FitFinalForecasterUnit
Fit the model a run keeps, with the best parameters, on the whole series.
The metrics come from the backtest; the kept model is the one that forecasts the future, so it has seen everything up to the last step: train, validation and test (D4). It is a fresh instance built from the parameters, not the backtest's.
The grid goes with it (time_grid): its frequency and last date are
what turn a forecast's steps into dates when the model is asked to
predict (D5). A run that reads exogenous variables fits it on the final
cut, which final.pkl made from the whole series, the same fit that
transforms the future when predicting.
Methods
execute(self, ctx: DashAI.back.units.context.ExecutionContext) -> None
FitFinalForecasterUnitDo the unit's work, reading from and writing to the context.
Parameters
- ctx : ExecutionContext
- The shared execution context.
get_credential(self, name: str)
ConfigObjectResolve a registered credential component by name.
Parameters
- name : str
- Credential component class name (e.g. "HuggingFaceCredential").
Returns
- BaseCredential
- An instance of the requested credential component.
get_schema(cls) -> dict
ConfigObjectGenerates the component related Json Schema.
Returns
- dict
- Dictionary representing the Json Schema of the component.
validate(self, ctx: DashAI.back.units.context.ExecutionContext) -> None
BaseUnitCheck preconditions without executing the unit.
Parameters
- ctx : ExecutionContext
- The shared execution context.
validate_and_transform(self, raw_data: dict) -> dict
ConfigObjectIt takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.
Parameters
- raw_data : dict
- A dictionary with the data provided by the user to initialize the model.
Returns
- dict
- A validated dictionary with the necessary objects.