9b50ea9 | Junpeng Lao | 16 June 2020, 08:07:17 UTC | Rename property name in NUTS to better reflect the computation | 16 June 2020, 09:22:02 UTC |
8f74fcb | Michael Osthege | 16 June 2020, 07:27:41 UTC | re-run almost all notebooks that use NUTS | 16 June 2020, 09:22:02 UTC |
fff0f94 | Junpeng Lao | 15 June 2020, 20:03:59 UTC | clean up | 16 June 2020, 09:22:02 UTC |
fca57d6 | Junpeng Lao | 15 June 2020, 19:57:45 UTC | add test | 16 June 2020, 09:22:02 UTC |
7a4d47c | Junpeng Lao | 15 June 2020, 19:52:12 UTC | move function to pymc3.math (2) | 16 June 2020, 09:22:02 UTC |
0ebedb0 | Junpeng Lao | 15 June 2020, 19:51:49 UTC | move function to pymc3.math | 16 June 2020, 09:22:02 UTC |
196d1fa | Junpeng Lao | 15 June 2020, 19:06:20 UTC | fix naming | 16 June 2020, 09:22:02 UTC |
ae6c1bb | Junpeng Lao | 15 June 2020, 18:59:58 UTC | Fix numerical issue in NUTS acceptance ratio computation Should reduce the frequency of getting "Mass matrix contains zeros on the diagonal" during warmup and fix a bunch of issue in https://github.com/pymc-devs/pymc3/issues/3959 | 16 June 2020, 09:22:02 UTC |
8d241cd | Michael Osthege | 13 June 2020, 16:58:09 UTC | repair yaml syntax (#3961) | 13 June 2020, 16:58:09 UTC |
2469ce5 | Michael Osthege | 13 June 2020, 15:08:15 UTC | Add release pipeline GitHub Action (#3954) * add long description content type * bump to 3.9.0 * add GitHub release pipeline definition * be conservative while waiting for PyPI * address TODOs to make merge-ready | 13 June 2020, 15:08:15 UTC |
8274b91 | Alexandre ANDORRA | 13 June 2020, 15:06:54 UTC | Update NBs prior to 3.9.0 release (#3955) * Re-run and fix many notebooks... Co-authored-by: Michael Osthege <m.osthege@fz-juelich.de> | 13 June 2020, 15:06:54 UTC |
cfa56a4 | Alexandre ANDORRA | 13 June 2020, 09:43:06 UTC | Add black_nbconvert and watermark to dev reqs (#3958) | 13 June 2020, 09:43:06 UTC |
f01c8e2 | Eelke Spaak | 13 June 2020, 09:42:46 UTC | distribution on new line in GraphViz node (#3957) * distribution on new line in GraphViz node * updating tests to check newline instead of space in graphviz graphs | 13 June 2020, 09:42:46 UTC |
bca5b88 | ljmartin | 11 June 2020, 19:20:57 UTC | changed ar1 logp to use ar1 precision instead of innovation precision (#3899) * changed ar1 logp to use ar1 precision instead of innovation precision * fixed tests for AR1 * making AR1 scipy test behave like pymc3 version * Update pymc3/distributions/timeseries.py Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com> * Update pymc3/distributions/timeseries.py Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com> * updated AR notebook to use new AR1 model * Fixed release notes * Black * Updated AR NB * Blackified AR NB Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com> Co-authored-by: AlexAndorra <andorra.alexandre@gmail.com> | 11 June 2020, 19:20:57 UTC |
7a50430 | Bill Engels | 10 June 2020, 23:01:14 UTC | Fix reparameterized gp.TP `chi2` variable name (#3945) * reparameterized TP chi2 parameter has unique name now * also fix TP chi2 name in tests * remove path that somehow got to top of file... | 10 June 2020, 23:01:14 UTC |
