pymc
https://github.com/pymc-devs/pymc
Python
Bayesian Modeling in Python
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported8 Subscribers
Add a CodeTriage badge to pymc
Help out
- Issues
- Fix find_constants excluding discrete observed data from constant_data
- BUG: `pm.sample(nuts_sampler="blackjax")` fails during warmup with every blackjax >= 1.6
- BUG: JAX-backend fit leaves jax.Array in shared variable storage, breaking later numba-compiled functions (approx.sample)
- BUG: pm.fit(..., backend="jax") fails for every model: ADVI approximation parameters lack static shapes
- Refactor existing samplers behind a shared Sampler interface
- Add icdf for Wald distribution
- Allow free-threaded parallel sampling
- Generic Blackjax external sampler: run any blackjax MCMC algorithm via pm.sample
- BUG: pm.sample can't disable init-value jitter for the external JAX samplers (numpyro/blackjax)
- Introduce `step-setup` in samplers
- Docs
- Python not yet supported