def save(
self, station_availability_algorithm: StationAvailabilityAlgorithm
) -> None:
station_id = station_availability_algorithm.station_id()
self._storage_manager.create_storage_location(self._model_storage_path)
with open(self._model_filename(station_id), "wb") as file:
self._serializer.dump(station_availability_algorithm.model(), file)
station_availability_algorithm.training_data_set().to_pickle(
self._data_training_set_filename(station_id))
def test_it_can_override_an_existing_one(self) -> None:
station_id = uuid.uuid4()
first = StationAvailabilityAlgorithm(
station_id, DataFrame(['data_1', 'frame_1', 'test_1']), Booster())
self._repository.save(first)
override = StationAvailabilityAlgorithm(
station_id, DataFrame(['data_2', 'frame_2', 'test_2']), Booster())
self._repository.save(override)
self.assertEqual(self._repository.find_by_station_id(station_id),
override)
def test_it_can_not_find_one_by_station_id_if_it_does_not_exist(
self) -> None:
station_availability_algorithm = StationAvailabilityAlgorithm(
uuid.uuid4(), DataFrame(['data', 'frame', 'test']), Booster())
self._repository.save(station_availability_algorithm)
self.assertIsNone(self._repository.find_by_station_id(uuid.uuid4()))
def test_it_can_find_one_by_station_id(self) -> None:
station_id = uuid.uuid4()
station_availability_algorithm = StationAvailabilityAlgorithm(
station_id, DataFrame(['data', 'frame', 'test']), Booster())
self._repository.save(station_availability_algorithm)
self.assertEqual(self._repository.find_by_station_id(station_id),
station_availability_algorithm)
def find_by_station_id(
self, station_id: uuid) -> Optional[StationAvailabilityAlgorithm]:
try:
with open(self._model_filename(station_id), "rb") as file:
model = self._serializer.load(file)
data_frame_train = pandas.read_pickle(
self._data_training_set_filename(station_id))
return StationAvailabilityAlgorithm(station_id, data_frame_train,
model)
except FileNotFoundError:
return None
def handle(self, command: CreateStationAvailabilityAlgorithmCommand) -> None:
station_id = command.station_id()
records = self._query.query(station_id)
if not records:
raise EmptyValueForDataTrainingError.with_station_id(station_id)
station_data = StationDataTraining(records, self._query.FIELDS, self._query.FEATURE_FIELD,
self._query.INDEX_FIELD, command.frequency(), command.start_date())
training_data_set = station_data.data_frame()
model = self._data_trainer.train(training_data_set)
self._repository.save(StationAvailabilityAlgorithm(command.station_id(), training_data_set, model))