76f3a7b | Adrian Seyboldt | 10 June 2020, 18:31:08 UTC | Allow specification of dims instead of shape (#3551) * Allow specification of dims instead of shape * Add pm.TidyData * Create coords for pm.Data(ndarray) * empty commit to trigger CI * Apply suggestions from code review Co-authored-by: Alexandre ANDORRA <andorra.alexandre@gmail.com> * apply black formatting * address review comments & formatting * Add demonstration of named coordinates/dims * don't require dim names to be identifiers * sort imports * raise ShapeError instead of ValueError * formatting * robustify Dtype and ShapeError * Removed TidyData and refined dims and coords implementation * Changed name of kwarg export_dims and improved docstrings * Add link to ArviZ in docstrings * Removed TidyData from __all__ * Polished Data container NB * Fixed line break in data.py * Fix inference of coords for dataframes * Refined Data container NB * Updated getting started NB with new dims and coords features * Reran getting started NB * Blackified NBs * rerun with ArviZ branch * use np.shape to be compatible with tuples/lists * add tests for named coordinate handling * Extended tests for data container Co-authored-by: Michael Osthege <m.osthege@fz-juelich.de> Co-authored-by: Michael Osthege <michael.osthege@outlook.com> Co-authored-by: Alexandre ANDORRA <andorra.alexandre@gmail.com> | 10 June 2020, 18:31:08 UTC |
8a8beab | Michael Osthege | 09 June 2020, 15:33:30 UTC | remove unused import to fix pylint CI job (#3952) | 09 June 2020, 15:33:30 UTC |
380f7f0 | Michael Osthege | 09 June 2020, 13:29:54 UTC | take out the DEMetropolisZ warning (#3949) | 09 June 2020, 13:29:54 UTC |
dc574b7 | Osvaldo Martin | 09 June 2020, 08:55:30 UTC | improve ABC sampler (#3940) * Expand ABC features. * valueerror * update notebook * remove unused import update release notes * fix notebook style and change order params argument | 09 June 2020, 08:55:30 UTC |
c6bba80 | Michael Osthege | 09 June 2020, 07:40:37 UTC | Run some CI tests with arviz master (#3948) * run some tests with arviz master * change the job definition syntax * rename binder job | 09 June 2020, 07:40:37 UTC |
680dadd | Dan Foreman-Mackey | 04 June 2020, 17:30:06 UTC | Fixing HMC et al. tuning schedule to reset at the beginning of a chain even on 1 core (#3941) * fixing #3939 * fixing introduced bug in fulladapt quadpot | 04 June 2020, 17:30:06 UTC |
b6a88f0 | Ravin Kumar | 29 May 2020, 19:15:28 UTC | Remove unused communication methods (#3936) * Remove unused communication methods * Update GOVERNANCE.md Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com> Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com> | 29 May 2020, 19:15:28 UTC |
aafa00b | Michael Osthege | 28 May 2020, 18:26:50 UTC | return_inferencedata option for pm.sample (#3911) * mention arviz functions by name in warning * convert to InferenceData already in sample function + convert to InferenceData and save metadata to it already in sample() + pass idata instead of trace to convergence check, to avoid duplicate work + directly use arviz diagnostics instead of pymc3 aliases * fix refactoring bugs * fix indentation * add return_inferencedata option + set to None + defaults to False * Fix numpy docstring format. Replaced "<varname>: <type>" with "<varname> : <type>" per numpy guidelines. Fix spelling typo. * pass model to from_pymc3 because of deprecation warning * add test for return_inferencedata option * advise against keeping warmup draws in a MultiTrace * mention #3911 * pin to arviz 0.8.0 and address review feedback * rerun/update notebook to show inferencedata trace * fix typo * make all from_pymc3 accessible to the user * remove duplicate entry, and wording * address review feedback * update arviz to 0.8.1 because of bugfix * incorporate review feedback + more direct use of ArviZ + some wording things * use arviz plot_ppc * also ignore Visual Studio cache * fix warmup saving logic and test * require latest ArviZ patch * change warning to nuget users towards InferenceData * update ArviZ minimum version * address review feedback * start showing the FutureWarning about return_inferencedata in minor release >=3.10 * require arviz>=0.8.3 for latest bugfix Co-authored-by: rpgoldman <rpgoldman@goldman-tribe.org> | 28 May 2020, 18:26:50 UTC |
