EvaluationConfig

class openstef_beam.evaluation.EvaluationConfig(**data: Any) → None

Bases: BaseConfig

Configuration for the evaluation pipeline.

Controls how predictions are filtered, grouped, and analyzed across different time dimensions.

Parameters:

data (Any)

available_ats: list[AvailableAt]

Time points when predictions become available relative to the target date

lead_times: list[LeadTime]

Time intervals between prediction generation and the target timestamp

windows: list[Window]

Time windows for rolling evaluation periods

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].