shrinkGPR (version 1.1.1)

plot.shrinkGPR_marg_samples_2D: Plot method for 2D marginal predictions from shrinkGPR

Description

Generates a 3D surface plot of 2D conditional predictive samples produced by gen_marginal_samples.

Usage

# S3 method for shrinkGPR_marg_samples_2D
plot(x, ...)

Value

A plotly plot object (interactive 3D surface). Can be further customized via pipes and plotly functions.

Arguments

x

An object of class "shrinkGPR_marg_samples_2D", typically returned by gen_marginal_samples when evaluating two covariates.

...

Additional arguments passed to add_surface for customizing the appearance of the surface plot (e.g., opacity, colorscale, showscale).

Author

Peter Knaus

Details

The function visualizes the posterior predictive mean across a 2D grid of evaluation points for two covariates. Interactive plotting is handled via the plotly package. Axis labels are automatically inferred from the object.

Note: The plotly package must be installed to use this function.

See Also

gen_marginal_samples, plot_ly, add_surface

Other plotting functions: plot.shrinkGPR(), plot.shrinkGPR_marg_samples_1D(), plot.shrinkTPR()

Examples

# \donttest{
# Simulate data
set.seed(123)
torch::torch_manual_seed(123)
n <- 100
x <- matrix(runif(n * 2), n, 2)
y <- sin(2 * pi * x[, 1]) * cos(2 * pi * x[, 2]) + rnorm(n, sd = 0.1)
data <- data.frame(y = y, x1 = x[, 1], x2 = x[, 2])

# Fit GPR model
res <- shrinkGPR(y ~ x1 + x2, data = data)

# Generate marginal predictions for x1 and x2 jointly
marginal_samps_both <- gen_marginal_samples(res, to_eval = c("x1", "x2"), nsamp = 100)

# Plot interactive surface
plot(marginal_samps_both)

# Customize surface appearance
plot(marginal_samps_both, opacity = 0.8, colorscale = "Magma")

# Customize further via plotly
p <- plot(marginal_samps_both, opacity = 0.8, colorscale = "Magma")

p |> plotly::layout(
  scene = list(
    xaxis = list(title = "Covariate 1"),
    yaxis = list(title = "Covariate 2"),
    zaxis = list(title = "Expected value")
  )
)
# }