30d28f4 | Osvaldo Martin | 25 May 2020, 16:59:28 UTC | add n_draws and t_sampling report to smc (#3931) * add n_draws and t_sampling report to smc * add _n_tune * update release notes * resolve conflicts | 25 May 2020, 16:59:28 UTC |
1522492 | Oriol Abril | 23 May 2020, 16:33:47 UTC | get docs for stats and plots to link to ArviZ (#3927) * get docs for stats and plots to link to ArviZ * update release notes | 23 May 2020, 16:33:47 UTC |
9e8a20d | Luciano Paz | 20 May 2020, 09:15:23 UTC | Drop support for float128 outside of linux and mac (#3930) * Drop support for float128 outside of linux and mac * Improve release notes | 20 May 2020, 09:15:23 UTC |
1ed0478 | Alexandre ANDORRA | 18 May 2020, 15:08:53 UTC | Expand pm.Data capacities (#3925) * Initial changes to allow pymc3.Data() to support both int and float input data (previously all input data was coerced to float) WIP for #3813 * added exception for invalid dtype input to pandas_to_array * Refined implementation * Finished dtype conversion handling * Added SharedVariable option to getattr_value * Added dtype handling to set_data function * Added tests for pm.Data used for index variables * Added tests for using pm.data as RV input * Ran Black on data tests files * Added release note * Updated release notes * Updated code in light of Luciano's comments * Fixed implementation of integer checking * Simplified implementation of type checking * Corrected implementation for other uses of pandas_to_array Co-authored-by: hottwaj <jonathan.a.clarke@gmail.com> | 18 May 2020, 15:08:53 UTC |
7f307b9 | Luciano Paz | 15 May 2020, 22:02:18 UTC | Cap the values that Beta.random can generate. (#3924) * TST: Added test for the failing sampler * BUG: Make Beta.random to use the clipped random number generator * DOC: Added to release notes * Fix the PR link in the release notes * FIX: use scipy.stats and change ref_rand to point to clipped_beta_rvs * FIX: Use np.maximum and np.minimum to work with scalars and arrays | 15 May 2020, 22:02:18 UTC |
e47b98a | Thomas Wiecki | 13 May 2020, 01:34:48 UTC | Fix ODE NB. (#3887) * Fix ODE NB. * Rerun ODE NB. | 13 May 2020, 01:34:48 UTC |
effe5c4 | Tirth Patel | 12 May 2020, 15:11:24 UTC | small changes to speed up find_MAP (#3916) | 12 May 2020, 15:11:24 UTC |
ccc78cb | Tirth Patel | 12 May 2020, 15:10:34 UTC | MAINT: omit examples from coverage (#3920) * omit examples and tests in coverage * tests are already omited | 12 May 2020, 15:10:34 UTC |
3546f40 | Alexandre ANDORRA | 11 May 2020, 19:26:06 UTC | Replaced ignore-installed flag by force-reinstall (#3918) | 11 May 2020, 19:26:06 UTC |
e200ba5 | Alexandre ANDORRA | 11 May 2020, 18:53:29 UTC | Set start method to forkserver for MacOS (#3919) * Set start method to forkserver for MacOS * Polished up changes * Added release note | 11 May 2020, 18:53:29 UTC |
ad59074 | Michael Osthege | 10 May 2020, 16:38:46 UTC | fix & specify type and shapes for plot_gp_dist (#3913) * fix & specify type and shapes for plot_gp_dist * warn user about nan samples closes #3917 * test that UserWarning is triggered when some samples are nan | 10 May 2020, 16:38:46 UTC |
