KernelPeriodic: R6 class for Periodic Kernels

In BKTR: Bayesian Kernelized Tensor Regression

R6 class for Periodic Kernels

Description

R6 class for Periodic Kernels

Super class

BKTR::Kernel -> KernelPeriodic

Public fields

lengthscale

The lengthscale parameter instance of the kernel

period_length

The period length parameter instance of the kernel

has_dist_matrix

Identify if the kernel has a distance matrix or not

name

The kernel's name

Methods

Public methods

• KernelPeriodic$new()

• KernelPeriodic$core_kernel_fn()

• KernelPeriodic$clone()

Inherited methods

• BKTR::Kernel$add_jitter_to_kernel()
• BKTR::Kernel$kernel_gen()
• BKTR::Kernel$plot()
• BKTR::Kernel$set_positions()

---

Method new()

Create a new KernelPeriodic object.

Usage

KernelPeriodic$new(
  lengthscale = KernelParameter$new(2),
  period_length = KernelParameter$new(2),
  kernel_variance = 1,
  jitter_value = NULL
)

Arguments

lengthscale

KernelParameter: The lengthscale parameter instance of the kernel

period_length

KernelParameter: The period length parameter instance of the kernel

kernel_variance

Numeric: The variance of the kernel

jitter_value

Numeric: The jitter value to add to the kernel matrix

Returns

A new KernelPeriodic object.

---

Method core_kernel_fn()

Method to compute the core kernel's covariance matrix

Usage

KernelPeriodic$core_kernel_fn()

Returns

The core kernel's covariance matrix

---

Method clone()

The objects of this class are cloneable with this method.

Usage

KernelPeriodic$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Create a new Periodic kernel
k_periodic <- KernelPeriodic$new()
# Set the kernel's positions
positions_df <- data.frame(x=c(-4, 0, 3), y=c(-2, 0, 2))
k_periodic$set_positions(positions_df)
# Generate the kernel's covariance matrix
k_periodic$kernel_gen()

BKTR documentation built on Sept. 12, 2024, 7:04 a.m.