544a806 | Chris Fonnesbeck | 19 April 2018, 02:42:36 UTC | Merge pull request #2934 from pymc-devs/v3.4_release Increment version to 3.4.1 | 19 April 2018, 02:42:36 UTC |
2bfae0f | Christopher Fonnesbeck | 18 April 2018, 21:13:11 UTC | Increment version to 3.4.1 | 18 April 2018, 21:13:11 UTC |
a8b1147 | Chris Fonnesbeck | 18 April 2018, 20:52:24 UTC | Merge pull request #2932 from pymc-devs/v3.4_release Increment version to 3.4 | 18 April 2018, 20:52:24 UTC |
bdac988 | Christopher Fonnesbeck | 17 April 2018, 16:04:51 UTC | Increment version to 3.4 | 17 April 2018, 16:04:51 UTC |
edd28d4 | Chris Fonnesbeck | 13 April 2018, 19:19:40 UTC | Merge pull request #2929 from pymc-devs/v3.4_release Version 3.4 RC2 | 13 April 2018, 19:19:40 UTC |
3ae6984 | Christopher Fonnesbeck | 13 April 2018, 18:26:41 UTC | Increment version to RC2 | 13 April 2018, 18:26:41 UTC |
a0ec8e2 | Chris Fonnesbeck | 13 April 2018, 01:08:24 UTC | Removed redundant specification of version number (#2926) * Removed redundant specification of version number * Replaced pymc3 import in setup with regex function for getting version * Removed typo | 13 April 2018, 01:08:24 UTC |
02af08a | Chris Fonnesbeck | 11 April 2018, 14:16:26 UTC | Merge pull request #2928 from aloctavodia/posteriorplot fix missing test_size argument | 11 April 2018, 14:16:26 UTC |
7f8ad73 | aloctavodia | 11 April 2018, 12:18:46 UTC | fix missing test_size argument | 11 April 2018, 12:18:46 UTC |
a502e2f | Chris Fonnesbeck | 10 April 2018, 02:14:55 UTC | Merge pull request #2924 from ColCarroll/update_setup Update short and long descriptions in setup.py | 10 April 2018, 02:14:55 UTC |
5899381 | Christopher Fonnesbeck | 09 April 2018, 14:00:01 UTC | Merge branch 'v3.4_release' | 09 April 2018, 14:00:01 UTC |
f46c099 | Christopher Fonnesbeck | 09 April 2018, 13:59:13 UTC | Fixed RC tags | 09 April 2018, 13:59:13 UTC |
94ae7d6 | Chris Fonnesbeck | 09 April 2018, 13:49:26 UTC | Merge pull request #2925 from pymc-devs/v3.4_release Version 3.4 RC 1 | 09 April 2018, 13:49:26 UTC |
7960066 | Chris Fonnesbeck | 08 April 2018, 22:05:58 UTC | Incremented version to 3.4 | 08 April 2018, 22:05:58 UTC |
380d50a | Colin Carroll | 07 April 2018, 21:17:56 UTC | Update short and long descriptions in setup.py | 07 April 2018, 21:17:56 UTC |
f7ab277 | Chris Fonnesbeck | 07 April 2018, 21:09:25 UTC | Merge pull request #2923 from aloctavodia/repr_latex fix wrong parameter name in beta's repr_latex | 07 April 2018, 21:09:25 UTC |
68dfa2c | aloctavodia | 07 April 2018, 20:53:18 UTC | fix wrong parameter name in beta's repr_latex | 07 April 2018, 20:53:18 UTC |
cc4e034 | Junpeng Lao | 05 April 2018, 15:41:17 UTC | implement `forward_val` in transform as a numpy function (#2920) * implement `forward_val` in transform as a numpy function it is faster to do forward transformation in numpy, could be useful for sampling from prior. * add test * change transform useage in SMC * rename test | 05 April 2018, 15:41:17 UTC |
33d0ab7 | Colin | 05 April 2018, 01:56:20 UTC | No comma in MCMC | 05 April 2018, 13:39:43 UTC |
ebc1e41 | Chris Fonnesbeck | 05 April 2018, 01:50:27 UTC | Merge pull request #2921 from DerekRoy/patch-1 edit README.rst | 05 April 2018, 01:50:27 UTC |
3f6c87d | DerekRoy | 04 April 2018, 23:56:35 UTC | edit README.rst Slight change to simplify text. | 04 April 2018, 23:56:35 UTC |
fe8efbb | Osvaldo Martin | 04 April 2018, 23:49:15 UTC | remove duplicated code (#2919) | 04 April 2018, 23:49:15 UTC |
75f64e9 | charlotteburki | 04 April 2018, 11:52:05 UTC | Blocked metropolis with fixed and continuous variables (#2918) | 04 April 2018, 11:52:05 UTC |
