def set_library_args(args, name=None):
"""Returns a library arguments dict
"""
if name is None:
name = args.name
library_args = set_basic_args(args, name)
if args.project_id is not None:
library_args.update({"project": args.project_id})
if args.imports is not None:
library_args.update({"imports": args.imports_})
update_attributes(library_args, args.json_args.get('library'))
return library_args
def set_script_args(args, name=None):
"""Returns a script arguments dict
"""
if name is None:
name = args.name
script_args = set_basic_args(args, name)
if args.project_id is not None:
script_args.update({"project": args.project_id})
if args.imports is not None:
script_args.update({"imports": args.imports_})
if args.parameters_ is not None:
script_args.update({"inputs": args.parameters_})
if args.declare_outputs_:
script_args.update({"outputs": args.declare_outputs_})
update_attributes(script_args, args.json_args.get('script'))
return script_args
def set_execution_args(args, name=None):
"""Returns an execution arguments dict
"""
if name is None:
name = args.name
execution_args = set_basic_args(args, name)
if args.project_id is not None:
execution_args.update({"project": args.project_id})
if args.arguments_:
execution_args.update({"inputs": args.arguments_})
if args.creation_defaults is not None:
execution_args.update({"creation_defaults": args.creation_defaults_})
if args.outputs_:
execution_args.update({"outputs": args.outputs_})
if args.input_maps_:
execution_args.update({"input_maps_": args.input_maps_})
update_attributes(execution_args, args.json_args.get('execution'))
return execution_args
def set_source_args(args,
name=None,
multi_label_data=None,
data_set_header=None,
fields=None):
"""Returns a source arguments dict
"""
if name is None:
name = args.name
source_args = set_basic_args(args, name)
if args.project_id is not None:
source_args.update({"project": args.project_id})
# if header is set, use it
if data_set_header is not None:
source_args.update({"source_parser": {"header": data_set_header}})
# If user has given an OS locale, try to add the locale used in bigml.com
if args.user_locale is not None:
source_locale = bigml_locale(args.user_locale)
if source_locale is None:
log_message("WARNING: %s locale equivalence not found."
" Using %s instead.\n" %
(args.user_locale, LOCALE_DEFAULT),
log_file=None,
console=True)
source_locale = LOCALE_DEFAULT
source_args.update({'source_parser': {}})
source_args["source_parser"].update({'locale': source_locale})
# If user has set a training separator, use it.
if args.training_separator is not None:
training_separator = decode2(args.training_separator,
encoding="string_escape")
source_args["source_parser"].update({'separator': training_separator})
# If uploading a multi-label file, add the user_metadata info needed to
# manage the multi-label fields
if (hasattr(args, 'multi_label') and args.multi_label
and multi_label_data is not None):
source_args.update(
{"user_metadata": {
"multi_label_data": multi_label_data
}})
# to update fields attributes or types you must have a previous fields
# structure (at update time)
if fields:
if args.field_attributes_:
update_attributes(source_args, {"fields": args.field_attributes_},
by_column=True,
fields=fields)
if args.types_:
update_attributes(source_args, {"fields": args.types_},
by_column=True,
fields=fields)
if args.import_fields:
fields_struct = fields.new_fields_structure(args.import_fields)
check_fields_struct(fields_struct, "source")
update_attributes(source_args, fields_struct)
if 'source' in args.json_args:
update_json_args(source_args, args.json_args.get('source'), fields)
return source_args
if args.node_threshold > 0:
ensemble_args.update(node_threshold=args.node_threshold)
if args.balance:
ensemble_args.update(balance_objective=True)
if args.weight_field:
try:
weight_field = fields.field_id(args.weight_field)
except ValueError, exc:
sys.exit(exc)
ensemble_args.update(weight_field=weight_field)
if args.objective_weights:
ensemble_args.update(objective_weights=args.objective_weights_json)
if args.random_candidates:
ensemble_args.update(random_candidates=args.random_candidates)
update_attributes(ensemble_args, args.json_args.get('model'))
ensemble_args = update_sample_parameters_args(ensemble_args, args)
ensemble_args["ensemble_sample"].update( \
{"rate": args.ensemble_sample_rate,
"replacement": args.ensemble_sample_replacement})
if 'ensemble' in args.json_args:
update_json_args(ensemble_args, args.json_args.get('ensemble'), fields)
return ensemble_args
def create_ensembles(datasets, ensemble_ids, ensemble_args, args,
number_of_ensembles=1,
dataset_args.update(json_filter=args.json_filter)
elif args.lisp_filter:
dataset_args.update(lisp_filter=args.lisp_filter)
if args.dataset_fields_ and fields is not None:
input_fields = configure_input_fields(fields, args.dataset_fields_)
dataset_args.update(input_fields=input_fields)
if (hasattr(args, 'multi_label') and args.multi_label
and multi_label_data is not None):
dataset_args.update(
user_metadata={'multi_label_data': multi_label_data})
if fields and args.import_fields:
fields_struct = fields.new_fields_structure(args.import_fields)
check_fields_struct(fields_struct, "dataset")
update_attributes(dataset_args, fields_struct)
if 'dataset' in args.json_args:
update_json_args(dataset_args, args.json_args.get('dataset'), fields)
return dataset_args
def set_dataset_split_args(name,
description,
args,
sample_rate=1,
out_of_bag=False,
multi_label_data=None):
"""Return dataset arguments dict to split a dataset
"""