diff options
author | Johannes Ranke <jranke@uni-bremen.de> | 2014-10-15 01:24:40 +0200 |
---|---|---|
committer | Johannes Ranke <jranke@uni-bremen.de> | 2014-10-15 01:24:40 +0200 |
commit | 1c1106777a98119cf29c05c3f6e0de7077eb19b5 (patch) | |
tree | 67252068119f8b2aca8a3f8bb3882ddf15cb36e2 | |
parent | 63e0ce4866e63cc6a844bfcb7b98c98619dd2831 (diff) |
Switch to using the Port algorithm per default
Actually this only changes the order of entries in the dropbox, the
default is set in mkin::mkinfit().
-rw-r--r-- | inst/GUI/gmkin.R | 2 | ||||
-rw-r--r-- | vignettes/gmkin_manual.Rmd | 9 |
2 files changed, 6 insertions, 5 deletions
diff --git a/inst/GUI/gmkin.R b/inst/GUI/gmkin.R index 9ffe1c7..50cd4ed 100644 --- a/inst/GUI/gmkin.R +++ b/inst/GUI/gmkin.R @@ -906,7 +906,7 @@ f.gg.opts.reweight.tol <- gedit(1e-8, label = "reweight.tol", width = 20, cont = f.gg.opts)
f.gg.opts.reweight.max.iter <- gedit(10, label = "reweight.max.iter",
width = 20, cont = f.gg.opts)
-optimisation_methods <- c("Marq", "Port", "SANN")
+optimisation_methods <- c("Port", "Marq", "SANN")
f.gg.opts.method.modFit <- gcombobox(optimisation_methods, selected = 1,
label = "method.modFit",
width = 200,
diff --git a/vignettes/gmkin_manual.Rmd b/vignettes/gmkin_manual.Rmd index 39669e8..af8a3b8 100644 --- a/vignettes/gmkin_manual.Rmd +++ b/vignettes/gmkin_manual.Rmd @@ -329,10 +329,11 @@ refer to the `mkinfit` [documentation](http://kinfit.r-forge.r-project.org/mkin_ for more details. The drop down box "method.modFit" makes it possible to choose between the optimisation -algorithms "Marq" (the default Levenberg-Marquardt implementation from the R package -`minpack.lm`), "Port" (an alternative, also local optimisation algorithm) and -"SANN" (the simulated annealing method - robust but inefficient and without a -convergence criterion). +algorithms "Port" (the default in mkin versions > 0.9-33, a local optimisation +algorithm using a model/trust region approach), "Marq" (the former default in +mkin, a Levenberg-Marquardt variant from the R package `minpack.lm`), +and "SANN" (the simulated annealing method - robust but inefficient and without +a convergence criterion). Finally, the maximum number of iterations for the optimisation can be adapted using the "maxit.modFit" field. |