**zeus is a Python implementation of the Ensemble Slice Sampling method.**
- Fast & Robust *Bayesian Inference*,
- Efficient *Markov Chain Monte Carlo (MCMC)*,
- Black-box inference, no hand-tuning,
- Excellent performance in terms of autocorrelation time and convergence rate,
- Scale to multiple CPUs without any extra effort,
- Automated Convergence diagnostics.
[](https://github.com/minaskar/zeus)
[](https://arxiv.org/abs/2002.06212)
[](https://arxiv.org/abs/2105.03468)
[](https://ascl.net/2008.010)
[](https://travis-ci.com/minaskar/zeus)
[](https://github.com/minaskar/zeus/blob/master/LICENSE)
[](https://zeus-mcmc.readthedocs.io/en/latest/?badge=latest)
[](https://pepy.tech/project/zeus-mcmc)
## Example
For instance, if you wanted to draw samples from a 10-dimensional Gaussian, you would do something like:
```python
import zeus
import numpy as np
def log_prob(x, ivar):
return - 0.5 * np.sum(ivar * x**2.0)
nsteps, nwalkers, ndim = 1000, 100, 10
ivar = 1.0 / np.random.rand(ndim)
start = np.random.randn(nwalkers,ndim)
sampler = zeus.EnsembleSampler(nwalkers, ndim, log_prob, args=[ivar])
sampler.run_mcmc(start, nsteps)
chain = sampler.get_chain(flat=True)
```
## Documentation
Read the docs at [zeus-mcmc.readthedocs.io](https://zeus-mcmc.readthedocs.io)
## Installation
To install ``zeus`` using ``pip`` run:
```bash
pip install zeus-mcmc
```
To install ``zeus`` in a [[Ana]Conda](https://conda.io/projects/conda/en/latest/index.html) environment use:
```bash
conda install -c conda-forge zeus-mcmc
```
## Attribution
Please cite the following papers if you found this code useful in your research:
```bash
@article{karamanis2021zeus,
title={zeus: A Python implementation of Ensemble Slice Sampling for efficient Bayesian parameter inference},
author={Karamanis, Minas and Beutler, Florian and Peacock, John A},
journal={arXiv preprint arXiv:2105.03468},
year={2021}
}
@article{karamanis2020ensemble,
title = {Ensemble slice sampling: Parallel, black-box and gradient-free inference for correlated & multimodal distributions},
author = {Karamanis, Minas and Beutler, Florian},
journal = {arXiv preprint arXiv: 2002.06212},
year = {2020}
}
```
## Licence
Copyright 2019-2021 Minas Karamanis and contributors.
zeus is free software made available under the GPL-3.0 License. For details see the `LICENSE` file.
Raw data
{
"_id": null,
"home_page": "https://github.com/minaskar/zeus",
"name": "zeus-mcmc",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "",
"author": "Minas Karamanis",
"author_email": "minaskar@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/15/c0/248a600ae0f3d1437612821f7c528c895b6a8408a052c352d4cac46dcf94/zeus-mcmc-2.5.4.tar.gz",
"platform": "any",
"description": "\n\n**zeus is a Python implementation of the Ensemble Slice Sampling method.**\n\n- Fast & Robust *Bayesian Inference*,\n- Efficient *Markov Chain Monte Carlo (MCMC)*,\n- Black-box inference, no hand-tuning,\n- Excellent performance in terms of autocorrelation time and convergence rate,\n- Scale to multiple CPUs without any extra effort,\n- Automated Convergence diagnostics.