Struct CrossValidation 

pub struct CrossValidation {
    pub number_of_folds: i64,
    pub stratified: bool,
    pub random_seed: i64,
    pub scheme_name: String,
    pub description: String,
}

Partition-based scheme for estimating generalization performance.

Fields

number_of_folds: i64

Number of folds.

stratified: bool

Whether folds are stratified.

random_seed: i64

Random seed.

scheme_name: String

Unique name identifying a resampling scheme.

description: String

Free-text description.

Implementations

impl CrossValidation

pub fn run( &self, n: usize, fit_score: impl FnMut(&[usize], &[usize]) -> f64, ) -> Result<CvScores>

Runs k-fold cross-validation using this scheme’s own configuration.

Reads the fold count from number_of_folds and seeds the deterministic PRNG from random_seed, then delegates to cross_validate. The i64 seed is reinterpreted to u64 bit-for-bit via i64::cast_unsigned (not a numeric as cast, which the style.rs guard bans), so a positive seed maps to the same magnitude. This makes the parameter struct itself executable against the numerics.

Arguments

• n — number of observations to partition into folds.
• fit_score — invoked once per fold as fit_score(train_idx, test_idx), returning that fold’s score.

Returns

The aggregated CvScores over the configured number of folds.

Errors

• Error::InvalidInput when number_of_folds is negative or unrepresentable as usize, or when the resolved fold count is < 2 (matching StratifiedCrossValidation::folds).
• Error::InsufficientData when the fold count exceeds n.

Examples

use stats_claw::resampling::CrossValidation;

let cv = CrossValidation { number_of_folds: 5, random_seed: 42, ..Default::default() };
let scores = cv.run(20, |_train, _test| 1.0)?;
assert_eq!(scores.fold_scores().len(), 5);
// Every fold scored 1.0, so the mean is 1.0 and the spread is zero.
assert!((scores.mean() - 1.0).abs() < 1e-12);
assert!(scores.std_error().abs() < 1e-12);

Trait Implementations

impl Clone for CrossValidation

fn clone(&self) -> CrossValidation

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CrossValidation

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for CrossValidation

fn default() -> CrossValidation

Returns the “default value” for a type.