Struct GaussianProcess 

pub struct GaussianProcess {
    pub kernel: KernelType,
    pub params: KernelParams,
    /* private fields */
}

A Gaussian process regressor using a stationary kernel.

Training points are stored internally. After GaussianProcess::fit the GP can predict the posterior mean and variance at arbitrary test points.

Fields

kernel: KernelType

Kernel type.

params: KernelParams

Kernel hyper-parameters.

Implementations

impl GaussianProcess

pub fn new(kernel: KernelType, params: KernelParams) -> Self

Construct a new, unfitted GP with the given kernel and parameters.

pub fn fit(&mut self, x: Vec<Vec<f64>>, y: Vec<f64>) -> Result<(), String>

Fit the GP to the given training data.

Panics

Panics if x and y have different lengths, or if x is empty.

pub fn predict(&self, x_star: &[f64]) -> (f64, f64)

Predict the posterior (mean, variance) at test point x_star.

Returns (mean, variance).

Panics

Panics if the GP has not been fitted.

pub fn n_train(&self) -> usize

Return the number of training points.

pub fn is_fitted(&self) -> bool

Return whether the GP has been fitted.

Trait Implementations

impl Clone for GaussianProcess

fn clone(&self) -> GaussianProcess

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GaussianProcess

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

Formats the value using the given formatter.