\n\n[](https://github.com/minaskar/zeus)\n[](https://arxiv.org/abs/2002.06212)\n[](https://arxiv.org/abs/2105.03468)\n[](https://ascl.net/2008.010)\n[](https://travis-ci.com/minaskar/zeus)\n[](https://github.com/minaskar/zeus/blob/master/LICENSE)\n[](https://zeus-mcmc.readthedocs.io/en/latest/?badge=latest)\n[](https://pepy.tech/project/zeus-mcmc)\n\n\n## Example\n\nFor instance, if you wanted to draw samples from a 10-dimensional Gaussian, you would do something like:\n\n```python\nimport zeus\nimport numpy as np\n\ndef log_prob(x, ivar):\n return - 0.5 * np.sum(ivar * x**2.0)\n\nnsteps, nwalkers, ndim = 1000, 100, 10\nivar = 1.0 / np.random.rand(ndim)\nstart = np.random.randn(nwalkers,ndim)\n\nsampler = zeus.EnsembleSampler(nwalkers, ndim, log_prob, args=[ivar])\nsampler.run_mcmc(start, nsteps)\nchain = sampler.get_chain(flat=True)\n```\n\n## Documentation\n\nRead the docs at [zeus-mcmc.readthedocs.io](https://zeus-mcmc.readthedocs.io)\n\n\n## Installation\n\nTo install ``zeus`` using ``pip`` run:\n\n```bash\npip install zeus-mcmc\n```\n\nTo install ``zeus`` in a [[Ana]Conda](https://conda.io/projects/conda/en/latest/index.html) environment use:\n\n```bash\nconda install -c conda-forge zeus-mcmc\n```\n\n## Attribution\n\nPlease cite the following papers if you found this code useful in your research:\n\n```bash\n@article{karamanis2021zeus,\n title={zeus: A Python implementation of Ensemble Slice Sampling for efficient Bayesian parameter inference},\n author={Karamanis, Minas and Beutler, Florian and Peacock, John A},\n journal={arXiv preprint arXiv:2105.03468},\n year={2021}\n}\n\n@article{karamanis2020ensemble,\n title = {Ensemble slice sampling: Parallel, black-box and gradient-free inference for correlated & multimodal distributions},\n author = {Karamanis, Minas and Beutler, Florian},\n journal = {arXiv preprint arXiv: 2002.06212},\n year = {2020}\n}\n```\n\n## Licence\n\nCopyright 2019-2021 Minas Karamanis and contributors.\n\nzeus is free software made available under the GPL-3.0 License. For details see the `LICENSE` file.\n",
"bugtrack_url": null,
"license": "GPLv3",
"summary": "zeus: Lightning Fast MCMC",
"version": "2.5.4",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "48cb99ee8021fa305d65b1fb369fabf96ccc65c60282407390e5355bb9e62f9f",
"md5": "2006a06536e91459bf00df4bbaf2fe84",
"sha256": "a64a7dae15f413200c6d590a3edfc3b8bc63c6bea3acdf123c0397c8089e123f"
},
"downloads": -1,
"filename": "zeus_mcmc-2.5.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2006a06536e91459bf00df4bbaf2fe84",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 24122,
"upload_time": "2023-01-12T04:14:19",
"upload_time_iso_8601": "2023-01-12T04:14:19.240714Z",
"url": "https://files.pythonhosted.org/packages/48/cb/99ee8021fa305d65b1fb369fabf96ccc65c60282407390e5355bb9e62f9f/zeus_mcmc-2.5.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "15c0248a600ae0f3d1437612821f7c528c895b6a8408a052c352d4cac46dcf94",
"md5": "94484a0a92700a27dd1a3c43845dbc69",
"sha256": "594baa90de4ad4488c4db5ed6a0446f7103bc4b3de787f4d7d23c91c9aa88769"
},
"downloads": -1,
"filename": "zeus-mcmc-2.5.4.tar.gz",
"has_sig": false,
"md5_digest": "94484a0a92700a27dd1a3c43845dbc69",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 35051,
"upload_time": "2023-01-12T04:14:20",
"upload_time_iso_8601": "2023-01-12T04:14:20.688593Z",
"url": "https://files.pythonhosted.org/packages/15/c0/248a600ae0f3d1437612821f7c528c895b6a8408a052c352d4cac46dcf94/zeus-mcmc-2.5.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-12 04:14:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "minaskar",
"github_project": "zeus",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "zeus-mcmc"
}
JSON
