def local_prediction(models, test_reader, output, args, exclude=None):
"""Get local model and issue prediction
"""
# Only one model at present
local_model = SupervisedModel(models[0], api=args.retrieve_api_)
kwargs = {"full": True}
if has_value(args.operating_point_):
kwargs.update({"operating_point": args.operating_point_})
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_model.predict(input_data_dict, **kwargs)
write_prediction(prediction_info, output, args.prediction_info,
input_data, exclude)
def fusion_dispatcher(args=sys.argv[1:]):
"""Parses command line and calls the different processing functions
"""
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
clear_log_files(LOG_FILES)
settings = {}
settings.update(SETTINGS)
if '--evaluate' in args:
settings.update({"default_output": "evaluation"})
command_args, _, api, session_file, _ = get_context(args, settings)
# Selects the action to perform
if a.has_value(command_args, "fusion_models_") or a.has_test(command_args):
compute_output(api, command_args)
u.log_message("_" * 80 + "\n", log_file=session_file)
def fusion_dispatcher(args=sys.argv[1:]):
"""Parses command line and calls the different processing functions
"""
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
clear_log_files(LOG_FILES)
settings = {}
settings.update(SETTINGS)
if '--evaluate' in args:
settings.update({"default_output": "evaluation"})
command_args, command, api, session_file, resume = get_context(args,
settings)
# Selects the action to perform
if a.has_value(command_args, "fusion_models_") or a.has_test(command_args):
compute_output(api, command_args)
u.log_message("_" * 80 + "\n", log_file=session_file)
def local_prediction(models, test_reader, output, args,
exclude=None):
"""Get local model and issue prediction
"""
# Only one model at present
try:
bigml.api.get_fusion_id(models[0])
local_model = Fusion(models[0], api=args.retrieve_api_)
except ValueError:
local_model = SupervisedModel(models[0],
api=args.retrieve_api_)
kwargs = {"full": True}
if has_value(args, "operating_point_"):
kwargs.update({"operating_point": args.operating_point_})
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_model.predict(
input_data_dict, **kwargs)
write_prediction(prediction_info, output,
args.prediction_info, input_data, exclude)