KSLCore/ksl.app.dist.config/FitConfiguration

FitConfiguration

@Serializable

data class FitConfiguration(val dataSource: DataSourceReference, val kind: DistributionKind = DistributionKind.CONTINUOUS, val estimatorIds: Set<String> = emptySet(), val scoringModelIds: Set<String> = emptySet(), val automaticShifting: Boolean = true, val rankingMethod: RankingMethod = RankingMethod.ORDINAL, val evaluationMethod: EvaluationMethod = EvaluationMethod.SCORING, val bootstrap: BootstrapConfig? = null, val includeStandardReport: Boolean = false)(source)

Serializable description of one distribution-fitting analysis: where the data comes from, what kind of distribution to fit, and which estimators and scoring models to use.

estimatorIds and scoringModelIds are catalog-stable IDs from the fitting catalog; an empty set means "use the catalog defaults for kind." scoringModelIds is ignored for DISCRETE configurations because PMF goodness-of-fit ranks by chi-squared p-value, not by MODA scoring.

automaticShifting applies only to the continuous path; it is ignored for DISCRETE configurations.

bootstrap is opt-in: a non-null BootstrapConfig requests engine-side bootstrap of the fitted parameters (summaries returned); null skips it. (The family-frequency bootstrap is a separate standalone analysis — see FittingRunner.familyFrequencyBootstrap — not a fit option.)

rankingMethod and evaluationMethod surface the engine's MODA-evaluation parameters (rank-tie handling and the recommendation criterion); both default to the engine defaults and apply to the continuous path only.

Constructors

FitConfiguration

constructor(dataSource: DataSourceReference, kind: DistributionKind = DistributionKind.CONTINUOUS, estimatorIds: Set<String> = emptySet(), scoringModelIds: Set<String> = emptySet(), automaticShifting: Boolean = true, rankingMethod: RankingMethod = RankingMethod.ORDINAL, evaluationMethod: EvaluationMethod = EvaluationMethod.SCORING, bootstrap: BootstrapConfig? = null, includeStandardReport: Boolean = false)