Struct GridSearchClassifier 

pub struct GridSearchClassifier { /* private fields */ }

Grid search over classifiers, scored by the log loss of the held-out folds (probabilities clipped to [1e-15, 1 − 1e-15]).

Implementations

impl GridSearchClassifier

pub fn new(candidates: Vec<Box<dyn Classifier>>) -> Self

pub fn cv(self, cv: usize) -> Self

Number of (stratified) cross-validation folds (default 5).

pub fn best_index(&self) -> Option<usize>

pub fn cv_scores(&self) -> &[f64]

Cross-validated log loss of every candidate.

Trait Implementations

impl Classifier for GridSearchClassifier

fn fit(&mut self, x: ArrayView2<'_, f64>, y: ArrayView1<'_, f64>) -> Result<()>

fn fit_weighted( &mut self, x: ArrayView2<'_, f64>, y: ArrayView1<'_, f64>, w: ArrayView1<'_, f64>, ) -> Result<()>

Fit minimising a w-weighted loss (needed by Lplr’s instrument score). The default reports that weights are unsupported.

fn predict_proba(&self, x: ArrayView2<'_, f64>) -> Result<Array1<f64>>

fn fresh(&self) -> Box<dyn Classifier>

impl Clone for GridSearchClassifier

fn clone(&self) -> Self

An unfitted copy with the same candidates.

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

Performs copy-assignment from source.