# GPyConform
GPyConform extends the GPyTorch library to implement Gaussian Process Regression Conformal Prediction based on the approach described in [1].
Designed to work seamlessly with Exact Gaussian Process (GP) models, GPyConform enhances GPyTorch by introducing the capability to generate
and evaluate both 'symmetric' and 'asymmetric' Conformal Prediction Intervals.
## Key Features
- **Provides Provably Valid Prediction Intervals**: Provides Prediction Intervals with guaranteed coverage under minimal assumptions (data exchangeability).
- **Inherits All GPyTorch Functionality**: Utilizes the robust and efficient GP modeling capabilities of GPyTorch.
- **Supports Both Symmetric and Asymmetric Prediction Intervals**: Implements both Full Conformal Prediction approaches for constructing Prediction Intervals.
### Note
Currently, GPyConform is tailored specifically for Exact GP models combined with any covariance function that employs an exact prediction strategy.
## Documentation
For detailed documentation and usage examples, see [GPyConform Documentation](https://gpyconform.readthedocs.io).
## Installation
From [PyPI](https://pypi.org/project/gpyconform/)
```bash
pip install gpyconform
```
From [conda-forge](https://anaconda.org/conda-forge/gpyconform)
```bash
conda install conda-forge::gpyconform
```
## Citing GPyConform
If you use `GPyConform` for a scientific publication, you are kindly requested to cite the following paper:
Harris Papadopoulos. Guaranteed Coverage Prediction Intervals with Gaussian Process Regression. *IEEE Transactions on Pattern Analysis and Machine Intelligence*, 2024. DOI: [10.1109/TPAMI.2024.3418214](https://doi.org/10.1109/TPAMI.2024.3418214).
([arXiv version](https://arxiv.org/abs/2310.15641))
Bibtex entry:
```bibtex
@ARTICLE{gprcp,
author={Papadopoulos, Harris},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Guaranteed Coverage Prediction Intervals with Gaussian Process Regression},
year={2024},
volume={},
number={},
pages={1-12},
doi={10.1109/TPAMI.2024.3418214}
}
```
## References
<a id="1">[1]</a> Harris Papadopoulos. Guaranteed Coverage Prediction Intervals with Gaussian Process Regression. *IEEE Transactions on Pattern Analysis and Machine Intelligence*, 2024. DOI: [10.1109/TPAMI.2024.3418214](https://doi.org/10.1109/TPAMI.2024.3418214).
([arXiv version](https://arxiv.org/abs/2310.15641))
<a id="2">[2]</a> Vladimir Vovk, Alexander Gammerman, and Glenn Shafer. *Algorithmic Learning in a Random World*, 2nd Ed. Springer, 2023. DOI: [10.1007/978-3-031-06649-8](https://doi.org/10.1007/978-3-031-06649-8).
- - -
Author: Harris Papadopoulos (h.papadopoulos@frederick.ac.cy) /
Copyright 2024 Harris Papadopoulos /
License: BSD 3 clause
Raw data
{
"_id": null,
"home_page": "https://github.com/harrisp/GPyConform",
"name": "gpyconform",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "Gaussian Process Regression, Conformal Prediction, Prediction Regions, Prediction Intervals, Uncertainty Quantification, Coverage Guarantee, Normalized Nonconformity",
"author": "Harris Papadopoulos",
"author_email": "h.papadopoulos@frederick.ac.cy",
"download_url": "https://files.pythonhosted.org/packages/e9/57/e5c718eeb04bf3f853ac13d8f675502fd7585cf42f83668e948e62458d39/gpyconform-0.1.0.tar.gz",
"platform": null,
"description": "# GPyConform\r\nGPyConform extends the GPyTorch library to implement Gaussian Process Regression Conformal Prediction based on the approach described in [1]. \r\nDesigned to work seamlessly with Exact Gaussian Process (GP) models, GPyConform enhances GPyTorch by introducing the capability to generate \r\nand evaluate both 'symmetric' and 'asymmetric' Conformal Prediction Intervals.\r\n\r\n## Key Features\r\n- **Provides Provably Valid Prediction Intervals**: Provides Prediction Intervals with guaranteed coverage under minimal assumptions (data exchangeability).\r\n- **Inherits All GPyTorch Functionality**: Utilizes the robust and efficient GP modeling capabilities of GPyTorch.\r\n- **Supports Both Symmetric and Asymmetric Prediction Intervals**: Implements both Full Conformal Prediction approaches for constructing Prediction Intervals.