18f1e51 | Ahan M R | 05 May 2020, 11:53:52 UTC | Closes #3051 - logp numpy array input fixed (#3836) * Closes #3051 - logp numpy array input- fixed Converts 'int' type to <TensorType(int64,Scalar)> to parse value to `astype` and allows arguments to `logp(self,value)` when called with numpy array. * Closes #3051 - Allows numpy array input to logp Allows `logp(self,value)` to take `value` input of type numpy array without errors * fixes #3051 * Fixes #3051 * updated RELEASE-NOTES.md Added the deprecation of `sd` with `sigma` in newer version with DeprecationWarning on usage of `sd`. * directly use floatX * mention #3836 * move all deprecations into their own chapter, as done in previous releases * add regression test Co-authored-by: Michael Osthege <michael.osthege@outlook.com> | 05 May 2020, 11:53:52 UTC |
727b88a | Jonathan Sedar | 04 May 2020, 13:57:15 UTC | Update robust glm notebook (#3908) * updated the Hogg notebook * attempted to clarify the kwargs in sample() docstring describing how to pass kwargs to the steppers I believe this fixes https://github.com/pymc-devs/pymc3/issues/3197 I also noted this need for more clarity in my updated notebook in this PR `pymc3/docs/source/notebooks/GLM-robust-with-outlier-detection.ipynb` * Remove deprecated stuff (#3906) * remove file which is not used * remove deprecated code * repair tests and notebooks that used deprecated API * mention #3906 Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> * add deprecation warnings for old backends (#3902) * add deprecation warnings for old backends * mention backend deprecation #3902 * fix typo Co-authored-by: Colin <ColCarroll@users.noreply.github.com> Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> Co-authored-by: Colin <ColCarroll@users.noreply.github.com> * minor formatting to notebook and rework of docstring for sample function notebook: dropped all headings one level lower to comply with TOC logic, and very minor language edits sampling.py: clarifired language around single vs compoundstep * updated the Hogg notebook * attempted to clarify the kwargs in sample() docstring describing how to pass kwargs to the steppers I believe this fixes https://github.com/pymc-devs/pymc3/issues/3197 I also noted this need for more clarity in my updated notebook in this PR `pymc3/docs/source/notebooks/GLM-robust-with-outlier-detection.ipynb` * minor formatting to notebook and rework of docstring for sample function notebook: dropped all headings one level lower to comply with TOC logic, and very minor language edits sampling.py: clarifired language around single vs compoundstep * updates folowing AlexAndorra review: upgrade to arviz=0.7 set prior params to slightly simpler (more justifiable) values, and testvals to simplier defaults explanatory clarifications formatting, typos, * removed the note re step_kwargs, since this PR updates the appropriate docstring * a cell had become markdown, silly. reset it to code and rerun * minor code reformatting via black_nbconvert, final check and re-run * rerun notebook purely as a lazy but safe way to trigger new CI | 04 May 2020, 13:57:15 UTC |
2d68025 | michaelosthege | 03 May 2020, 09:26:37 UTC | add deprecation warnings for old backends (#3902) * add deprecation warnings for old backends * mention backend deprecation #3902 * fix typo Co-authored-by: Colin <ColCarroll@users.noreply.github.com> Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> Co-authored-by: Colin <ColCarroll@users.noreply.github.com> | 03 May 2020, 09:26:37 UTC |
d59a6e8 | michaelosthege | 03 May 2020, 09:25:29 UTC | Remove deprecated stuff (#3906) * remove file which is not used * remove deprecated code * repair tests and notebooks that used deprecated API * mention #3906 Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> | 03 May 2020, 09:25:29 UTC |
