aboutsummaryrefslogtreecommitdiff
path: root/vignettes
AgeCommit message (Collapse)AuthorFilesLines
2023-02-17Update benchmark results for 7950XJohannes Ranke10-123/+208
2023-02-17Rethink versioning and remove 7950X benchmarksJohannes Ranke2-0/+0
I will add benchmark data for 1.2.0, 1.2.2 and 1.2.3 for better comparison
2023-02-17Finish adapting to upcoming deSolveJohannes Ranke7-149/+217
2023-02-17Commit prebuilt vignettes from desktopJohannes Ranke3-0/+0
2023-02-17Merge remote-tracking branch 'origin/main' into faster_lsodaJohannes Ranke1-1/+1
2023-02-17Fix path, build target for prebuilt pdf vignettesJohannes Ranke1-1/+1
2023-02-13WIP adapting to new deSolve with faster lsodaJohannes Ranke2-16/+83
2023-02-13Merge branch 'main' into custom_lsoda_callJohannes Ranke27-566/+3259
2023-01-28Update saem benchmark with new CPUJohannes Ranke1-0/+0
2023-01-09Prebuilt PDF vignettes, summary_listingJohannes Ranke26-499/+3293
2022-12-06Some parplot improvementsJohannes Ranke2-67/+53
llquant argument, improved legend text, tests
2022-11-24Start online docs of the development versionJohannes Ranke2-0/+0
2022-11-17Complete update of online docs for v1.2.0Johannes Ranke2-0/+0
2022-11-16Update online docsJohannes Ranke1-0/+0
2022-11-16We get about 25% performance gainJohannes Ranke5-15/+137
with the custom lsoda call, avoiding repeated getNativeSymbolInfo calls. It's just that we should not be calling foreign functions from different packages, because the may change without notice. Using getNativeSymbolInfo for "call_lsoda" avoids the CRAN note, and a similar call could probably be used for "unlock_solver", avoiding the NOTE in checks for cran, but we should not do this in a CRAN package.
2022-11-15Import saemix for easier profiling, update online docsJohannes Ranke6-134/+13
2022-11-14Update online docsJohannes Ranke2-0/+0
2022-11-14Start benchmark vignette for saem fitsJohannes Ranke4-0/+2281
2022-11-14Comment on an errorJohannes Ranke1-1/+1
I will not correct the error in order to keep the benchmarks consistent
2022-11-01Update online docsJohannes Ranke1-0/+0
2022-10-28Rename parhist to parplot and make it genericJohannes Ranke1-3/+3
That parhist name was not the brightest idea, as it does not show histograms.
2022-10-26Really test anova output, test covariatesJohannes Ranke1-36/+0
2022-10-26Update multistart example code and vignetteJohannes Ranke3-22/+97
2022-09-28Update vignette and static docsJohannes Ranke3-2/+2
2022-09-28Fix handling of multistart fits with failuresJohannes Ranke3-26/+0
2022-09-19Improve parhist and llhistJohannes Ranke3-11/+15
In particular, adapt the display of parameter boxplots for saem fits using mkin transformations to the way used for saem fits using saemix transformations, i.e. always show parameters on the natural scale, and normalised them by dividing by the median from the multiple runs.
2022-09-16Add llhist to the multistart vignetteJohannes Ranke2-0/+14
2022-09-16Improve multistart documentation, bugfixJohannes Ranke3-0/+512
- Split out llhist and parhist documentation - Add example code for multistart - Create a multistart vignette, because the example code fails when run by pkgdown - Fix multistart for the case of mkin transformations in the saem fit
2022-09-16Improve docs and update pkgdownJohannes Ranke1-0/+0
2022-09-16Diagnostic plots for multistart methodJohannes Ranke1-72/+79
2022-08-10Change dev branch used for docs, update static docsJohannes Ranke1-0/+0
2022-07-22Update static docsJohannes Ranke1-0/+0
2022-07-14Improve readability of benchmark code shown in vignetteJohannes Ranke3-29/+44
2022-07-12Tests before releasev1.1.1Johannes Ranke1-112/+0
2022-07-12Rerun benchmarks on desktop computerJohannes Ranke4-13/+162
2022-07-08Store DLL info in mkinmod objects for performanceJohannes Ranke6-314/+83
Thanks to Tomas Kalibera for his analysis of the problem on the r-package-devel mailing list and for the suggestion on how to fix it. See the current benchmark vignette for the new data on mkin 1.1.1 with R 4.2.1, with unprecedented performance.
2022-07-01Sensitivity of AIC values in DMTA vignette to BLAS versionJohannes Ranke9-2/+2209
2022-07-01Rerun benchmarks with R 4.2.1 and openblas-serialJohannes Ranke2-11/+11
After confirming that lapack versus atlas versus openblas results are quite similar, and therefore not responsible for the differences between R 4.1.3 and R 4.2.1
2022-07-01Update benchmark article in online docsJohannes Ranke1-0/+0
2022-07-01Add benchmarks on laptop with R 4.1.3 and 4.2.1Johannes Ranke3-46/+75
2022-07-01Add R version to data in benchmark vignetteJohannes Ranke5-15/+2342
2022-06-30Merge branch 'dmta_vignette'Johannes Ranke1-1/+1
2022-06-30Remove stray sentence from vignette, update docsJohannes Ranke1-1/+1
2022-05-18Remove outdated comment in FOCUS L vignette, update docsJohannes Ranke6-4088/+80
This also adds the first benchmark results obtained on my laptop system
2022-03-16Use saemix in help page, typo in vignetteJohannes Ranke1-1/+1
2022-03-07Remove nlmixr interface for release of mkin 1.1.0Johannes Ranke2-267/+134
I am postponing my attempts to get the nlmixr interface to CRAN, given some problems with nlmixr using R-devel under Windows, see https://github.com/nlmixrdevelopment/nlmixr/issues/596 and https://github.com/r-hub/rhub/issues/512, which is fixed by the removal of nlmixr from the testsuite. For the tests to be more platform independent, the biphasic mixed effects models test dataset was defined in a way that fitting should be more robust (less ill-defined).
2022-03-02Make tests more platform independent, update docsJohannes Ranke6-27/+28
2022-02-28Improve dimethenamid vignetteJohannes Ranke3-241/+126
2022-02-09Adapt saemix interface to saemix 3.0 on CRANJohannes Ranke4-25/+25
2022-01-11Update the dimethenamid vignette with current saemixJohannes Ranke14-162/+153
Convergence is faster with this version (@ecomets mentioned that there was a bugfix lately that could lead to faster convergence). However, if I use too many iterations (i.e. 10 000 as in the last version of this vignette), I get an error in solving omega.teta during later iterations, apparently due to overparameterisation of the DFOP model in this case.

Contact - Imprint