# DisCERN-XAI
DisCERN: Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods
### Installing DisCERN
DisCERN supports Python 3+. The stable version of DisCERN is available on [PyPI](https://pypi.org/project/discern-xai/):
pip install discern-xai
To install the dev version of DisCERN and its dependencies, clone this repo and run `pip install` from the top-most folder of the repo:
pip install -e .
DisCERN requires the following packages:<br>
`numpy`<br>
`pandas`<br>
`lime`<br>
`shap`<br>
`scikit-learn`
### Getting Started with DisCERN
Binary Classification example using the Adult Income dataset and RandomForest classifier is in tests/test_adult_income.py
Multi-class Classification example using the Cancer risk dataset and RandomForest classifier is in tests/test_cancer_risk.py
### Citing
Please cite it as follows:
Nirmalie Wiratunga and Anjana Wijekoon and Ikechukwu Nkisi-Orji and Kyle Martin and Chamath Palihawadana and David Corsar (2021). DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods. ArXiv, vol. abs/2109.05800
Bibtex:
@misc{wiratunga2021discerndiscovering,
title={DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods},
author={Nirmalie Wiratunga and Anjana Wijekoon and Ikechukwu Nkisi-Orji and Kyle Martin and Chamath Palihawadana and David Corsar},
year={2021},
eprint={2109.05800},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
<br>
<br>
<br>
<br>
<img align="left" src="isee.png" alt="drawing" height="50"/>
<img align="right" src="chistera.png" alt="drawing" height="50"/><br><br><br>
<center>This research is funded by the <a href="https://isee4xai.com">iSee project</a> which received funding from EPSRC under the grant number EP/V061755/1. iSee is part of the <a href="https://www.chistera.eu/">CHIST-ERA pathfinder programme</a> for European coordinated research on future and emerging information and communication technologies.</center>
Raw data
{
"_id": null,
"home_page": "https://github.com/RGU-Computing/discern-xai",
"name": "discern-xai",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "machine-learning explanation interpretability counterfactual",
"author": "Anjana Wijekoon",
"author_email": "a.wijekoon1@rgu.ac.uk",
"download_url": "https://files.pythonhosted.org/packages/16/0c/0bf7bf8d8ab1f442fb93e08052f79859265dff06cb0729b60d80eaab7130/discern-xai-0.0.25.tar.gz",
"platform": null,
"description": "# DisCERN-XAI\nDisCERN: Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods\n\n### Installing DisCERN\nDisCERN supports Python 3+. The stable version of DisCERN is available on [PyPI](https://pypi.org/project/discern-xai/):\n\n pip install discern-xai\n\nTo install the dev version of DisCERN and its dependencies, clone this repo and run `pip install` from the top-most folder of the repo:\n\n pip install -e .\n\nDisCERN requires the following packages:<br>\n`numpy`<br>\n`pandas`<br>\n`lime`<br>\n`shap`<br>\n`scikit-learn`\n\n\n### Getting Started with DisCERN\n\nBinary Classification example using the Adult Income dataset and RandomForest classifier is in tests/test_adult_income.py\n\nMulti-class Classification example using the Cancer risk dataset and RandomForest classifier is in tests/test_cancer_risk.py\n\n### Citing\n\nPlease cite it as follows:\n\nNirmalie Wiratunga and Anjana Wijekoon and Ikechukwu Nkisi-Orji and Kyle Martin and Chamath Palihawadana and David Corsar (2021). DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods. ArXiv, vol. abs/2109.05800\n\n\nBibtex:\n\n @misc{wiratunga2021discerndiscovering,\n title={DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods}, \n author={Nirmalie Wiratunga and Anjana Wijekoon and Ikechukwu Nkisi-Orji and Kyle Martin and Chamath Palihawadana and David Corsar},\n year={2021},\n eprint={2109.05800},\n archivePrefix={arXiv},\n primaryClass={cs.LG}\n}\n\n\n<br>\n<br>\n<br>\n<br>\n\n<img align=\"left\" src=\"isee.png\" alt=\"drawing\" height=\"50\"/>\n<img align=\"right\" src=\"chistera.png\" alt=\"drawing\" height=\"50\"/><br><br><br>\n<center>This research is funded by the <a href=\"https://isee4xai.com\">iSee project</a> which received funding from EPSRC under the grant number EP/V061755/1. iSee is part of the <a href=\"https://www.chistera.eu/\">CHIST-ERA pathfinder programme</a> for European coordinated research on future and emerging information and communication technologies.</center>\n\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "DisCERN: Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods",
"version": "0.0.25",
"split_keywords": [
"machine-learning",
"explanation",
"interpretability",
"counterfactual"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "2e318fbeabdb1e87e20a749dba39450d",
"sha256": "2212ab6ce1ccf2a2ea55771fda29e348807900b6e12ee63289864e32f47feac0"
},
"downloads": -1,
"filename": "discern_xai-0.0.25-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2e318fbeabdb1e87e20a749dba39450d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 7353,
"upload_time": "2022-12-10T20:45:10",
"upload_time_iso_8601": "2022-12-10T20:45:10.943064Z",
"url": "https://files.pythonhosted.org/packages/c5/d7/e39b5fb44677fd1a73a65429967b1d67847cd652d2b2acceb49cbc383d24/discern_xai-0.0.25-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "5a89be13569eab1c61d8870e511803a2",
"sha256": "72ee189139b67538770e6864064504ec8a7f7d006251fe2a176490d11b176c72"
},
"downloads": -1,
"filename": "discern-xai-0.0.25.tar.gz",
"has_sig": false,
"md5_digest": "5a89be13569eab1c61d8870e511803a2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 5188,
"upload_time": "2022-12-10T20:45:12",
"upload_time_iso_8601": "2022-12-10T20:45:12.812802Z",
"url": "https://files.pythonhosted.org/packages/16/0c/0bf7bf8d8ab1f442fb93e08052f79859265dff06cb0729b60d80eaab7130/discern-xai-0.0.25.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-10 20:45:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "RGU-Computing",
"github_project": "discern-xai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "numpy",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "scikit-learn",
"specs": []
},
{
"name": "heapq",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "lime",
"specs": []
}
],
"lcname": "discern-xai"
}
JSON
