mkin/tests/testthat/test_parent_only.R, branch C_analyticalFitting kinetic models to chemical degradation data (also on github)https://erac.jrwb.de/mkin/atom?h=C_analytical2019-10-21T10:11:34ZRefactor mkinfit, infrastructure work2019-10-21T10:11:34ZJohannes Rankejranke@uni-bremen.de2019-10-21T10:11:34Zurn:sha1:7624a2b8398b4ad665a3b0b622488e1893a5ee7c
mkinfit objects now include an ll() function to calculate the
log-likelihood. Part of the code was refactored, hopefully making it
easier to read and maintain. IRLS is currently the default algorithm for
the error model "obs", for no particular reason. This may be subject
to change when I get around to investigate.
Slow tests are now in a separate subdirectory and will probably
only be run by my own Makefile target.
Formatting of test logs is improved.
Roundtripping error model parameters works with a precision of 10% when
we use lots of replicates in the synthetic data (see slow tests). This
is not new in this commit, but as I think it is reasonable this
closes #7.
Fixes for last commit2019-02-25T20:18:11ZJohannes Rankejranke@uni-bremen.de2019-02-25T20:18:11Zurn:sha1:885ea2cd3392e57efff72e5094643917d6ba2be8Test AIC calculation2019-02-25T20:15:51ZJohannes Rankejranke@uni-bremen.de2019-02-25T20:15:51Zurn:sha1:a9285f356f92e45dfec43ab6ad06d65b1ffe08d1Skip more tests on CRAN2018-09-14T19:02:46ZJohannes Rankejranke@uni-bremen.de2018-09-14T19:02:46Zurn:sha1:587662437bce06ea202551048226b86cff0db187
Static documentation rebuilt by pkgdown
Skip some more tests on CRAN2018-09-14T16:25:17ZJohannes Rankejranke@uni-bremen.de2018-09-14T16:24:49Zurn:sha1:851f146e866817e48a7becf25b7d76f0ad45f1fe
Static documentation rebuilt by pkgdown
Only use 1 core to pass test on windows2017-07-21T19:47:04ZJohannes Rankejranke@uni-bremen.de2017-07-21T19:47:04Zurn:sha1:e621d0ea24081b3b5b3e324e8fd19422dd60e16fFix tests, try FOMC ill-defined again2017-07-21T14:16:27ZJohannes Rankejranke@uni-bremen.de2017-07-21T14:16:01Zurn:sha1:1623d0f0df92e2d4f44faa7a64a0b795e275b444Relax test tolerance for SFORB, FOCUS B and deSolve2015-05-15T09:45:12ZJohannes Rankejranke@uni-bremen.de2015-05-15T09:45:12Zurn:sha1:ded6e62ad7d1a4aa565a06f33964db0af8c7d78b
While this was OK on my local windows machine, the test failed on
winbuilder
Make FOMC test for FOCUS A robust towards non-convergence2015-05-15T09:03:43ZJohannes Rankejranke@uni-bremen.de2015-05-15T09:03:43Zurn:sha1:4fa48c8ef79d75c008fe5cbd0f57b3d96db0b888Skip testing FOMC with FOCUS A Windows2015-05-15T08:39:55ZJohannes Rankejranke@uni-bremen.de2015-05-15T08:39:55Zurn:sha1:25a9e7b1014d0b9bc956b45a5da61496a7b37ccf
Testing the package on winbuilder shows that the Port algorithm
does not converge on Windows with this combination, which is
not a problem as the FOMC model is not appropriate for the dataset
anyways.