Struct DeepGaussianProcessRegressor 

pub struct DeepGaussianProcessRegressor<S = Untrained> { /* private fields */ }

Deep Gaussian Process Regressor

Implements a deep GP with multiple layers, where each layer is a sparse GP using inducing points for computational efficiency.

Implementations

impl DeepGaussianProcessRegressor<Untrained>

pub fn new() -> Self

Create a new Deep GP regressor

pub fn builder() -> DeepGaussianProcessRegressorBuilder

Create a builder for configuring the Deep GP

pub fn add_layer(self, kernel: Box<dyn Kernel>, n_inducing: usize) -> Self

Add a layer to the Deep GP

pub fn with_learning_rate(self, learning_rate: f64) -> Self

Set the learning rate for variational optimization

pub fn with_max_epochs(self, max_epochs: usize) -> Self

Set the maximum number of training epochs

pub fn with_convergence_threshold(self, threshold: f64) -> Self

Set the convergence threshold

pub fn with_jitter(self, jitter: f64) -> Self

Set the jitter for numerical stability

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

Set random seed for reproducibility

pub fn fit( self, x_train: &Array2<f64>, y_train: &Array1<f64>, ) -> SklResult<DeepGaussianProcessRegressor<Trained>>

Fit the Deep GP to training data

impl DeepGaussianProcessRegressor<Trained>

pub fn predict( &self, x_test: &Array2<f64>, ) -> SklResult<(Array1<f64>, Array1<f64>)>

Make predictions using the trained Deep GP

pub fn num_layers(&self) -> usize

Get the number of layers in the Deep GP

pub fn log_likelihood(&self) -> f64

Get the log likelihood of the trained model

pub fn predict_layer( &self, x_test: &Array2<f64>, layer_idx: usize, ) -> SklResult<(Array2<f64>, Array2<f64>)>

Get predictions from a specific layer

pub fn get_inducing_points(&self, layer_idx: usize) -> SklResult<&Array2<f64>>

Get the inducing points for a specific layer

pub fn get_variational_params( &self, layer_idx: usize, ) -> SklResult<(&Array1<f64>, &Array1<f64>)>

Get the variational parameters for a specific layer

Trait Implementations

impl<S: Clone> Clone for DeepGaussianProcessRegressor<S>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<S: Debug> Debug for DeepGaussianProcessRegressor<S>

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

Formats the value using the given formatter.

impl Default for DeepGaussianProcessRegressor<Untrained>

fn default() -> Self

Returns the “default value” for a type.

impl<S> Estimator for DeepGaussianProcessRegressor<S>

type Config = DeepGPConfig

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 Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for DeepGaussianProcessRegressor<Untrained>

type Fitted = DeepGaussianProcessRegressor<Trained>

The fitted model type

fn fit(self, x: &Array2<f64>, y: &Array1<f64>) -> SklResult<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 Predict<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 1]>>> for DeepGaussianProcessRegressor<Trained>

fn predict(&self, x: &Array2<f64>) -> SklResult<Array1<f64>>

Make predictions on the provided data

fn predict_with_uncertainty( &self, x: &X, ) -> Result<(Output, UncertaintyMeasure), SklearsError>

Make predictions with confidence intervals