Create a fitness class with custom_fit

custom_fit is designed to estimate the quality of a surrogate

custom_fit

Format

An R6Class generator object

Details

custom fit enable linear combination of several criteria

Fields

listComp

List of component

dcoeff

Coefficient of each term fitness

Methods

custom_fit$new(coeff, components)

Creates a new custom_fit. Used to construct an assesment of a quality of a surrogate model

get_val(surrogate_model)

It gives an evaluation of a surrogate model (object sm).

Examples

library(UP)
d              <- 2
X             <- expand.grid(x1=seq(0,1,length=5), x2=seq(0,1,length=4))
y                   <- apply(X, 1, branin)
upsm                <- UPSM$new(sm= krigingsm$new(), UP=UPClass$new(X,y,Scale =TRUE))
listCrit       <- list()
listCrit[[1]]  <- MSE$new()
listCrit[[2]]  <- Resampling_Error$new()
listCrit[[3]]  <- penlrm$new(X, y)
PPS            <- custom_fit$new(c(4,2,1), listCrit)
valPPS         <- PPS$get_val(upsm)
#> Warning: some row.names duplicated: 20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,43,45,48,49,51,53,55,58,59,60,61,62,63,64,65,66,67,68,71,72,73,75 --> row.names NOT used
print("PPS")
#> [1] "PPS"
print(valPPS)
#> [1] 187.1586