mod binomial;
mod gaussian;
mod linked;
mod multivariate;
pub use binomial::Binomial;
pub use gaussian::Gaussian;
pub use linked::LinkedDatafit;
pub use multivariate::MultivariateGaussian;
pub(crate) use multivariate::StackedGaussian;
use crate::FitError;
pub trait Datafit {
type Error;
fn value(&self, predictor: &[f64]) -> Result<f64, Self::Error>;
}
pub trait DifferentiableDatafit: Datafit<Error = FitError> {
fn n_obs(&self) -> usize;
fn fits_intercept(&self) -> bool;
fn gradient(&self, predictor: &[f64], output: &mut [f64]) -> Result<(), FitError>;
}
pub trait SmoothDatafit: DifferentiableDatafit {
fn gap_safe(&self) -> Option<&dyn crate::GapSafeDatafit> {
None
}
}
pub trait DiagonalHessianDatafit: DifferentiableDatafit {
fn hessian_diagonal(&self, predictor: &[f64], output: &mut [f64]) -> Result<(), FitError>;
}
pub trait QuadraticModelDatafit: DifferentiableDatafit {
fn working_curvature(&self, predictor: &[f64], output: &mut [f64]) -> Result<(), FitError>;
fn initial_intercept(&self) -> Result<f64, FitError> {
Ok(0.0)
}
fn valid_predictor(&self, _predictor: &[f64]) -> bool {
true
}
}
impl<D: DiagonalHessianDatafit + ?Sized> DiagonalHessianDatafit for Box<D> {
fn hessian_diagonal(&self, predictor: &[f64], output: &mut [f64]) -> Result<(), FitError> {
(**self).hessian_diagonal(predictor, output)
}
}
impl<D: QuadraticModelDatafit + ?Sized> QuadraticModelDatafit for Box<D> {
fn working_curvature(&self, predictor: &[f64], output: &mut [f64]) -> Result<(), FitError> {
(**self).working_curvature(predictor, output)
}
fn initial_intercept(&self) -> Result<f64, FitError> {
(**self).initial_intercept()
}
fn valid_predictor(&self, predictor: &[f64]) -> bool {
(**self).valid_predictor(predictor)
}
}