883f4ef | Maxim Kochurov | 03 April 2018, 16:52:16 UTC | raise an error when model has discrete vars (#2917) * raise an error when model has discrete vars * unicode char | 03 April 2018, 16:52:16 UTC |
e97f5ab | Osvaldo Martin | 03 April 2018, 09:58:11 UTC | DOC: Divergences, fix small issues (#2915) * small fixes * small fixes | 03 April 2018, 09:58:11 UTC |
0bf1c8c | Chris Fonnesbeck | 02 April 2018, 17:21:08 UTC | Changed support of exponential to include zero (#2914) * Changed support of exponential to include zero * Added exponential fix to release notes | 02 April 2018, 17:21:08 UTC |
e3c4d87 | Leo Singer | 31 March 2018, 15:33:45 UTC | Fix typo | 31 March 2018, 19:32:49 UTC |
7493d5b | Junpeng Lao | 23 March 2018, 06:04:36 UTC | Small bugfix Right now, doing below gives NaN: ```python with pm.Model() as m: a = pm.Uniform('a', -100, 100) for RV in m.basic_RVs: print(RV.name, RV.logp(m.test_point)) ``` This PR fix this | 23 March 2018, 13:50:18 UTC |
0aea848 | Robert Perrotta | 22 March 2018, 22:53:35 UTC | Fixed typo in Bayes factor heuristics discussion (#2905) Bayes factors cannot be less than zero. Bayes factors less than one support the model in the denominator. | 22 March 2018, 22:53:35 UTC |
f833a14 | Luciano Paz | 21 March 2018, 10:04:26 UTC | Refactor distribution.draw_values (#2902) * Fix for #2900. Changed the way in which draw_values handles the named node-inputs. Now the tree dependence is constructed to set the givens dict. * Fixed conflicts * Fixed more conflicts * Fixed typo * Changed test_dep_vars to test for successful draws even in the cases of dependent variables. * Removed comments from test_random.py, and distribution.py. Added content to RELEASE-NOTES. Fixed bug in the interaction between draw_values, _draw_value and _compile_theano_function. In some cases, draw_values would set an item of the givens dictionary to a theano.tensor.TensorConstant. In _draw_value(param, ...), if param was a theano.tensor.TensorVariable without a random method, and not set in point, _compile_theano_function would be called, using as one of its variables, a theano.tensor.TensorConstant. This lead to TypeError: ("Constants not allowed in param list",...) exceptions being raised. The fix was to skip the inclusion into the givens dictionary of named nodes that were instances of theano.tensor.TensorConstant, because their value would already be available for theano during the function compilation. * Fixed another bug which was similar to the theano.tensor.TensorConstant, but it occurred on theano.tensor.sharedvar.SharedVariable instances. The error that was raised was similar, SharedVariables cannot be supplied as raw input to theano.function. The fix was the same as for TensorConstants, skip them when constructing the givens dictionary. * Guarded against a potencial bug. In draw_values, when skipping for TensorConstant and SharedVariable types, these nodes could be added to the stack again later because their names would not be in givens.keys(). To counter that, a separate set, `stored`, with the names of nodes that are either stored in givens or whos values should be available to theano.function, is used to chose which nodes to add to the stack. * Syntax change based on twiecki's comment. * Extended RELEASE-NOTES.md to also mention the sharedvar.ShareVariable fix. | 21 March 2018, 10:04:26 UTC |
7d327b3 | Junpeng Lao | 19 March 2018, 16:03:11 UTC | Mixture of mixtures (#2904) * Mixture of mixtures Following the discussion on Discourse: https://discourse.pymc.io/t/how-can-we-build-a-mixture-of-mixtures/910/ I made some small fix so that it is easier to create multivariate mixture and mixture of mixtures * fix test * add test for multivariate mixture * fix float32 test Co-authored-by: Junpeng Lao <junpeng.lao@unifr.ch> Co-authored-by: Hubert Wassner <hubert.wassner@gmail.com> | 19 March 2018, 16:03:11 UTC |
