Struct FittedLinearProbe 

pub struct FittedLinearProbe {
    pub weights: Vec<f64>,
    pub in_dim: usize,
    pub n_classes: usize,
    pub n_iter: Vec<usize>,
    pub converged: Vec<bool>,
}

A fitted one-vs-all logistic regression model.

Fields

weights: Vec<f64>

Weight matrix stored row-major [n_classes × (in_dim + 1)]. The last column of each row is the absorbed bias term.

in_dim: usize

Feature dimensionality (before bias augmentation).

n_classes: usize

Number of classes.

n_iter: Vec<usize>

IRLS iterations taken per binary sub-problem.

converged: Vec<bool>

Whether each binary sub-problem converged within max_iter.

Trait Implementations

impl Clone for FittedLinearProbe

fn clone(&self) -> FittedLinearProbe

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FittedLinearProbe

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

Formats the value using the given formatter.