def metric_calibration_status(y_true, y_pred):
"""
Metric for the `calibration_status`.
:param y_true:
Reference calibration_status.
:type y_true: list
:param y_pred:
Predicted calibration_status.
:type y_pred: list
:return:
Error.
:rtype: list
"""
return [v[0] for v in y_pred]
#: Metrics to compare outputs with targets.
metrics = sh.map_list(targets, mae, metric_calibration_status)
#: Upper score limits to raise the warnings.
up_limit = {'identified_co2_emissions': 0.5}
#: Prediction model.
# noinspection PyProtectedMember
dsp = sh.Blueprint(
copy.deepcopy(_fc).add_data('kco2_wltp_correction_factor'), inputs,
outputs, models)._set_cls(define_sub_model)
eng = calculate_gear_box_speeds_in(gears, vel, vsr, sv)
return calculate_error_coefficients(t_gears, gears, t_eng, eng, vel,
sv)
def _sort(v):
e = sh.selector(t_e, v[0], output_type='list')
return (e[0], -e[1], -e[2]), v[1]
# Sort by error.
rank = sorted(
((_err(k, m), k, m)
for k, m in sorted(sh.selector(at_m, data, allow_miss=True).items())),
key=_sort)
if rank:
data['at_scores'] = collections.OrderedDict((k, e) for e, k, m in rank)
e, k, m = rank[0]
mdl[sgs], mdl[k] = k, m
log.debug(
'at_gear_shifting_model: %s with mean_absolute_error %.3f '
'[RPM], accuracy_score %.3f, and correlation_coefficient '
'%.3f.', k, *sh.selector(t_e, e, output_type='list'))
return mdl
#: Prediction model.
# noinspection PyProtectedMember
dsp = sh.Blueprint(_at_gear, inputs, outputs,
models)._set_cls(define_sub_model)
#: Upper score limits to raise the warnings.
up_limit = sh.map_list(targets, 40)
def select_models(keys, data):
"""
Select models from data.
:param keys:
Model keys.
:type keys: list
:param data:
Cycle data.
:type data: dict
:return:
Models.
:rtype: dict
"""
mdl = sh.selector(keys, data, allow_miss=True)
if 'tyre_dynamic_rolling_coefficient' in mdl:
mdl.pop('r_dynamic', None)
return mdl
#: Prediction model.
# noinspection PyProtectedMember
dsp = sh.Blueprint(_physical, inputs, outputs,
models)._set_cls(define_sub_model)
#: Inputs required to run the model.
inputs = [
'drive_battery_electric_powers', 'times', 'motive_powers', 'accelerations',
'on_engine', 'starter_currents', 'initial_service_battery_state_of_charge'
]
#: Relevant outputs of the model.
outputs = [
'alternator_currents', 'service_battery_currents',
'drive_battery_currents', 'dcdc_converter_currents',
'service_battery_state_of_charges', 'drive_battery_state_of_charges'
]
#: Targets to compare the outputs of the model.
targets = outputs
#: Weights coefficients to compute the model score.
weights = sh.map_list(targets, 1, 1, 1, 1, 0, 0)
#: Metrics to compare outputs with targets.
metrics = sh.map_list(targets, *([co2_utl.mae] * 6))
#: Upper score limits to raise the warnings.
up_limit = dict.fromkeys(('alternator_currents', 'service_battery_currents',
'drive_battery_currents', 'dcdc_converter_currents'),
60)
#: Prediction model.
# noinspection PyProtectedMember
dsp = sh.Blueprint(_electrics, inputs, outputs,
models)._set_cls(define_sub_model)
ext=('.dill', )))
dsp.add_function(function=parse_excel_file,
inputs=['input_file_name', 'input_file'],
outputs=['raw_data'],
input_domain=check_file_format)
if _dice is not None:
_out, _inp = ['base', 'meta', 'dice'], [
'input_file_name', 'input_file', 'encryption_keys',
'encryption_keys_passwords'
]
# noinspection PyProtectedMember
dsp.add_function(function=sh.Blueprint(
sh.SubDispatchFunction(_dice,
function_id='load_ta_file',
inputs=_inp[1:],
outputs=_out))._set_cls(sh.add_args),
description='Load inputs from .co2mpas.ta file.',
inputs=_inp,
outputs=['raw_data'],
filters=[functools.partial(sh.map_list, [_out])],
input_domain=functools.partial(check_file_format,
ext=('.co2mpas.ta', )))
_out, _inp = ['data', 'dice'], ['input_file_name', 'input_file']
# noinspection PyProtectedMember
dsp.add_function(function=sh.Blueprint(
sh.SubDispatchFunction(_dice, inputs=_inp[1:],
outputs=_out))._set_cls(sh.add_args),
function_id='load_co2mpas_file',
:param y_pred:
Predicted engine speed vector [RPM].
:type y_pred: numpy.array
:param after_treatment_warm_up_phases:
Phases when engine speed is affected by the after treatment warm up [-].
:type after_treatment_warm_up_phases: numpy.array
:return:
Error.
:rtype: float
"""
b = after_treatment_warm_up_phases
if b.any():
from co2mpas.utils import mae
return float(mae(y_true[b], y_pred[b]))
else:
return 0
#: Metrics to compare outputs with targets.
metrics = sh.map_list(targets, metric_after_treatment_speed_model)
#: Upper score limits to raise the warnings.
up_limit = sh.map_list(targets, 160)
#: Prediction model.
# noinspection PyProtectedMember
dsp = sh.Blueprint(_after_treat, inputs, outputs,
models)._set_cls(define_sub_model)
'timestamp'
],
outputs=['output_file_name'],
input_domain=check_first_arg_false)
if _dice is not None:
dsp.add_data('co2mpas_version', __version__)
_out, _inp = ['output_file_name', 'output_file'], [
'excel_input', 'base', 'start_time', 'excel_output', 'output_folder',
'report', 'encryption_keys', 'meta', 'sign_key', 'dice', 'timestamp',
'co2mpas_version'
]
# noinspection PyProtectedMember,PyTypeChecker
dsp.add_function(function=sh.Blueprint(
sh.SubDispatchFunction(_dice, inputs=_inp,
outputs=_out))._set_cls(sh.add_args),
function_id='write_ta_output',
description='Write ta output file.',
inputs=['type_approval_mode', 'input_file'] + _inp[1:],
outputs=_out,
input_domain=check_first_arg)
else:
dsp.add_data('base', description='Base data.')
dsp.add_data('excel_input', description='Excel input file.')
dsp.add_data('encryption_keys', description='Encryption keys for TA mode.')
dsp.add_data('meta', description='Meta data.')
dsp.add_data('sign_key', description='User signature key for TA mode.')
@sh.add_function(dsp)