pymc
pymc copied to clipboard
pymc-devs
Bayesian Modeling and Probabilistic Programming in Python
Closes #5973 ## Major / Breaking Changes - ... ## Bugfixes / New features - ... ## Docs / Maintenance - Log name of `basic_RVs` sampled in prior and posterior...
I've seen this fail a couple of times, most recently in * https://github.com/pymc-devs/pymc/actions/runs/3104834907/jobs/5029759150 * https://github.com/pymc-devs/pymc/actions/runs/3104845472/jobs/5029781127 Might need to be seeded or given a higher tolerance
That file is quite long, and anyway `draw` and `sample_prior/posterior_predictive` behave very differently from `sample` so we could separate them across two files (and same for tests). WDYT?
Hi, this is not really a bug, but a small change to improve the code consistency in the pymc gp module. In `pymc.gp.gp.py` file, several GP classes such as "[Marginal](https://github.com/pymc-devs/pymc/blob/a90c420b8b31fe4996f11d8ca9b3cc80abf4a97d/pymc/gp/gp.py#L415)"...
Is this possible? Config is here: https://github.com/pymc-devs/pymc/blob/main/.github/workflows/autoupdate-pre-commit-config.yml
## Base PullRequest default branch (https://github.com/pymc-devs/pymc/tree/main) ## Command results Details: add path ```Shell /home/runner/work/_actions/technote-space/create-pr-action/v2/node_modules/npm-check-updates/build/src/bin ``` pip install pre-commit ```Shell Collecting pre-commit Using cached pre_commit-2.20.0-py2.py3-none-any.whl (199 kB) Collecting pyyaml>=5.1 Using cached...
This PR introduces the world famous `ZeroSumNormal` distribution, i.e a Normal distribution where one or several axes are constrained to sum to zero. By default, the last axis is constrained...
**What is this PR about?** ... **Checklist** + [ ] Explain important implementation details 👆 + [ ] Make sure that [the pre-commit linting/style checks pass](https://docs.pymc.io/en/latest/contributing/python_style.html). + [ ] Link...
Discovered while skimming the diff since last release
