buildLOESS: Build LOESS Model

In SPOT: Sequential Parameter Optimization Toolbox

Build LOESS Model

Description

Build an interpolation model using the loess function. Essentially a SPOT-style interface to that function.

Usage

buildLOESS(x, y, control = list())

Arguments

x	design matrix (sample locations), rows for each sample, columns for each variable.
y	vector of observations at x
control	named list, with the options for the model building procedure loess. These will be passed to loess as arguments. Please refrain from setting the formula or data arguments as these will be supplied by the interface, based on x and y.

Value

returns an object of class spotLOESS.

See Also

predict.spotLOESS

Examples

## Create a test function: branin
braninFunction <- function (x) {	
	(x[2]  - 5.1/(4 * pi^2) * (x[1] ^2) + 5/pi * x[1]  - 6)^2 + 
10 * (1 - 1/(8 * pi)) * cos(x[1] ) + 10
}
## Create design points
set.seed(1)
x <- cbind(runif(40)*15-5,runif(40)*15)
## Compute observations at design points
y <- as.matrix(apply(x,1,braninFunction))
## Create model with default settings
fit <- buildLOESS(x,y)
fit
## Predict new point
predict(fit,cbind(1,2))
## True value at location
braninFunction(c(1,2))
## Change model control
fit <- buildLOESS(x,y,control=list(parametric=c(TRUE,FALSE)))
fit

SPOT documentation built on June 26, 2022, 1:06 a.m.