aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2020-06-15Use current devel version of vdiffr on TravisJohannes Ranke1-1/+3
2020-06-15Fix a bug, update for current vdiffrJohannes Ranke7-118/+17
Vignette FOCUS_L failed as I had introduced a bug in the handling of warnings. Current vdiffr only runs visual tests if R < 4.1.0, skipping r-devel for now, see https://github.com/r-lib/vdiffr/commit/630a29d013361fd63fea242f531e2db6aef37919
2020-05-29Improve handling of warnings, reorganize testsJohannes Ranke14-166/+354
2020-05-29Warn if standardized residuals are unlikely normalJohannes Ranke14-152/+131
This revealed a bug in the data returned in mkinfit$data in the case of the d_3 algorithm, which also affected the residual plot - the data from the direct fitting was not returned even if this was the better method.
2020-05-28use_of_ff = "max" for shorthand models like "SFO"Johannes Ranke9-33/+35
2020-05-27Improve mkinmod docsJohannes Ranke4-85/+135
2020-05-27Change dev version label to info colorJohannes Ranke26-94/+95
instead of the orange danger color.
2020-05-27Advertise docs of the dev versionJohannes Ranke2-13/+14
2020-05-27Add docs generated using released version 0.9.52Johannes Ranke63-1348/+660
2020-05-27Create up to date pkgdown docs in development modeJohannes Ranke187-1/+24660
2020-05-26Use all cores per default, confint toleranceJohannes Ranke29-405/+466
Also, use more intelligent starting values for the variance of the random effects for saemix. While this does not appear to speed up the convergence, it shows where this variance is greatly reduced by using mixed-effects models as opposed to the separate independent fits.
2020-05-26Use upstream saemix for travisJohannes Ranke1-1/+1
The necessary change has been merged
2020-05-25Tell travis where to really find the saemix version...Johannes Ranke1-1/+1
2020-05-25Tell travis where to find the required saemix versionJohannes Ranke5-14/+14
2020-05-25First working version of saemix helper functionsJohannes Ranke20-26/+694
saemix_data depends on a development version of saemix, see pull request saemixdevelopment/saemixextension#2
2020-05-18Add commentJohannes Ranke1-1/+2
2020-05-15Improve docsJohannes Ranke2-23/+15
2020-05-15Use markdown links in mkinfit documentationJohannes Ranke4-95/+97
2020-05-14Update version number, better example formattingJohannes Ranke11-38/+35
2020-05-14Add a parms method for mmkin objectsJohannes Ranke7-8/+143
2020-05-14Test markdown link, article update due to .rmd extensionJohannes Ranke15-79/+98
2020-05-13Further formatting improvement of benchmark vignetteJohannes Ranke13-672/+631
Also, use .rmd extension instead of .Rmd for vignettes.
2020-05-12Another documentation updateJohannes Ranke4-43/+39
2020-05-12Update pkgdownJohannes Ranke3-31/+166
2020-05-12Improve formatting of benchmark vignetteJohannes Ranke3-39/+182
2020-05-12Add a link to the benchmark vignette to the docsJohannes Ranke8-1/+21
2020-05-12Update vignettes and docsJohannes Ranke100-1662/+1767
2020-05-12Update .Rbuildignorev0.9.50.2Johannes Ranke2-2/+1
2020-05-12Rerun tests and checks, CRAN commentsJohannes Ranke6-15/+13
2020-05-12Improve documentation, now using a spell checkerJohannes Ranke36-148/+370
2020-05-12Address solaris platform dependence revealed on CRANJohannes Ranke1-1/+2
2020-05-12Documentation improvements, rebuild static docsJohannes Ranke86-1102/+1165
2020-05-11Release to CRANv0.9.50.1Johannes Ranke4-4/+8
2020-05-11Merge branch 'master' of kolab.jrwb.de:mkinJohannes Ranke0-0/+0
2020-05-11Add analytical solution for DFOP-SFOJohannes Ranke17-30/+88
This is about twice as fast as deSolve compiled in the case of FOCUS D
2020-05-11Add analytical solution for DFOP-SFOJohannes Ranke6-11/+65
This is about twice as fast as deSolve compiled with FOCUS D
2020-05-11Analytical solutions for all SFO variantsJohannes Ranke8-73/+128
2020-05-11Don't run visual tests on r-devel for nowJohannes Ranke4-16/+29
https://github.com/r-lib/vdiffr/issues/86
2020-05-11Reduce precision of traced parameters, formattingJohannes Ranke2-123/+123
2020-05-11Avoid merge() and data.frame() in cost functionJohannes Ranke36-715/+799
also for deSolve and eigenvalue based solutions. This noticeably increases performance for these methods, see test.log and benchmark vignette.
2020-05-10Default to analytical for coupled models if availableJohannes Ranke8-157/+150
This revealed that transforming rates is necessary for fitting the analytical solution of the SFO-SFO model to the FOCUS D dataset. Benchmarks show that fitting coupled models with deSolve got a bit slower through the latest changes
2020-05-09Avoid the call to merge for analytical solutionsJohannes Ranke14-112/+135
This increases performance up to a factor of five!
2020-05-09Make mkinpredict consistently return a dataframeJohannes Ranke1-16/+16
2020-05-08Profiling suggests the merge in mkinfit is the bottleneckJohannes Ranke1-0/+3
2020-05-08We do not need the n.outtimes argument for mkinfitJohannes Ranke2-19/+12
As we set the tolerance for ode() appropriately
2020-05-08Avoid duplicate merge in tc error model fitJohannes Ranke2-21/+18
This increases the performance in the complete test suite by about 20 secs from 120 to around 100 secs. I tried improving merge speed by using data.table on another branch, but this did not give a noticeable performance gain.
2020-05-08Slight performance gain by reducing default n.outtimesJohannes Ranke3-18/+18
2020-05-08Roxygenize, adapt testsJohannes Ranke9-114/+128
2020-05-08Analytical SFO_SFO about as fast as deSolve compiledJohannes Ranke2-19/+52
2020-05-07Don't use binary version of covrJohannes Ranke1-2/+0
in an attempt to circumvent outdated apt repositories for r-api-35

Contact - Imprint