aggregation: Create a kriging adapter class for the objects codekm of...
In malekbs/UP: What the package does (short line)

Description Usage Format Details Fields Methods Examples

krigingsm is a kriging adapter. It makes the use of the universal distirbution easier

1	aggregation

An R6Class generator object

It construct a kriging model from the package DiceKriging and it inherits form the sm. The inheritance of the class sm is required when one want to use the universal distribution

numsm: : number of sub models
model_name: : "aggregation"
aggweights: : aggregation weights
fit: : fitness function used to tune the wieghts

krigingsm$new(x=NULL,y=NULL,parameters = NULL, type= "UK"): Creates a new krigingsm object.
train(): train the surrogate model.
predict(newdata): it predicts the new data.

library(UP)
d            <- 2;
n            <- 16
X    	      <- expand.grid(x1=s <- seq(0,1, length=5), x2=s)
Xtest	      <- expand.grid(x1=seq(0,1,length=5), x2=seq(0,1,length=4))
Y            <- apply(X, 1, branin)
sm = krigingsm$new()
sm$setDOE(X,Y)
sm$train() 
sm$predict(Xtest)