6dd0e81 | Chris Fonnesbeck | 15 March 2018, 15:06:42 UTC | Merge pull request #2764 from pymc-devs/compare_tweak Changed arguments for compare to accept dict | 15 March 2018, 15:06:42 UTC |
2743564 | Chris Fonnesbeck | 14 March 2018, 14:49:55 UTC | Added change to release notes | 14 March 2018, 14:49:55 UTC |
ed4b485 | Christopher Fonnesbeck | 14 March 2018, 02:46:52 UTC | Removed old warnings code | 14 March 2018, 02:46:52 UTC |
297b419 | Christopher Fonnesbeck | 13 March 2018, 16:16:47 UTC | Changed compare arguments to support model-trace dict | 13 March 2018, 16:16:47 UTC |
03bc7ee | Christopher Fonnesbeck | 13 March 2018, 13:54:40 UTC | Copied identical models in test_compare | 13 March 2018, 13:54:40 UTC |
bc7df0c | Christopher Fonnesbeck | 13 March 2018, 13:35:59 UTC | Merge branch 'master' into compare_tweak | 13 March 2018, 13:35:59 UTC |
999661c | Maxim Kochurov | 10 March 2018, 08:28:43 UTC | fix PyMC3 variable is not replaced if provided in more_replacements (VI) (#2891) * fixes #2890 * float32 y * update release notes * use floatX | 10 March 2018, 08:28:43 UTC |
b385791 | aloctavodia | 08 March 2018, 14:43:02 UTC | use pm.get_data | 08 March 2018, 14:50:52 UTC |
6006f85 | Max Margenot | 08 March 2018, 02:13:57 UTC | DOC: Added PyMC3 version code and changed plot style | 08 March 2018, 10:20:34 UTC |
cf0a373 | Max Margenot | 07 March 2018, 02:38:22 UTC | DOC: Updated getting_started.ipynb to use Google Finance as pandas_datareader deprecated Yahoo Finance | 08 March 2018, 10:20:34 UTC |
543fb5f | Agustina Arroyuelo | 07 March 2018, 15:05:34 UTC | Remove statsmodels and add new data csv files (#2892) * remove statsmodels and add new data csv files * use get_data | 07 March 2018, 15:05:34 UTC |
4fb8aed | Osvaldo Martin | 07 March 2018, 14:56:54 UTC | densityplot: fix bug hpd_markers (#2895) | 07 March 2018, 14:56:54 UTC |
7471e4e | Osvaldo Martin | 06 March 2018, 23:51:08 UTC | remove df_summary (#2893) * remove df_summary * fix typo | 06 March 2018, 23:51:08 UTC |
6f77cc6 | Holger Peters | 06 March 2018, 02:53:55 UTC | Doc Improvements: Bound API doc, HalfNormal description, markup fixes (#2888) * Include API reference for Bound class * Include API reference for Bound class * In documentation for bounds, link to distributions * Fix mean and variance of HalfNormal in docs * Add missing sphinx markup for kronecker/math * Fix external link in docs notebook * Add encoding declaration in distribution.py * Change URL to https * Fix markup for MatrixNormal | 06 March 2018, 02:53:55 UTC |
e72b0d5 | Junpeng Lao | 04 March 2018, 15:37:39 UTC | Add offset to glm models (#2889) * Add `offset` kwarg to glm with test * add release note and clean ups * minor potential fail safe * set default to 0. | 04 March 2018, 15:37:39 UTC |
b463f2b | Holger Peters | 03 March 2018, 19:07:06 UTC | Include pymc.model in documentation (#2885) * Add API docs for the model module to sphinx docs * Fix docstring, so that code is properly rendered * Fix markup in docstrings in pymc3.model * Unpacking operators are not part of the name, and sphinx assumes they are markup. * Small changes, such as replacing markdown-style single backticks for marking up identifiers with proper RST style double backticks * Constructor should be documented in the class docstring * Remove defaults from docstring and use RST instead of markdown * Reformatting of the code-example's comments * Create a sphinx _static dir that is tracked by git Avoids warning of sphinx that the directory does not exist | 03 March 2018, 19:07:06 UTC |
