Function generic_saliency 

pub fn generic_saliency(
    model: &dyn FpcPredictor,
    data: &FdMatrix,
    scalar_covariates: Option<&FdMatrix>,
    n_samples: usize,
    seed: u64,
) -> Result<FunctionalSaliencyResult, FdarError>

Generic functional saliency maps via SHAP-weighted rotation.

Lifts FPC-level attributions to the function domain.

Errors

Returns FdarError::InvalidDimension if data has zero rows or its column count does not match the model. Returns FdarError::InvalidParameter if the model has zero components or n_samples is zero (propagated from generic_shap_values).