irace (version 3.5)

psRace: psRace

Description

psRace performs a postselection race a set of configurations.

Usage

psRace(
  iraceLogFile = NULL,
  iraceResults = NULL,
  conf.ids = NULL,
  postselection = NULL,
  max.experiments = NULL,
  elites = FALSE,
  seed = 1234567
)

Value

If iraceLogFile is NULL, it returns a list with the following elements:

configurations

Configurations used in the race.

instances

A matrix with the instances used in the experiments. First column has the instances ids from iraceResults$scenario$instances, second column the seed assigned to the instance.

maxExperiments

Maximum number of experiments set for the race.

experiments

A matrix with the results of the experiments (columns are configurations, rows are instances).

elites

Best configurations found in the experiments.

If iraceLogFile is provided this list object will be saved in iraceResults$psrace.log.

Arguments

iraceLogFile

NULL Log file created by irace, this file must contain the iraceResults object.

iraceResults

NULL Object created by irace and saved in scenario$logFile.

conf.ids

NULL IDs of the configurations in iraceResults$allConfigurations to be used for ablation. If NULL, the elites argument will be used.

postselection

NULL Percentage of the maxExperiments provided in the scenario to be used in the race.

max.experiments

NULL Number of experiments available for the race. If NULL budget for the race is set by the parameter scenario$postselection, which defines the percentage of the total budget of irace (iraceResults$scenario$maxExperiments or iraceResults$scenario$maxTime/iraceResults$state$timeEstimate) to use for the postselection.

elites

FALSE Flag for selecting configurations. If FALSE, the best configurations of each iteration are used for the race. If TRUE, the elite configurtions of each iteration are used for the race.

seed

1234567 Numerical value to use as seed for the random number generation.

Author

Leslie Pérez Cáceres

Examples

if (FALSE) {
  # Execute the postselection automatically after irace
  scenario <- readScenario(filename="scenario.txt")
  parameters <- readParameters("parameters.txt")
  # Use 10% of the total budget
  scenario$postselection <- 0.1
  irace(scenario=scenario, parameters=parameters)
  # Execute the postselection after the execution of \pkg{irace}.
  psRace(iraceLogFile="irace.Rdata", max.experiments=120)
}