\r\n\r\n### Note\r\nCurrently, GPyConform is tailored specifically for Exact GP models combined with any covariance function that employs an exact prediction strategy.\r\n\r\n## Documentation\r\n\r\nFor detailed documentation and usage examples, see [GPyConform Documentation](https://gpyconform.readthedocs.io).\r\n\r\n## Installation\r\n\r\nFrom [PyPI](https://pypi.org/project/gpyconform/)\r\n\r\n```bash\r\npip install gpyconform\r\n```\r\n\r\nFrom [conda-forge](https://anaconda.org/conda-forge/gpyconform)\r\n\r\n```bash\r\nconda install conda-forge::gpyconform\r\n```\r\n\r\n## Citing GPyConform\r\n\r\nIf you use `GPyConform` for a scientific publication, you are kindly requested to cite the following paper:\r\n\r\nHarris Papadopoulos. Guaranteed Coverage Prediction Intervals with Gaussian Process Regression. *IEEE Transactions on Pattern Analysis and Machine Intelligence*, 2024. DOI: [10.1109/TPAMI.2024.3418214](https://doi.org/10.1109/TPAMI.2024.3418214).\r\n([arXiv version](https://arxiv.org/abs/2310.15641))\r\n\r\nBibtex entry:\r\n\r\n```bibtex\r\n@ARTICLE{gprcp,\r\n author={Papadopoulos, Harris},\r\n journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, \r\n title={Guaranteed Coverage Prediction Intervals with Gaussian Process Regression}, \r\n year={2024},\r\n volume={},\r\n number={},\r\n pages={1-12},\r\n doi={10.1109/TPAMI.2024.3418214}\r\n}\r\n```\r\n\r\n## References\r\n\r\n<a id=\"1\">[1]</a> Harris Papadopoulos. Guaranteed Coverage Prediction Intervals with Gaussian Process Regression. *IEEE Transactions on Pattern Analysis and Machine Intelligence*, 2024. DOI: [10.1109/TPAMI.2024.3418214](https://doi.org/10.1109/TPAMI.2024.3418214). \r\n([arXiv version](https://arxiv.org/abs/2310.15641))\r\n\r\n<a id=\"2\">[2]</a> Vladimir Vovk, Alexander Gammerman, and Glenn Shafer. *Algorithmic Learning in a Random World*, 2nd Ed. Springer, 2023. DOI: [10.1007/978-3-031-06649-8](https://doi.org/10.1007/978-3-031-06649-8).\r\n\r\n\r\n- - -\r\n\r\nAuthor: Harris Papadopoulos (h.papadopoulos@frederick.ac.cy) / \r\nCopyright 2024 Harris Papadopoulos / \r\nLicense: BSD 3 clause\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Extends GPyTorch with Gaussian Process Regression Conformal Prediction",
"version": "0.1.0",
"project_urls": {
"Bug Tracker": "https://github.com/harrisp/GPyConform/issues",
"Homepage": "https://github.com/harrisp/GPyConform"
},
"split_keywords": [
"gaussian process regression",
" conformal prediction",
" prediction regions",
" prediction intervals",
" uncertainty quantification",
" coverage guarantee",
" normalized nonconformity"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "055e3aabb7f9280ad146281081a29d77367d7bae9e2766a46a6cd35e6ab17c8f",
"md5": "43e73a205af458358b6317701bcef8f7",
"sha256": "2943e816087b5b861aa68b08057f4afd4dc00692eb90cdb77c6d7b2985fe5ed7"
},
"downloads": -1,
"filename": "gpyconform-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "43e73a205af458358b6317701bcef8f7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 14039,
"upload_time": "2024-10-14T18:38:25",
"upload_time_iso_8601": "2024-10-14T18:38:25.574132Z",
"url": "https://files.pythonhosted.org/packages/05/5e/3aabb7f9280ad146281081a29d77367d7bae9e2766a46a6cd35e6ab17c8f/gpyconform-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e957e5c718eeb04bf3f853ac13d8f675502fd7585cf42f83668e948e62458d39",
"md5": "ca619eb4bbe010cc80f081adcba6030d",
"sha256": "741f304bb35a65ecf5d7ef3a19b002e7b5363761cf20f70752f2cdb344ef4dad"
},
"downloads": -1,
"filename": "gpyconform-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "ca619eb4bbe010cc80f081adcba6030d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 12579,
"upload_time": "2024-10-14T18:38:27",
"upload_time_iso_8601": "2024-10-14T18:38:27.846971Z",
"url": "https://files.pythonhosted.org/packages/e9/57/e5c718eeb04bf3f853ac13d8f675502fd7585cf42f83668e948e62458d39/gpyconform-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-14 18:38:27",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "harrisp",
"github_project": "GPyConform",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "gpyconform"
}
JSON
