Bayinx: Bayesian Inference with JAX
Bayinx is an embedded probabilistic programming language in Python, powered by JAX. It is heavily inspired by and aims to have feature parity with Stan, but extends the types of objects you can work with and focuses on normalizing flows variational inference for sampling.
Installation
Bayinx requires Python 3.12+, JAX, and a few extra libraries in the JAX ecosystem.
The easiest way to get started is by installing from PyPi using your favourite python package manager. For example with uv:
# Ensure you are in your project environment
uv add bayinx
This installs the bare-bones version of Bayinx, however if you need additional functionality like GPU support, there are a couple of dependency groups:
# Ensure you are in your project environment
uv add 'bayinx[cuda]' # Installs Bayinx with CUDA support
Documentation
Documentation is available at: https://toddpocuca.github.io/bayinx.
Roadmap
- Allow shape definitions to include expressions (e.g., shape = 'n_obs + 1' will evaluate to the correct specification).
- Implement SALSA https://arxiv.org/abs/2002.10597.
- Nodes carry bounds for their support (i.e., node.obj ∈ [node._lb, node._ub]) which are used to check if inputs to distributions are valid (e.g., a node inputted as the scale of a normal dist must have
node._lb >= 0).
1 maintainer
Metadata
1 maintainer
Release files for bayinx 0.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| bayinx-0.8.0.tar.gz | 701.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| bayinx-0.8.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 780.1 kB
Release files / bayinx-0.8.0.tar.gz
| Download URL | bayinx-0.8.0.tar.gz |
|---|---|
| Size | 701.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
57f774bc293d308b03fe77bd018fb5ecefa33a8d06807a32fc2c164f598aff8e
|
|
BLAKE2b-256 checksum How to use checksums |
30cfff65b1fbecb5cacc4a80fa692e9c5344055d2738d7def5be6b6f50fd12da
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.8 {"installer":{"name":"uv","version":"0.11.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / bayinx-0.8.0-py3-none-any.whl
| Download URL | bayinx-0.8.0-py3-none-any.whl |
|---|---|
| Size | 78.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b40a1b3bb20a16f7d855456e89982cf5110ddde9ae0041f59fcf2f138a7d0952
|
|
BLAKE2b-256 checksum How to use checksums |
2d619275d8e9e996d937a97d939bb66a760311d8845d96d2059e9b48dd748a49
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.8 {"installer":{"name":"uv","version":"0.11.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for bayinx 0.8.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
