register_GA: Register a Genetic Algorithm Seriation Method

In seriation: Infrastructure for Ordering Objects Using Seriation

Register a Genetic Algorithm Seriation Method

Description

Register a GA-based seriation metaheuristic for use with seriate().

Usage

register_GA()

gaperm_mixedMutation(ismProb = 0.8)

Arguments

ismProb

probability to use GA::gaperm_ismMutation() (inversion) versus GA::gaperm_simMutation() (simple insertion).

Details

Registers the method "GA" for seriate(). This method can be used to optimize any criterion in package seriation.

The GA uses by default the ordered cross-over (OX) operator. For mutation, the GA uses a mixture of simple insertion and simple inversion operators. This mixed operator is created using seriation::gaperm_mixedMutation(ismProb = .8), where ismProb is the probability that the simple insertion mutation operator is used. See package GA for a description of other available cross-over and mutation operators for permutations. The appropriate operator functions in GA start with gaperm_.

We warm start the GA using "suggestions" given by several heuristics. Set "suggestions" to NA to start with a purely random initial population.

See Example section for available control parameters.

Note: Package GA needs to be installed.

Value

Nothing.

Author(s)

Michael Hahsler

References

Luca Scrucca (2013): GA: A Package for Genetic Algorithms in R. Journal of Statistical Software, 53(4), 1–37. URL \Sexpr[results=rd]{tools:::Rd_expr_doi("10.18637/jss.v053.i04")}.

See Also

Other seriation: register_DendSer(), register_optics(), register_smacof(), register_tsne(), register_umap(), registry_for_seriaiton_methods, seriate(), seriate_best()

Examples

## Not run: 
register_GA()
get_seriation_method("dist", "GA")

data(SupremeCourt)
d <- as.dist(SupremeCourt)

## optimize for linear seriation criterion (LS)
o <- seriate(d, "GA", criterion = "LS", verbose = TRUE)
pimage(d, o)

## Note that by default the algorithm is already seeded with a LS heuristic.
## This run is no warm start (no suggestions) and increase run to 100
o <- seriate(d, "GA", criterion = "LS", suggestions = NA, run = 100,
  verbose = TRUE)
pimage(d, o)

o <- seriate(d, "GA", criterion = "LS", suggestions = NA, run = 100,
  verbose = TRUE,  )

pimage(d, o)

## End(Not run)

seriation documentation built on Sept. 11, 2024, 7:33 p.m.