<p align="center">
<img src="https://raw.githubusercontent.com/givasile/effector/main/docs/docs/static/effector_logo.png" width="500"/>
</p>
[](https://badge.fury.io/py/effector)


[](https://github.com/givasile/effector/actions/workflows/run_tests.yml)
[](https://pepy.tech/projects/effector)
[](https://github.com/ambv/black)
---
[Documenation](https://xai-effector.github.io/) | [Global Effect](https://xai-effector.github.io/global_effect_intro/) | [Regional Effect](https://xai-effector.github.io/regional_effect_intro/) | [API](https://xai-effector.github.io/api/) | [Tutorials](https://xai-effector.github.io/)
`Effector` is a python package for global and regional effect analysis.
### Installation
`Effector` is compatible with `Python 3.7+`. We recommend to first create a virtual environment with `conda`:
```bash
conda create -n effector python=3.11
conda activate effector
```
and then install `Effector` via `pip`:
```bash
pip install effector
```
If you want to also run the Tutorial notebooks, add some more dependencies to the environment:
```bash
pip install -r requirements-dev.txt
```
## Methods and Publications
### Methods
`Effector` implements the following methods:
| Method | Global Effect | Regional Effect | Paper |
|----------|-----------------------------------------------------------|-------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|
| PDP | [`PDP`](./api/#effector.global_effect_pdp.PDP) | [`RegionalPDP`](./api/#effector.regional_effect_pdp.RegionalPDP) | [PDP](https://projecteuclid.org/euclid.aos/1013203451), [ICE](https://arxiv.org/abs/1309.6392), [GAGDET-PD](https://arxiv.org/pdf/2306.00541.pdf) |
| d-PDP | [`DerPDP`](./api/#effector.global_effect_pdp.DerPDP) | [`RegionalDerPDP`](./api/#effector.regional_effect_pdp.RegionalDerPDP) | [d-PDP, d-ICE](https://arxiv.org/abs/1309.6392) |
| ALE | [`ALE`](./api/#effector.global_effect_ale.ALE) | [`RegionalALE`](./api/#effector.regional_effect_ale.RegionalALE) | [ALE](https://academic.oup.com/jrsssb/article/82/4/1059/7056085), [GAGDET-ALE](https://arxiv.org/pdf/2306.00541.pdf) |
| RHALE | [`RHALE`](./api/#effector.global_effect_ale.RHALE) | [`RegionalRHALE`](./api/#effector.regional_effect_ale.RegionalRHALE) | [RHALE](https://ebooks.iospress.nl/doi/10.3233/FAIA230354), [DALE](https://proceedings.mlr.press/v189/gkolemis23a/gkolemis23a.pdf) |
| SHAP-DP | [`ShapDP`](./api/#effector.global_effect_shap.ShapDP) | [`RegionalShapDP`](./api/#effector.regional_effect_shap.RegionalShapDP) | [SHAP](https://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions), [GAGDET-DP](https://arxiv.org/pdf/2306.00541.pdf) |
Raw data
{
"_id": null,
"home_page": null,
"name": "effector",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "Julia Herbinger <julia.herbinger@gmail.com>, Christos Diou <cdiou@hua.gr>, Giuseppe Casalicchio <giuseppe.casalicchio@gmail.com>",
"keywords": "explainability, machine learning, deep learning, interpretability, feature effect",
"author": null,
"author_email": "Vasilis Gkolemis <ntipakos@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/17/67/25d3cbe966403d366c126f9a610600cebeca8ba18f6abc56ca4df5f2d518/effector-0.1.0.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img src=\"https://raw.githubusercontent.com/givasile/effector/main/docs/docs/static/effector_logo.png\" width=\"500\"/>\n</p>\n\n\n[](https://badge.fury.io/py/effector)\n\n\n[](https://github.com/givasile/effector/actions/workflows/run_tests.yml)\n[](https://pepy.tech/projects/effector)\n[](https://github.com/ambv/black)\n---\n\n[Documenation](https://xai-effector.github.io/) | [Global Effect](https://xai-effector.github.io/global_effect_intro/) | [Regional Effect](https://xai-effector.github.io/regional_effect_intro/) | [API](https://xai-effector.github.io/api/) | [Tutorials](https://xai-effector.github.io/)\n\n`Effector` is a python package for global and regional effect analysis.