cc45303 | Brandon T. Willard | 01 May 2020, 21:02:21 UTC | Always define the `diverging` variable in sampling generator (#3901) | 01 May 2020, 21:02:21 UTC |
eec70e8 | Thomas Wiecki | 29 April 2020, 11:21:33 UTC | Move logging import as well as set_compiler_flags up. (#3894) * Move logging import as well as set_compiler_flags up. They seem to otherwise not be picked up on newer python versions. * Add Python 3.8 qualifier. * Remove white-space. | 29 April 2020, 11:21:33 UTC |
2d7d1d0 | michaelosthege | 28 April 2020, 16:37:38 UTC | omit test files from coverage calculation (#3895) most configurations for pytest-cov must be done via a .coveragerc config file Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> | 28 April 2020, 16:37:38 UTC |
a4aed97 | Colin | 28 April 2020, 14:41:35 UTC | Add jitter+full_adapt initialization (#3893) * Add jitter+full_adapt initialization * Add tests and benchmarks * Actually save file | 28 April 2020, 14:41:35 UTC |
ae54ba2 | Alexandre ANDORRA | 28 April 2020, 12:57:12 UTC | Simplify MvNormal Cholesky decomposition API (#3881) * Defined wrapper function on top of LKJCholeskyCov class * Added possibility of changing stds and rho names * Reorganized docs for LKJCholeskyCov * Updated examples for MvNormal * Integrated Adrian's comments * Added release note * Replaced name_stds and name_rho args by postfix * Modified docstring accordingly * Started updated LKJ notebook * Finished updating LKJ NB * Finished updating Radon example NB * Ran Black on NBs | 28 April 2020, 12:57:12 UTC |
60cca23 | Thomas Wiecki | 27 April 2020, 16:57:11 UTC | BUG Initialize adapt_full with a diagonal covariance matrix rather than ones. (#3891) | 27 April 2020, 16:57:11 UTC |
c1c7700 | Tirth Patel | 25 April 2020, 21:23:34 UTC | add matern 1/2 example in notebook (#3875) * add matern 1/2 exmaple in notebook * add equation of matern 1/2 kernel in the example | 25 April 2020, 21:23:34 UTC |
2d1d2e8 | Michael Osthege | 23 April 2020, 08:34:36 UTC | Merge branch 'master' of https://github.com/pymc-devs/pymc3 | 23 April 2020, 08:34:36 UTC |
14f6eea | Michael Osthege | 23 April 2020, 08:34:30 UTC | address review feedback | 23 April 2020, 08:34:30 UTC |
17ef4f7 | Michael Osthege | 21 April 2020, 11:51:43 UTC | address review feedback | 21 April 2020, 11:51:43 UTC |
981fb0a | Michael Osthege | 21 April 2020, 07:25:19 UTC | reduce the template to 5 checkable bullet points | 21 April 2020, 07:25:19 UTC |
e908d9f | michaelosthege | 20 April 2020, 17:47:04 UTC | Merge pull request #3888 from pymc-devs/import_warnings Import warnings module in timeseries.py. | 20 April 2020, 17:47:04 UTC |
b05c572 | Thomas Wiecki | 20 April 2020, 13:48:20 UTC | Import warnings module in timeseries.py. | 20 April 2020, 13:48:20 UTC |
80a82dd | Oriol (ZBook) | 19 April 2020, 12:21:18 UTC | update release notes | 20 April 2020, 07:42:09 UTC |
e2a90c0 | Oriol (ZBook) | 18 April 2020, 19:22:53 UTC | use from_pymc3(..., log_likelihood=False) and update requirements | 20 April 2020, 07:42:09 UTC |
dcb9cf0 | Michael Osthege | 19 April 2020, 11:08:18 UTC | add a PR template | 19 April 2020, 11:08:18 UTC |
7301027 | Chris Fonnesbeck | 19 April 2020, 01:33:28 UTC | Merge pull request #3885 from aaparab/fix#3882 minor change in documentation: support of sum is union of supports. | 19 April 2020, 01:33:28 UTC |
