Struct LogisticRegressionCV 

pub struct LogisticRegressionCV { /* private fields */ }

L2-penalised logistic regression with C chosen by stratified K-fold cross-validation, as scikit-learn’s LogisticRegressionCV.

The candidates are n_cs values of C evenly spaced on a log scale between 1e-4 and 1e4 (or given explicitly). Each is fitted on every fold (warm-started along the path), the C with the best total score is chosen and the model is refitted on all the data. Folds follow scikit-learn’s StratifiedKFold without shuffling.

Implementations

impl LogisticRegressionCV

pub fn new() -> Self

Ten values of C from 1e-4 to 1e4, 5 folds, log-loss scoring.

pub fn n_cs(self, n: usize) -> Self

n values of C evenly spaced on a log scale from 1e-4 to 1e4.

pub fn cs(self, cs: Vec<f64>) -> Self

Explicit candidate values of C, tried in the given order.

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

pub fn scoring(self, scoring: CvScoring) -> Self

pub fn tol(self, tol: f64) -> Self

Newton tolerance, as LogisticRegression::tol.

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

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

The candidate values of C.

pub fn c(&self) -> Option<f64>

The chosen C.

pub fn scores(&self) -> Option<&Array2<f64>>

Score of every C on every fold (higher is better; the log loss enters negated), shape (cv, n_cs).

pub fn coef(&self) -> Option<&Array1<f64>>

pub fn intercept(&self) -> f64

Trait Implementations

impl Classifier for LogisticRegressionCV

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

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

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

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.

impl Clone for LogisticRegressionCV

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LogisticRegressionCV

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

Formats the value using the given formatter.

impl Default for LogisticRegressionCV

fn default() -> Self

Returns the “default value” for a type.