REMLResult

class superglm.REMLResult(lambdas: dict[str, float], pirls_result: object, n_reml_iter: int, converged: bool, lambda_history: list[dict[str, float]] = <factory>, objective: float | None = None, reml_penalties: list | None = None, scop_states: dict | None = None, inner_iter_history: list[int] | None = None, objective_history: list[float] | None = None, curvature_source: str | None = None, termination_reason: str | None = None, scop_step_norms: list[dict[str, float]] | None = None, scop_fisher_fallbacks: int = 0, managed_cleanup_names: list[str] | None = None, managed_cleanup_frozen_names: list[str] | None = None, managed_cleanup_freeze_iter: int | None = None, managed_cleanup_active_history: list[list[str]] | None = None, managed_cleanup_frozen_history: list[list[str]] | None = None, tweedie_scale_data: object | None = None)

Bases: object

Result of REML smoothing parameter estimation.

Cleanup histories, when present, are accepted post-update snapshots from each outer REML iteration.