https://github.com/auggiemarignier/pxmcmc
Solving inverse problems with Proximal Markov Chain Monte Carlo
https://github.com/auggiemarignier/pxmcmc
bayesian-inference inverse-problems mcmc proximal-algorithms python
Last synced: 4 months ago
JSON representation
Solving inverse problems with Proximal Markov Chain Monte Carlo
- Host: GitHub
- URL: https://github.com/auggiemarignier/pxmcmc
- Owner: auggiemarignier
- License: gpl-3.0
- Created: 2021-02-15T11:55:07.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2023-10-08T02:30:51.000Z (over 1 year ago)
- Last Synced: 2024-12-21T09:35:05.339Z (5 months ago)
- Topics: bayesian-inference, inverse-problems, mcmc, proximal-algorithms, python
- Language: Python
- Homepage: https://pxmcmc.readthedocs.io/en/latest/?badge=latest
- Size: 28.8 MB
- Stars: 7
- Watchers: 3
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://badge.fury.io/py/pxmcmc) [](https://pxmcmc.readthedocs.io/en/latest/?badge=latest) [](https://github.com/auggiemarignier/pxmcmc/actions/workflows/python-app.yml) [](https://joss.theoj.org/papers/ed274b8490fbc89365e6e0a993f73d86) 
# Python ProxMCMC
## Installation
Available on [pypi](https://pypi.org/project/pxmcmc/)
```bash
pip install pxmcmc
```
If installing from source it recommended to use [poetry](https://python-poetry.org/)
```bash
git clone https://github.com/auggiemarignier/pxmcmc
cd pxmcmc
poetry install
source /bin/activate
pytest
```
## Documentation
Full documentation available on [readthedocs](https://pxmcmc.readthedocs.io/en/latest/?badge=latest).
## Examples
Examples of how to use this code with sample data are found in the `experiments` directory.
Please start with the `earthtopography` example, which will quickly run something to get you going!
```bash
cd experiments/earthtopography
python main.py --infile ETOPO1_Ice_hpx_256.fits
python plot.py myula_synthesis_.hdf5 .
```
The `phasevel` and `weaklensing` examples replicate the work shown [in this paper](https://doi.org/10.1093/rasti/rzac010).
## Contributing
Contributions to the package are encouraged! If you wish to contribute, are experiencing problems with the code or need further support, please open an [issue](https://github.com/auggiemarignier/pxmcmc/issues/new) to start a discussion. Changes will be integrated via pull requests.
## CITATION
If you use this package in your work please cite the following papers
Marignier (2023) PxMCMC: A Python package for proximal Markov Chain Monte Carlo, Journal of Open Source Software, 0(0), 5582. https://doi.org/10.21105/joss.05582
Marignier et al., Posterior sampling for inverse imaging problems on the sphere in seismology and cosmology, RAS Techniques and Instruments, Volume 2, Issue 1, January 2023, Pages 20–32, https://doi.org/10.1093/rasti/rzac010