20e9be9 | Abhishek | 18 April 2020, 15:54:40 UTC | minor change in documentation: support of sum is union of supports. | 18 April 2020, 15:54:40 UTC |
e7bc832 | michaelosthege | 12 April 2020, 07:59:49 UTC | add type annotations in docstring | 12 April 2020, 15:46:54 UTC |
7d9a7ab | Robert P. Goldman | 11 April 2020, 16:41:00 UTC | Fix docstrings. Added raw string qualifiers for docstrings that were causing the deprecation warnings in issue #3878. In passing, fixed some other minor docstring formatting issues. | 12 April 2020, 15:46:54 UTC |
683faaa | Bill Engels | 11 April 2020, 04:38:26 UTC | Merge pull request #3877 from tirthasheshpatel/fix-gp-array-wrap [MRG] ENH: Fix array wrap in gp submodule to allow one dimensional arrays | 11 April 2020, 04:38:26 UTC |
fd79d1f | Tirth Patel | 09 April 2020, 15:52:19 UTC | fir array_wrap to support any dimensional input | 09 April 2020, 15:52:19 UTC |
3add916 | Fearghus | 07 April 2020, 10:59:17 UTC | ENH: Moyal distribution (#3870) * Added Moyal distribution to continuous class. Added tests for Moyal distribution. * Release notes updated. * Added float32 exception for Moyal dist in tests. | 07 April 2020, 10:59:17 UTC |
18a2c3b | Tirth Patel | 06 April 2020, 16:09:35 UTC | move change from V3.8 to V3.9 (#3869) * move change from V3.8 to V3.9 #3852 adds the new feature to the V3.8 changelog while it should go in the V3.9 changelog. * fix small typo * move the change a little down in the changelog | 06 April 2020, 16:09:35 UTC |
70218bf | Tirth Patel | 06 April 2020, 14:22:50 UTC | ENH: add exponentiation of a covariance function with a scalar (#3852) * ENH: add exponentiation with a scalar * fix the scalar condition * add examples in notebook | 06 April 2020, 14:22:50 UTC |
c34ae3f | Alexandre ANDORRA | 03 April 2020, 16:02:47 UTC | Check that concentration parameters of Dirichlet distribution are all > 0 (#3853) * Added check that a>0 in Dirichlet * Cast a as array for tests * Test a>0 only when a not an RV and convert to array when list * Added test for init of Dirichlet with negative values * Added release note * Resolved conflict in release notes * Escaped parenthesis in match regexp | 03 April 2020, 16:02:47 UTC |
0456f39 | Fearghus | 01 April 2020, 14:01:06 UTC | NegativeBinomial distribution sample generator wrapper (#3866) * Added wrapper for gamma sampling in negative binomial distribution. * Fixed typo in posterior sampling warnings. * Drop nuts init method from pm.sample (#3863) * Dropped nuts init method * Dropped nuts init method from tests * Refined doc string and added release note * Added wrapper for gamma sampling in negative binomial distribution. * Fixed typo in posterior sampling warnings. * Added test for negative binomial input shape. * Updating release notes with changes to negative binomial sampling. Co-authored-by: Alexandre ANDORRA <andorra.alexandre@gmail.com> | 01 April 2020, 14:01:06 UTC |
bf8552e | Alexandre ANDORRA | 31 March 2020, 17:40:19 UTC | Drop nuts init method from pm.sample (#3863) * Dropped nuts init method * Dropped nuts init method from tests * Refined doc string and added release note | 31 March 2020, 17:40:19 UTC |
de0024c | Fearghus | 30 March 2020, 12:46:26 UTC | Documentation sample plot for Rice distribution docs (#3862) * Added example plot for the Rice distribution. * Updated for scipy rice distribution convention. * Reordering sigmas in rice docstring. | 30 March 2020, 12:46:26 UTC |
5a7680f | Alexandre ANDORRA | 30 March 2020, 11:15:52 UTC | Change draws and tune defaults to 1000 in pm.sample (#3855) * Changed sampling defaults and cleaned typos * Switched tune default to 1000 * Added release note * Moved release note under Maintenance | 30 March 2020, 11:15:52 UTC |
