DataSaveCallback#

class openstef_models.workflows.callbacks.DataSaveCallback(**data: Any) → None[source]

Bases: BaseConfig, ForecastingCallback

Saves intermediate datasets to parquet files during workflow execution.

Toggle individual outputs via the boolean fields. All paths use workflow.run_name as an identifier in the filename.

Parameters:

data (Any)

cache_dir: Path
save_training_data: bool
save_prepared_data: bool
save_predict_data: bool
save_forecast: bool
save_contributions: bool
model_post_init(context: Any) → None[source]

Override this method to perform additional initialization after __init__ and model_construct. This is useful if you want to do some validation that requires the entire model to be initialized.

Parameters:

context (Any)

Return type:

None

on_fit_start(context: WorkflowContext[CustomForecastingWorkflow], data: VersionedTimeSeriesDataset | TimeSeriesDataset) → None[source]

Called before model fitting begins.

Use this hook for pre-training validation, data preprocessing, or setting up training monitoring.

Parameters:

  • context (WorkflowContext[CustomForecastingWorkflow]) – The workflow context performing the fitting.

  • data (VersionedTimeSeriesDataset | TimeSeriesDataset) – Training dataset being used for fitting.

  • context

  • data

Return type:

None

on_fit_end(context: WorkflowContext[CustomForecastingWorkflow], result: ModelFitResult) → None[source]

Called after model fitting completes successfully.

Use this hook for post-training validation, model evaluation, saving training metrics, or triggering downstream processes.

Parameters:

  • context (WorkflowContext[CustomForecastingWorkflow]) – The workflow context that completed fitting.

  • result (ModelFitResult) – Result of the fitting process.

  • context

  • result

Return type:

None

on_predict_end(context: WorkflowContext[CustomForecastingWorkflow], data: VersionedTimeSeriesDataset | TimeSeriesDataset, result: ForecastDataset) → None[source]

Called after prediction generation completes successfully.

Use this hook for forecast validation, saving predictions, calculating metrics, or triggering downstream processes.

Parameters:
Return type:

None

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': False, 'extra': 'ignore', 'protected_namespaces': ()}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].