\n\n### Installation\n\n`Effector` is compatible with `Python 3.7+`. We recommend to first create a virtual environment with `conda`:\n\n```bash\nconda create -n effector python=3.11\nconda activate effector\n```\n\nand then install `Effector` via `pip`:\n\n```bash\npip install effector\n```\n\nIf you want to also run the Tutorial notebooks, add some more dependencies to the environment:\n\n```bash\npip install -r requirements-dev.txt\n```\n\n## Methods and Publications\n\n### Methods\n\n`Effector` implements the following methods:\n\n| Method | Global Effect | Regional Effect | Paper | \n|----------|-----------------------------------------------------------|-------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|\n| PDP | [`PDP`](./api/#effector.global_effect_pdp.PDP) | [`RegionalPDP`](./api/#effector.regional_effect_pdp.RegionalPDP) | [PDP](https://projecteuclid.org/euclid.aos/1013203451), [ICE](https://arxiv.org/abs/1309.6392), [GAGDET-PD](https://arxiv.org/pdf/2306.00541.pdf) |\n| d-PDP | [`DerPDP`](./api/#effector.global_effect_pdp.DerPDP) | [`RegionalDerPDP`](./api/#effector.regional_effect_pdp.RegionalDerPDP) | [d-PDP, d-ICE](https://arxiv.org/abs/1309.6392) | \n| ALE | [`ALE`](./api/#effector.global_effect_ale.ALE) | [`RegionalALE`](./api/#effector.regional_effect_ale.RegionalALE) | [ALE](https://academic.oup.com/jrsssb/article/82/4/1059/7056085), [GAGDET-ALE](https://arxiv.org/pdf/2306.00541.pdf) | \n| RHALE | [`RHALE`](./api/#effector.global_effect_ale.RHALE) | [`RegionalRHALE`](./api/#effector.regional_effect_ale.RegionalRHALE) | [RHALE](https://ebooks.iospress.nl/doi/10.3233/FAIA230354), [DALE](https://proceedings.mlr.press/v189/gkolemis23a/gkolemis23a.pdf) |\n| SHAP-DP | [`ShapDP`](./api/#effector.global_effect_shap.ShapDP) | [`RegionalShapDP`](./api/#effector.regional_effect_shap.RegionalShapDP) | [SHAP](https://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions), [GAGDET-DP](https://arxiv.org/pdf/2306.00541.pdf) |\n\n",
"bugtrack_url": null,
"license": null,
"summary": "A Python library for global and regional effects",
"version": "0.1.0",
"project_urls": {
"documentation": "https://xai-effector.github.io",
"source": "https://github.com/givasile/effector",
"tracker": "https://github.com/givasile/effector/issues"
},
"split_keywords": [
"explainability",
" machine learning",
" deep learning",
" interpretability",
" feature effect"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "00a863330770d516700304a48bfac2eb7a0576e5a20fb09bcba7e6419b371df9",
"md5": "0897ed14fe05bab712bc2e58006a3d06",
"sha256": "c31bf5bcfb7f8c171a2b81512204962968d0aa89f78cd9eb1eb30ce8c6c358d6"
},
"downloads": -1,
"filename": "effector-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0897ed14fe05bab712bc2e58006a3d06",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 53898,
"upload_time": "2025-02-17T11:39:20",
"upload_time_iso_8601": "2025-02-17T11:39:20.927599Z",
"url": "https://files.pythonhosted.org/packages/00/a8/63330770d516700304a48bfac2eb7a0576e5a20fb09bcba7e6419b371df9/effector-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "176725d3cbe966403d366c126f9a610600cebeca8ba18f6abc56ca4df5f2d518",
"md5": "2ccc24d831a5394d81e9e040459fc62a",
"sha256": "5dabc66ec27093f830837f4fe9d8eecdb6e5e4886180865fba45c2a605b07df9"
},
"downloads": -1,
"filename": "effector-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "2ccc24d831a5394d81e9e040459fc62a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 41734,
"upload_time": "2025-02-17T11:39:23",
"upload_time_iso_8601": "2025-02-17T11:39:23.114124Z",
"url": "https://files.pythonhosted.org/packages/17/67/25d3cbe966403d366c126f9a610600cebeca8ba18f6abc56ca4df5f2d518/effector-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-17 11:39:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "givasile",
"github_project": "effector",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "effector"
}