7327f9d | Junpeng Lao | 03 March 2018, 11:53:33 UTC | Fix Binomial GLM In glm module binomial familiy is actually Bernoulli. This PR fix the Binomial likelihood, with the flexibility of specifying the `n`. Default n set to 1 for backward compatibility. Also added test. | 03 March 2018, 19:05:03 UTC |
f6cb5ff | Junpeng Lao | 02 March 2018, 13:47:46 UTC | fix typo (#2883) `lenght` --> `length` | 02 March 2018, 13:47:46 UTC |
be532de | Osvaldo Martin | 02 March 2018, 13:38:50 UTC | Densityplot: add support for discrete variables (#2878) * densityplot: add support for discrete variables * fix error with xticks, add to release notes * fix typo | 02 March 2018, 13:38:50 UTC |
fde52a4 | Osvaldo Martin | 27 February 2018, 20:24:57 UTC | Add LogitNormal distribution and tests (#2877) * Add LogitNormal disribution and tests Co-authored-by: denadai2 <denadai2@users.noreply.github.com> Co-authored-by: aloctavodia <aloctavodia@gmail.com> * reduce precision for float32 | 27 February 2018, 20:24:57 UTC |
dcdd543 | Maxim Kochurov | 26 February 2018, 12:16:42 UTC | update gitignore | 26 February 2018, 21:49:30 UTC |
f026fb8 | Maxim Kochurov | 26 February 2018, 12:15:40 UTC | fix test | 26 February 2018, 21:49:30 UTC |
c950a2a | Maxim Kochurov | 26 February 2018, 09:55:51 UTC | refactor memoize | 26 February 2018, 21:49:30 UTC |
553f057 | Agustina Arroyuelo | 26 February 2018, 14:33:48 UTC | Add scatterplot function (#2861) * add new scatterplot function * followed sugestions made in #2861 * run Divergences notebook with examples * add carriage return * fix plot_transformed argument * fix fig_size * fix gridspec import error and minor issues * remove unused module import line | 26 February 2018, 14:33:48 UTC |
4b3620c | Junpeng Lao | 25 February 2018, 19:41:22 UTC | Merge pull request #2867 from junpenglao/fix_2866 fix BinaryGibbsMetropolis issue for p=.5 | 25 February 2018, 19:41:22 UTC |
3c18c4d | Vaibhav Kumar Dixit | 25 February 2018, 17:24:24 UTC | Changes in test for random kwarg in DensityDist (#2840) * Added test * Test scipy distribution compatibility with DensityDist * Updated RELEASE-NOTES.md * Changes in test for random method in DensityDist * Added docstring for DensityDist * Update tests for random method with DensityDist | 25 February 2018, 17:24:24 UTC |
e3c4422 | Junpeng Lao | 25 February 2018, 17:15:12 UTC | Update follow comments | 25 February 2018, 17:15:12 UTC |
38bfc65 | Osvaldo Martin | 25 February 2018, 16:02:12 UTC | DOC: Add missing plots for discrete and continuous distributions (#2871) * Plots of discrete distributions in the docstrings * Plots of discrete distributions in the docstrings * unify style and add missing continuous * fix several error after building locally * add line to clarify that formula correspond to pdf/pmf * fix indent | 25 February 2018, 16:02:12 UTC |
023e572 | Austin Rochford | 25 February 2018, 12:02:10 UTC | Add option to disable joblib mmap-ing (#2872) * Add option to disable joblib mmap-ing that can sometimes lead to alignment errors * Don't use mmap by default | 25 February 2018, 12:02:10 UTC |
9af7993 | Austin Rochford | 24 February 2018, 14:23:32 UTC | Merge pull request #2873 from AustinRochford/add-dev-reqs-docker Copy requirements-dev.txt to Docker container | 24 February 2018, 14:23:32 UTC |
48ad319 | AustinRochford | 24 February 2018, 14:21:57 UTC | Copy requirements-dev.txt to Docker container | 24 February 2018, 14:21:57 UTC |
0596c33 | Junpeng Lao | 23 February 2018, 16:56:03 UTC | Change logp of some distributions to returns element_wise logp (#2870) * Mixture logp returns element_wise logp close #2868 * MultiNomial logp return element_wise more precisely it returns logp for each row * Additional warning for waic and loo * fix multinomial elementwise logp add test * fix warning bug in waic and loo | 23 February 2018, 16:56:03 UTC |
