model['object'].get('locale', None)
csv_properties.update(data_locale=args.user_locale)
if 'model_fields' in model['object']['model']:
model_fields = model['object']['model']['model_fields'].keys()
csv_properties.update(include=model_fields)
if 'missing_tokens' in model['object']['model']:
missing_tokens = model['object']['model']['missing_tokens']
else:
missing_tokens = MISSING_TOKENS
csv_properties.update(missing_tokens=missing_tokens)
objective_field = models[0]['object']['objective_fields']
if isinstance(objective_field, list):
objective_field = objective_field[0]
csv_properties.update(objective_field=objective_field)
fields = Fields(model['object']['model']['fields'], **csv_properties)
# end of model processing
# If predicting
if models and test_set and not args.evaluate:
predict(test_set, test_set_header, models, fields, output,
objective_field, args.remote, api, log,
args.max_batch_models, args.method, resume, args.tag,
args.verbosity, session_file, args.debug)
# When combine_votes flag is used, retrieve the predictions files saved
# in the comma separated list of directories and combine them
if votes_files:
model_id = re.sub(r'.*(model_[a-f0-9]{24})__predictions\.csv$',
r'\1', votes_files[0]).replace("_", "/")
try:
model = api.check_resource(model_id, api.get_model)
except ValueError, exception:
sys.exit("Failed to get model %s: %s" % (model_id, str(exception)))
local_model = Model(model)
message = u.dated("Combining votes.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
u.combine_votes(votes_files, local_model.to_prediction,
output, args.method)
