def local_prediction(deepnets, test_reader, output, args, exclude=None):
"""Get local deepnet and issue prediction
"""
kwargs = {"full": True}
if args.operating_point_:
kwargs.update({"operating_point": args.operating_point_})
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0], api=args.retrieve_api_)
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(input_data_dict, **kwargs)
write_prediction(prediction_info, output, args.prediction_info,
input_data, exclude)
def local_prediction(deepnets, test_reader, output, args,
exclude=None):
"""Get local deepnet and issue prediction
"""
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0],
api=args.retrieve_api_)
test_set_header = test_reader.has_headers()
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(
input_data_dict, by_name=test_set_header)
write_prediction(prediction_info, output,
args.prediction_info, input_data, exclude)
def local_prediction(deepnets, test_reader, output, args,
exclude=None):
"""Get local deepnet and issue prediction
"""
kwargs = {"full": True}
if args.operating_point_:
kwargs.update({"operating_point": args.operating_point_})
# Only one deepnet at present
local_deepnet = Deepnet(deepnets[0],
api=args.retrieve_api_)
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_deepnet.predict(
input_data_dict, **kwargs)
write_prediction(prediction_info, output,
args.prediction_info, input_data, exclude)
"YEAR": 1,
"DATE": 1,
"Index_": 1,
"ACCNUM": 1,
"X": 1,
"Y": 1,
"AUTOMOBILE": "yes",
"MOTORCYCLE": "yes",
"CYCLIST": "yes",
"STREET1": "ave",
"STREET2": "ave",
"DRIVACT": "Driving Properly",
"MANOEUVER": "Going Ahead",
"DRIVCOND": "Normal",
"FATAL_NO": 1,
"VEHTYPE": "automobile",
"INITDIR": "West",
"DATE.hour": 1,
"DATE.day-of-month": 1,
"DATE.day-of-week": 1,
"DATE.year": 1,
"DATE.month": 1
}
deepnet.predict(input_data, full=True)
#
# input_data: dict for the input values
# (e.g. {"petal length": 1, "sepal length": 3})
# full: if set to True, the output will be a dictionary that includes all the
# available information about the prediction. The attributes vary depending
# on the ensemble type. Please check:
# https://bigml.readthedocs.io/en/latest/#local-deepnet-predictions
