Shrink a ParamSet towards a point. — shrink

Shrinks a paradox::ParamSet towards a point. Boundaries of numeric values are shrunk to an interval around the point of half of the previous length, while for discrete variables, a random (currently not chosen) level is dropped.

Note that for paradox::p_lgl()s the value to be shrunk around is set as the default value instead of dropping a level. Also, a tag shrunk is added.

Note that the returned paradox::ParamSet has lost all its original defaults, as they may have become infeasible.

x is always expected to contain the values on the scale of param_set, i.e. the untransformed values before a trafo is applied.

Usage

shrink_ps(param_set, x, check.feasible = FALSE)

Arguments

param_set: (paradox::ParamSet)
The paradox::ParamSet to be shrunk.
x: (data.table::data.table)
data.table::data.table with one row containing the point to shrink around.
check.feasible: (logical(1))
Should feasibility of the parameters be checked? If feasibility is not checked, and invalid values are present, no shrinking will be done. Default is FALSE.

Value

paradox::ParamSet

Examples

library(paradox)
library(data.table)
param_set = ps(
  x1 = p_dbl(lower = 0, upper = 10),
  x2 = p_int(lower = -10, upper = 10),
  x3 = p_fct(levels = c("a", "b", "c")),
  x4 = p_lgl()
)
x = data.table(x1 = 5, x2 = 0, x3 = "b", x4 = FALSE)
shrink_ps(param_set, x = x)
#> <ParamSet(4)>
#>        id    class lower upper nlevels        default  value
#>    <char>   <char> <num> <num>   <num>         <list> <list>
#> 1:     x1 ParamDbl   2.5   7.5     Inf <NoDefault[0]> [NULL]
#> 2:     x2 ParamInt  -5.0   5.0      11 <NoDefault[0]> [NULL]
#> 3:     x3 ParamFct    NA    NA       2 <NoDefault[0]> [NULL]
#> 4:     x4 ParamLgl    NA    NA       2          FALSE [NULL]