1aeca78 | Colin | 23 February 2018, 13:27:15 UTC | Fix possible undefined variables (#2869) | 23 February 2018, 13:27:15 UTC |
c56bf3b | Junpeng Lao | 21 February 2018, 22:09:58 UTC | More flexible kernel that allows antithetical sampling. Setting transit_p=1 we recover the old behavior of the sampler. | 21 February 2018, 22:09:58 UTC |
801accb | Austin Rochford | 21 February 2018, 15:24:09 UTC | Merge pull request #2863 from himkt/fix-varname Fix the wrong varname | 21 February 2018, 15:24:09 UTC |
2865760 | Junpeng Lao | 21 February 2018, 14:35:53 UTC | fix BinaryGibbsMetropolis issue for p=.5 close #2866. BinaryGibbsMetropolis propose alternating update to pm.Bernoulli('x', 0.5) which generate deterministic sequence | 21 February 2018, 14:35:53 UTC |
8566a12 | Junpeng Lao | 21 February 2018, 14:31:34 UTC | Revert "bug fix #2866" This reverts commit 3f6855833ea252ccf4eacf68052ca5d368df7950. | 21 February 2018, 14:31:54 UTC |
3f68558 | Junpeng Lao | 21 February 2018, 14:31:34 UTC | bug fix #2866 close #2866. | 21 February 2018, 14:31:34 UTC |
5dfd082 | Junpeng Lao | 21 February 2018, 13:08:16 UTC | Merge pull request #2864 from junpenglao/fast_kde_fix Small fix for fast_kde | 21 February 2018, 13:08:16 UTC |
55729cf | Junpeng Lao | 21 February 2018, 12:07:02 UTC | Small fix for fast_kde After #2837 fast_kde failed with stale trace (ie, trast with only one value like [0, 0, 0, 0, ...]). This PR make sure the fast_kde behavior is the same as before. | 21 February 2018, 12:07:02 UTC |
2f35eb9 | himkt | 21 February 2018, 07:36:07 UTC | Fix the wrong varname | 21 February 2018, 07:36:07 UTC |
a3af00d | Junpeng Lao | 15 February 2018, 06:38:18 UTC | Merge pull request #2731 from jordan-melendez/KroneckerGP Kronecker GP | 15 February 2018, 06:38:18 UTC |
77afa45 | Junpeng Lao | 14 February 2018, 17:44:48 UTC | Update README.rst (#2857) remove outdated `scikits.sparse` optional dependence. | 14 February 2018, 17:44:48 UTC |
0446166 | Osvaldo Martin | 14 February 2018, 06:24:44 UTC | Update model comparison and SMC notebooks (#2855) * update model comparison and SMC notebooks * add gBokiau corrections | 14 February 2018, 06:24:44 UTC |
cabdbf9 | Osvaldo Martin | 14 February 2018, 06:15:07 UTC | KDE: compute bandwith using entropy instead of standard deviation (#2837) * kde: compute bandwith using entropy instead of std * scale factor 4.5 * add argument for bandwidth scaling factor * add to release notes | 14 February 2018, 06:15:07 UTC |
ece6ee8 | jordan-melendez | 06 February 2018, 01:01:03 UTC | Added Kronecker GP PR features | 13 February 2018, 22:57:57 UTC |
71c5077 | Adrian Seyboldt | 05 January 2018, 12:17:26 UTC | Add logit parametrization of Bernoulli | 13 February 2018, 22:48:06 UTC |
a3521e8 | jordan-melendez | 18 January 2018, 01:55:08 UTC | Added working KroneckerNormal random tests | 13 February 2018, 22:45:22 UTC |
2239bf2 | jordan-melendez | 18 January 2018, 01:54:18 UTC | Added tests for Kron, Coregion, and MarginalKron, and fix strange failure | 13 February 2018, 22:45:22 UTC |
783ecfd | jordan-melendez | 18 January 2018, 01:52:16 UTC | Finalized KroneckerNormal distribution | 13 February 2018, 22:45:22 UTC |
177e039 | jordan-melendez | 25 November 2017, 14:17:38 UTC | Added Kronecker operations tests | 13 February 2018, 22:45:22 UTC |
ab96e18 | jordan-melendez | 25 November 2017, 14:16:31 UTC | Added KroneckerNormal tests | 13 February 2018, 22:43:34 UTC |
84291c7 | jordan-melendez | 25 November 2017, 14:14:00 UTC | Cleaned up documentation | 13 February 2018, 22:43:34 UTC |
d2d0fae | jordan-melendez | 23 November 2017, 15:42:24 UTC | Added local fix of theano EighGrad | 13 February 2018, 22:43:34 UTC |
