plot.moead

S3 method for plotting moead objects (the output of moead()).

# S3 method for moead
plot(
  x,
  ...,
  useArchive = FALSE,
  feasible.only = TRUE,
  viol.threshold = 1e-06,
  nondominated.only = TRUE,
  plot.weights = FALSE,
  which.objectives = NULL,
  suppress.pause = FALSE,
  color.by.obj = 1
)

Arguments

x

list object of class moead (generated by moead())

...

other parameters to be passed down to specific plotting functions (currently unused)

useArchive

logical flag to use information from x$Archive. Only used if x$Archive is not NULL.

feasible.only

logical flag to use only feasible points in the plots.

viol.threshold

threshold of tolerated constraint violation, used to determine feasibility if feasible.only == TRUE.

nondominated.only

logical flag to use only nondominated points in the plots.

plot.weights

logical flag to plot the weight vectors for 2 and 3-objective problems.

which.objectives

integer vector of which objectives to plot. Defaults to NULL (use all objectives)

suppress.pause

logical flag to prevent pause messages from being show after every image. Defaults to FALSE (show pause messages)

color.by.obj

integer, determines which objective is used as the basis for coloring the parallel coordinates plot.

References

F. Campelo, L.S. Batista, C. Aranha (2020): The MOEADr Package: A Component-Based Framework for Multiobjective Evolutionary Algorithms Based on Decomposition. Journal of Statistical Software doi:10.18637/jss.v092.i06

Examples

problem.1 <- list(name = "example_problem",
                  xmin = rep(-1,30),
                  xmax = rep(1,30),
                  m    = 2)
out <- moead(preset    = preset_moead("original2"),
             problem   = problem.1,
             stopcrit  = list(list(name = "maxiter",
                                   maxiter = 100)),
             showpars  = list(show.iters = "dots",
                              showevery  = 10))
#> 
#> MOEA/D running: ..........
plot(out, suppress.pause = TRUE)