Struct Matern32 

pub struct Matern32 {
    pub length_scale: f64,
    pub signal_variance: f64,
}

Matérn kernel with ν = 3/2

k(x, x’) = σ² (1 + √3 r / l) exp(-√3 r / l), where r = ||x - x’|| Once differentiable, smoother than Matérn 1/2.

Fields

length_scale: f64

signal_variance: f64

Implementations

impl Matern32

pub fn new(length_scale: f64, signal_variance: f64) -> Self

Trait Implementations

impl Clone for Matern32

fn clone(&self) -> Matern32

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Matern32

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

Formats the value using the given formatter.

impl Default for Matern32

fn default() -> Self

Returns the “default value” for a type.

impl Kernel for Matern32

fn compute(&self, x1: &ArrayView1<'_, f64>, x2: &ArrayView1<'_, f64>) -> f64

Compute covariance between two points

fn get_params(&self) -> Vec<f64>

Get kernel parameters (for optimization)

fn set_params(&mut self, params: &[f64])

Set kernel parameters

fn compute_matrix(&self, x: &Array2<f64>) -> Array2<f64>

Compute covariance matrix for a set of points

fn compute_cross_matrix( &self, x1: &Array2<f64>, x2: &Array2<f64>, ) -> Array2<f64>

Compute covariance matrix between two sets of points

fn n_params(&self) -> usize

Get number of parameters