Container around a data.table::data.table which stores all performed function calls of the Objective.

Technical details

The data is stored in a private .data field that contains a data.table::data.table which logs all performed function calls of the Objective. This data.table::data.table is accessed with the public $data() method. New values can be added with the $add_evals() method. This however is usually done through the evaluation of the OptimInstance by the Optimizer.

Public fields

search_space

(paradox::ParamSet)
Search space of objective.

codomain

(paradox::ParamSet)
Codomain of objective function.

start_time

(POSIXct).

check_values

(logical(1))

Active bindings

n_evals

(integer(1))
Number of evaluations stored in the archive.

n_batch

(integer(1))
Number of batches stored in the archive.

cols_x

(character()). Column names of search space parameters.

cols_y

(character()). Column names of codomain parameters.

Methods

Public methods


Method new()

Creates a new instance of this R6 class.

Usage

Archive$new(search_space, codomain, check_values = TRUE)

Arguments

search_space

(paradox::ParamSet)
Specifies the search space for the Optimizer. The paradox::ParamSet describes either a subset of the domain of the Objective or it describes a set of parameters together with a trafo function that transforms values from the search space to values of the domain. Depending on the context, this value defaults to the domain of the objective.

codomain

(paradox::ParamSet)
Specifies codomain of function. Most importantly the tags of each output "Parameter" define whether it should be minimized or maximized. The default is to minimize each component.

check_values

(logical(1))
Should x-values that are added to the archive be checked for validity? Search space that is logged into archive.


Method add_evals()

Adds function evaluations to the archive table.

Usage

Archive$add_evals(xdt, xss_trafoed, ydt)

Arguments

xdt

(data.table::data.table())
Set of untransformed points / points from the search space. One point per row, e.g. data.table(x1 = c(1, 3), x2 = c(2, 4)). Column names have to match ids of the search_space. However, xdt can contain additional columns.

xss_trafoed

(list())
Transformed point(s) in the domain space.

ydt

(data.table::data.table())
Optimal outcome.


Method best()

Returns the best scoring evaluation. For single-crit optimization, the solution that minimizes / maximizes the objective function. For multi-crit optimization, the Pareto set / front.

Usage

Archive$best(m = NULL)

Arguments

m

(integer())
Take only batches m into account. Default is all batches.

Returns

data.table::data.table().


Method data()

Returns a data.table::data.table which contains all performed Objective function calls.

Usage

Archive$data(unnest = NULL)

Arguments

unnest

(character())
Set of column names for columns to unnest via mlr3misc::unnest(). Unnested columns are stored in separate columns instead of list-columns.

Returns

data.table::data.table().


Method format()

Helper for print outputs.

Usage

Archive$format()


Method print()

Printer.

Usage

Archive$print()

Arguments

...

(ignored).


Method clear()

Clear all evaluation results from archive.

Usage

Archive$clear()


Method clone()

The objects of this class are cloneable with this method.

Usage

Archive$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.