Feature-Based Landscape Analysis of Continuous and Constrained Optimization Problems

Contains tools and features, which can be used for an Exploratory Landscape Analysis (ELA) of single-objective continuous optimization problems. Those features are able to quantify rather complex properties, such as the global structure, separability, etc., of the optimization problems.


News

flacco_1.3:

  • ela_local: -- made L-BFGS-B the default local optimizer -- use lower / upper bounds of the feature object as bounds of the L-BFGS-B -- local search algorithm used to maximize the problems (it's fixed now)
  • updated tests due to interface changes in testthat and checkmate

flacco_1.2:

  • converted assert* into test* - due to update of checkmate

flacco_1.1:

  • barrier trees: -- fixed a bug in feature computation: ratio of levels and nodes should only be taken for the maximum number of levels -- added number of leaves as a feature
  • replace createInitialDesign by createInitialSample as that name should be more intuitive and less misleading
  • createInitialSample stores the attributes lower and upper, which will be used by createFeatureObject

flacco_1.0:

  • initial release to CRAN

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("flacco")

1.7 by Pascal Kerschke, 3 months ago


https://github.com/kerschke/flacco


Report a bug at https://github.com/kerschke/flacco/issues


Browse source code at https://github.com/cran/flacco


Authors: Pascal Kerschke [aut, cre], Christian Hanster [ctb], Jan Dagefoerde [ctb]


Documentation:   PDF Manual  


BSD_2_clause + file LICENSE license


Imports BBmisc, checkmate, mlr

Suggests devtools, e1071, expm, ggplot2, lhs, MASS, Matrix, mda, mlbench, numDeriv, parallel, parallelMap, ParamHelpers, plotly, plyr, RANN, R.rsp, rpart, shape, shiny, smoof, testthat


See at CRAN