d973361 | jordan-melendez | 21 November 2017, 22:07:57 UTC | Added MarginalKron | 13 February 2018, 22:43:34 UTC |
5e99b02 | jordan-melendez | 21 November 2017, 22:07:31 UTC | Added KroneckerNormal | 13 February 2018, 22:43:34 UTC |
6324cf7 | jordan-melendez | 21 November 2017, 22:07:11 UTC | Added KroneckerNormal and switched to local Eigh | 13 February 2018, 22:43:34 UTC |
ad875f4 | jordan-melendez | 21 November 2017, 22:06:51 UTC | Added Coregion kernel and Kron covariance | 13 February 2018, 22:43:34 UTC |
8437e80 | jordan-melendez | 21 November 2017, 22:06:36 UTC | Added MarginalKron functionality | 13 February 2018, 22:43:34 UTC |
68500f0 | jordan-melendez | 21 November 2017, 22:06:08 UTC | Added efficient Kronecker functions | 13 February 2018, 22:43:34 UTC |
79677da | Junpeng Lao | 13 February 2018, 16:32:36 UTC | Fix effective sample size estimation (#2854) * Fix effective sample size estimation Close #2810 Reference implementation in PyStan: https://github.com/stan-dev/pystan/pull/415 - improve autocorr and autocov function, use fft convolve for autocorrelation computation * Improve effective sample size implementation Effective sample size computed using autocov and Geyer's initial monotone sequence criterion for vhat. * Improve effective sample size implementation Effective sample size computed using autocov and Geyer's initial monotone sequence criterion for vhat. Co-authored-by: Junpeng Lao <junpeng.lao@unifr.ch> Co-authored-by: Sharan Yalburgi <sharanyalburgi@gmail.com> * Turn off automatic convergent check for short chain * update release note * Turn off convergent check in benchmark model To have more accurate computation of the things we want to benchmark. effective_n computation is slower than before for large number of samples (at 10000 sample it is around 10x slower). There should be a large increase in effective_n benchmark. | 13 February 2018, 16:32:36 UTC |
ffc0608 | Colin | 13 February 2018, 11:23:07 UTC | Update posterior_predictive notebook (#2853) * Grammar, style, version edits * Address comments | 13 February 2018, 11:23:07 UTC |
dc7e3f1 | Colin Carroll | 11 February 2018, 15:17:44 UTC | Only set random seed if specified. | 12 February 2018, 15:55:00 UTC |
deff999 | Junpeng Lao | 12 February 2018, 08:42:11 UTC | Bugfix for #2849 (#2850) * Bugfix for #2849 add conditioning to get_untransformed_name to have correct output for CholeskyCovPacked transform * Fix potential fail if name with `__` | 12 February 2018, 08:42:11 UTC |
371bb28 | ArjitJ | 06 February 2018, 15:47:22 UTC | Fixed broken links (#2842) * Update model_averaging.ipynb * Updated links * Revert "Updated links" * Fixed broken links Updated links for model_comparison.ipynb and GLM-model-selection.ipynb * Updated links Changed the links from http://docs.pymc.io/ to http://pymc-devs.github.io/pymc3/ | 06 February 2018, 15:47:22 UTC |
0379ef5 | Osvaldo Martin | 05 February 2018, 15:10:13 UTC | add numpy=1.13 as a dependency (#2841) | 05 February 2018, 15:10:13 UTC |
760fba4 | Vaibhav Kumar Dixit | 05 February 2018, 08:10:14 UTC | Add random kwarg to DensityDist #2106 (#2805) * Add random kwarg to DensityDist #2106 * Added test * Test scipy distribution compatibility with DensityDist * Updated RELEASE-NOTES.md | 05 February 2018, 08:10:14 UTC |
0ecb6d1 | Junpeng Lao | 04 February 2018, 18:30:56 UTC | fix tuning warning (#2839) * fix tuning warning fix #2838 and move small trace warning into pm.sampling * fix test | 04 February 2018, 18:30:56 UTC |
946fa0c | Chris Fonnesbeck | 04 February 2018, 01:48:30 UTC | Merge pull request #2831 from pymc-devs/sample_arg_rename Replace njobs with cores argument | 04 February 2018, 01:48:30 UTC |