e21191f | Alexandre ANDORRA | 30 March 2020, 06:27:46 UTC | Update Posterior Predictive Checks Notebook (#3857) * Changed sampling defaults and cleaned typos * Finished updating PPC section * Finished updating prediction section * Ran whole NB * Ran Black * Revert "Changed sampling defaults and cleaned typos" This reverts commit 5c08d9289a381cee6b678d385163b3b20185959c. Revert changes made in sampling file * Updated posterior pred NB | 30 March 2020, 06:27:46 UTC |
7874295 | Tushar Mittal | 28 March 2020, 15:42:13 UTC | Add QuadPotentialFullAdapt in pm.sample init (#3858) | 28 March 2020, 15:42:13 UTC |
4972258 | rpgoldman | 28 March 2020, 13:24:06 UTC | Fix for 3727. (#3856) | 28 March 2020, 13:24:06 UTC |
4a37e24 | Robert P. Goldman | 24 March 2020, 15:22:39 UTC | Fix docstrings. The layout of parameters sections was wrong. Also pruned some dead code. | 26 March 2020, 20:15:22 UTC |
6699447 | Demetri Pananos | 24 March 2020, 02:19:38 UTC | Render `DifferentialEquation` Documentation (#3850) * ls * Changes to ode.rst to make docs appear. * Should be working now | 24 March 2020, 02:19:38 UTC |
3036da5 | michaelosthege | 20 March 2020, 18:57:58 UTC | Support xarray input to sample_posterior_predictive (#3846) * add test for xarray input to sample_posterior_predictive * support for xarray.Dataset as trace argument to sample_posterior_predictive and fast_sample_posterior_predictive. * closes #3828 Co-authored-by: Michael Osthege <zufallsprinzip@hotmail.de> Co-authored-by: rpgoldman <rpgoldman@goldman-tribe.org> | 20 March 2020, 18:57:58 UTC |
29821a5 | rpgoldman | 20 March 2020, 12:03:51 UTC | Fix issue 3793 (#3843) * Demonstrate issue 3793. * Give Data model-relative names. Use Model.name_for() to relativize pm.Data names. * Move test description into docstring * mention changes to pm.Data naming closes #3793 Co-authored-by: michaelosthege <thecakedev@hotmail.com> | 20 March 2020, 12:03:51 UTC |
74b7788 | rpgoldman | 19 March 2020, 18:58:18 UTC | Merge pull request #3841 from rpgoldman/iss3840 Fix computation of samples argument in sample_posterior_predictive Solves #3840 | 19 March 2020, 18:58:18 UTC |
839206b | Robert P. Goldman | 19 March 2020, 16:21:18 UTC | Fix issue 3840. Previously, if the argument to sample_posterior_predictive was a list of points, AND the samples argument was not supplied, then spp would error out, because the code for computing samples assumed that the trace argument was a MultiTrace. | 19 March 2020, 18:02:57 UTC |
b566060 | Robert P. Goldman | 19 March 2020, 16:15:55 UTC | Test to replicate issue 3840. | 19 March 2020, 16:15:55 UTC |
363afc8 | Ahan M R | 19 March 2020, 11:57:29 UTC | updated RELEASE-NOTES.md (#3838) * updated RELEASE-NOTES.md Added the deprecation of `sd` with `sigma` in newer version with DeprecationWarning on usage of `sd`. * Update RELEASE-NOTES.md | 19 March 2020, 11:57:29 UTC |
40d9597 | Ahan M R | 19 March 2020, 09:10:26 UTC | Improve documentation for distributions (#3837) * partially fixes #3688 * fixes #3688 sd deprecated to sigma | 19 March 2020, 09:10:26 UTC |
e2979a3 | Brandon T. Willard | 17 March 2020, 23:43:45 UTC | Merge pull request #3834 from DeliciousHair/theano_tutorial_fix Fixed small but critical typo in Theano Op example (#3832) | 17 March 2020, 23:43:45 UTC |
0368675 | DeliciousHair | 17 March 2020, 22:42:59 UTC | fixed small but critical typo | 17 March 2020, 22:42:59 UTC |
