Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2020-07-20 | Require upcoming nlme version, remove anova.nlme.mmkin | Johannes Ranke | 1 | -29/+0 | |
The method is no longer necessary, now that Bug 17761 is fixed upstream https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17761 | |||||
2020-07-17 | mkinfit: Ignore unused components of state.ini | Johannes Ranke | 1 | -1/+2 | |
2020-07-15 | Improve tests | Johannes Ranke | 1 | -1/+1 | |
- Reduce significant digits for the objective function output in mkinfit(..., quiet = FALSE) as R and R-devel gave different output on my system - Add makefile target 'devtest' for testing with R-devel, in order to fix problems showing up with R-devel on Travis | |||||
2020-07-15 | Improve handling of (partially) failing fits | Johannes Ranke | 2 | -22/+29 | |
2020-07-15 | Use try() within mmkin | Johannes Ranke | 1 | -1/+1 | |
This keeps mmkin from stopping if one of the fits fails. Instead, a try-error is assigned to the respective position in the mmkin object. | |||||
2020-06-15 | Fix a bug, update for current vdiffr | Johannes Ranke | 2 | -83/+1 | |
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 | |||||
2020-05-29 | Improve handling of warnings, reorganize tests | Johannes Ranke | 3 | -14/+111 | |
2020-05-29 | Warn if standardized residuals are unlikely normal | Johannes Ranke | 2 | -46/+59 | |
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. | |||||
2020-05-28 | use_of_ff = "max" for shorthand models like "SFO" | Johannes Ranke | 1 | -1/+1 | |
2020-05-27 | Improve mkinmod docs | Johannes Ranke | 1 | -26/+39 | |
2020-05-26 | Use all cores per default, confint tolerance | Johannes Ranke | 5 | -50/+78 | |
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. | |||||
2020-05-25 | Tell travis where to find the required saemix version | Johannes Ranke | 1 | -6/+5 | |
2020-05-25 | First working version of saemix helper functions | Johannes Ranke | 1 | -0/+118 | |
saemix_data depends on a development version of saemix, see pull request saemixdevelopment/saemixextension#2 | |||||
2020-05-18 | Add comment | Johannes Ranke | 1 | -1/+2 | |
2020-05-15 | Improve docs | Johannes Ranke | 1 | -16/+14 | |
2020-05-15 | Use markdown links in mkinfit documentation | Johannes Ranke | 1 | -24/+24 | |
2020-05-14 | Update version number, better example formatting | Johannes Ranke | 1 | -13/+15 | |
2020-05-14 | Add a parms method for mmkin objects | Johannes Ranke | 1 | -2/+32 | |
2020-05-14 | Test markdown link, article update due to .rmd extension | Johannes Ranke | 1 | -1/+1 | |
2020-05-12 | Another documentation update | Johannes Ranke | 1 | -9/+8 | |
2020-05-12 | Update vignettes and docs | Johannes Ranke | 1 | -1/+0 | |
2020-05-12 | Improve documentation, now using a spell checker | Johannes Ranke | 6 | -6/+6 | |
2020-05-12 | Documentation improvements, rebuild static docs | Johannes Ranke | 2 | -4/+13 | |
2020-05-11 | Add analytical solution for DFOP-SFO | Johannes Ranke | 1 | -1/+23 | |
This is about twice as fast as deSolve compiled in the case of FOCUS D | |||||
2020-05-11 | Analytical solutions for all SFO variants | Johannes Ranke | 2 | -15/+48 | |
2020-05-11 | Reduce precision of traced parameters, formatting | Johannes Ranke | 1 | -2/+2 | |
2020-05-11 | Avoid merge() and data.frame() in cost function | Johannes Ranke | 5 | -28/+32 | |
also for deSolve and eigenvalue based solutions. This noticeably increases performance for these methods, see test.log and benchmark vignette. | |||||
2020-05-10 | Default to analytical for coupled models if available | Johannes Ranke | 2 | -3/+4 | |
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 | |||||
2020-05-09 | Avoid the call to merge for analytical solutions | Johannes Ranke | 6 | -72/+83 | |
This increases performance up to a factor of five! | |||||
2020-05-09 | Make mkinpredict consistently return a dataframe | Johannes Ranke | 1 | -16/+16 | |
2020-05-08 | Profiling suggests the merge in mkinfit is the bottleneck | Johannes Ranke | 1 | -0/+3 | |
2020-05-08 | We do not need the n.outtimes argument for mkinfit | Johannes Ranke | 1 | -10/+3 | |
As we set the tolerance for ode() appropriately | |||||
2020-05-08 | Avoid duplicate merge in tc error model fit | Johannes Ranke | 1 | -10/+7 | |
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. | |||||
2020-05-08 | Slight performance gain by reducing default n.outtimes | Johannes Ranke | 1 | -2/+2 | |
2020-05-08 | Analytical SFO_SFO about as fast as deSolve compiled | Johannes Ranke | 2 | -19/+52 | |
2020-05-07 | Another overhaul of analytical solutions | Johannes Ranke | 7 | -116/+74 | |
Still in preparation for analytical solutions of coupled models | |||||
2020-05-07 | Merge parent solutions to one file | Johannes Ranke | 2 | -2/+9 | |
- Combine R/*.solution.R into R/parent_solutions.R - Create a roxygen family of related functions - Reduce redundancy by using the inherit tag - Change the parent.0 argument to parent_0 to match the corresponding parameter name used in mkinfit | |||||
2020-05-07 | Static documentation rebuilt by pkgdown | Johannes Ranke | 7 | -186/+231 | |
2020-05-06 | Change implementation of analytical solutions | Johannes Ranke | 3 | -94/+104 | |
Preparing for symbolic solutions for more than one compound | |||||
2020-05-06 | Formatting, README update, color palette of R 4.x | Johannes Ranke | 1 | -32/+32 | |
2020-05-06 | Remove redundant comments | Johannes Ranke | 1 | -7/+0 | |
2020-04-22 | Support SFORB with formation fractions | Johannes Ranke | 2 | -33/+22 | |
2020-04-22 | Remove GPL header from test files | Johannes Ranke | 1 | -3/+3 | |
2020-04-18 | Fix NOTE, prepare for releasev0.9.49.10 | Johannes Ranke | 1 | -1/+1 | |
2020-04-18 | Avoid assignment to .GlobalEnv for CRAN | Johannes Ranke | 2 | -15/+32 | |
2020-04-17 | Fix summarizing old objects | Johannes Ranke | 1 | -6/+12 | |
2020-04-17 | Add AIC, BIC and log likelihood to summary.mkinfit | Johannes Ranke | 1 | -0/+7 | |
2020-04-16 | mean_degparms: Fix rownames in random effects | Johannes Ranke | 1 | -1/+1 | |
2020-04-15 | Adapt endpoint() to also work for nlme.mmkin objects | Johannes Ranke | 2 | -8/+36 | |
2020-04-15 | Include random effects in starting parameters | Johannes Ranke | 3 | -79/+131 | |
- mean_degparms() now optionally returns starting values for fixed and random effects, which makes it possible to obtain acceptable fits also in more difficult cases (with more parameters) - Fix the anova method, as it is currently not enough to inherit from lme: https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17761 - Show fit information, and per default also errmin information in plot.nlme.mmkin() - Examples for nlme.mmkin: Decrease tolerance and increase the number of iterations in the PNLS step in order to be able to fit FOMC-SFO and DFOP-SFO |