Struct CustomKernelSampler 

pub struct CustomKernelSampler<K, State = Untrained>
where
    K: KernelFunction,
{
    pub kernel: K,
    pub n_components: usize,
    pub random_state: Option<u64>,
    /* private fields */
}

Custom kernel random feature generator

Generates random Fourier features for any custom kernel function that implements the KernelFunction trait. This provides a flexible framework for kernel approximation with user-defined kernels.

Parameters

• kernel - Custom kernel function implementing KernelFunction trait
• n_components - Number of random features to generate (default: 100)
• random_state - Random seed for reproducibility

Examples

use sklears_kernel_approximation::custom_kernel::{CustomKernelSampler, CustomRBFKernel};
use sklears_core::traits::{Transform, Fit, Untrained}
use scirs2_core::ndarray::array;

let X = array![[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]];
let kernel = CustomRBFKernel::new(0.1);

let sampler = CustomKernelSampler::new(kernel, 100);
let fitted_sampler = sampler.fit(&X, &()).unwrap();
let X_transformed = fitted_sampler.transform(&X).unwrap();
assert_eq!(X_transformed.shape(), &[3, 100]);

CustomKernelSampler

Fields

kernel: K

Custom kernel function

n_components: usize

Number of random features

random_state: Option<u64>

Random seed

Implementations

impl<K> CustomKernelSampler<K, Untrained>

where K: KernelFunction,

pub fn new(kernel: K, n_components: usize) -> Self

Create a new custom kernel sampler

pub fn random_state(self, seed: u64) -> Self

Set random state for reproducibility

impl<K> CustomKernelSampler<K, Trained>

where K: KernelFunction,

pub fn random_weights(&self) -> &Array2<Float>

Get the random weights

pub fn random_offset(&self) -> &Array1<Float>

Get the random offset

pub fn kernel_description(&self) -> String

Get the kernel description

pub fn exact_kernel_matrix( &self, x: &Array2<Float>, y: &Array2<Float>, ) -> Array2<Float>

Compute exact kernel matrix for comparison/evaluation

Trait Implementations

impl<K, State: Clone> Clone for CustomKernelSampler<K, State>

where K: KernelFunction + Clone,

fn clone(&self) -> CustomKernelSampler<K, State>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<K, State: Debug> Debug for CustomKernelSampler<K, State>

where K: KernelFunction + Debug,

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

Formats the value using the given formatter.

impl<K> Estimator for CustomKernelSampler<K, Untrained>

where K: KernelFunction,

type Config = ()

Configuration type for the estimator

type Error = SklearsError

Error type for the estimator

type Float = f64

The numeric type used by this estimator

fn config(&self) -> &Self::Config

Get estimator configuration

fn validate_config(&self) -> Result<(), SklearsError>

Validate estimator configuration with detailed error context

fn check_compatibility( &self, n_samples: usize, n_features: usize, ) -> Result<(), SklearsError>

Check if estimator is compatible with given data dimensions

fn metadata(&self) -> EstimatorMetadata

Get estimator metadata

impl<K> Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ()> for CustomKernelSampler<K, Untrained>

where K: KernelFunction,

type Fitted = CustomKernelSampler<K, Trained>

The fitted model type

fn fit(self, x: &Array2<Float>, _y: &()) -> Result<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl<K> Transform<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for CustomKernelSampler<K, Trained>

where K: KernelFunction,

fn transform(&self, x: &Array2<Float>) -> Result<Array2<Float>>

Transform the input data