a0bde88 | Tom McClintock | 17 March 2020, 18:52:35 UTC | Typo fix. (#3833) | 17 March 2020, 18:52:35 UTC |
6c5254f | michaelosthege | 11 March 2020, 11:34:17 UTC | Include n_tune, n_draws and t_sampling in SamplerReport (#3827) * include n_tune, n_draws and t_sampling in SamplerReport * count tune/draw samples instead of trusting parameters (because of KeyboardInterrupt) * fall back to tune and len(trace) if tune stat is unavailable * add test for SamplerReport n_tune and n_draws * clarify that n_tune are not necessarily in the trace * use actual number of chains to compute totals * mention new SamplerReport properties in release notes Co-authored-by: Michael Osthege <m.osthege@fz-juelich.de> | 11 March 2020, 11:34:17 UTC |
b5891be | Luciano Paz | 10 March 2020, 16:48:14 UTC | Merge pull request #3597 from rpgoldman/vectorize-posterior-predictive Second try to vectorize sample_posterior_predictive. | 10 March 2020, 16:48:14 UTC |
e2c334e | rpgoldman | 09 March 2020, 15:05:41 UTC | Style fix. Co-Authored-By: Thomas Wiecki <thomas.wiecki@gmail.com> | 10 March 2020, 15:48:37 UTC |
ce60289 | Robert P. Goldman | 09 March 2020, 15:04:48 UTC | Remove dead code. | 10 March 2020, 15:48:37 UTC |
a88d12e | Robert P. Goldman | 09 March 2020, 02:23:52 UTC | Add entry to changelog. | 10 March 2020, 15:48:37 UTC |
ea6e7eb | Robert P. Goldman | 09 March 2020, 02:18:45 UTC | Amplify the documentation string. | 10 March 2020, 15:48:37 UTC |
426ca09 | Robert P. Goldman | 03 January 2020, 00:27:38 UTC | Fixed incorrect reshaping. I believe that this reshaping -- which flattened the samples -- was a hold-over from the pointwise variant. It was causing test failures. | 10 March 2020, 15:48:37 UTC |
0ae72c5 | Robert P. Goldman | 11 October 2019, 14:29:12 UTC | Merge from master. | 10 March 2020, 15:48:37 UTC |
b8a67fe | Robert P. Goldman | 10 October 2019, 16:26:38 UTC | Fix forward reference error. Local class declared after reference. | 10 March 2020, 15:48:37 UTC |
ab227bd | Robert P. Goldman | 16 September 2019, 20:53:50 UTC | Add contextvars requirement. The contextvars library is used to make the vectorized version of sample_posterior_predictive compatible with the legacy version. contextvars was added in python 3.7, but there is a compatibility library for 3.6 This is an attempt to ensure it will be loaded in python 3.6 | 10 March 2020, 15:48:37 UTC |
f915dce | Robert P. Goldman | 06 September 2019, 00:21:51 UTC | Fix test bugs. | 10 March 2020, 15:48:37 UTC |
94660a5 | Robert P. Goldman | 05 September 2019, 22:16:16 UTC | Add typing_extensions to reqs. | 10 March 2020, 15:48:37 UTC |
e95b2a4 | Robert P. Goldman | 05 September 2019, 21:26:05 UTC | Ugly fix for shape problem. When sampling fast_posterior_predictive gets some values with a degenerate extra dimension (e.g., 1 row of 200 values, instead of just 200 values: (1, 200) instead of (200,) ). Trim these off. It would be better if I could figure out where these are coming from and avoid that. | 10 March 2020, 15:48:37 UTC |
dfa5ea1 | Robert P. Goldman | 05 September 2019, 21:24:16 UTC | Refined test_sample while debugging. More carefully check the results of posterior predictive sampling with pm.Data. | 10 March 2020, 15:48:37 UTC |
b94e80b | Robert P. Goldman | 23 August 2019, 04:25:08 UTC | Unpleasant patch to deal with wrap_random_with_dist_shape | 10 March 2020, 15:48:37 UTC |
234e0c3 | Robert P. Goldman | 23 August 2019, 02:19:43 UTC | Fix test typo. | 10 March 2020, 15:48:37 UTC |
11fda15 | Robert P. Goldman | 23 August 2019, 02:15:42 UTC | Fix _TraceDict indexing bug. | 10 March 2020, 15:48:37 UTC |