Methodology that combines feature selection, model tuning, and parsimonious model selection with Genetic Algorithms (GA) proposed in {Martinez-de-Pison} (2015) <doi:10.1016/j.asoc.2015.06.012>. To this objective, a novel GA selection procedure is introduced based on separate cost and complexity evaluations.
| Version: |
0.9.4 |
| Depends: |
R (≥ 3.0), methods, foreach, iterators |
| Imports: |
stats, graphics, grDevices, utils |
| Suggests: |
parallel, doParallel, doRNG (≥ 1.6), knitr (≥ 1.8), lhs, MASS, caret, mlbench, e1071, nnet, kernlab |
| Published: |
2019-12-03 |
| Author: |
F.J. Martinez-de-Pison [aut, cre] |
| Maintainer: |
F.J. Martinez-de-Pison <fjmartin at unirioja.es> |
| License: |
GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| URL: |
https://github.com/jpison/GAparsimony |
| NeedsCompilation: |
no |
| Materials: |
NEWS |
| CRAN checks: |
GAparsimony results |