X-Why
XWhy: eXplain Why with SMILE -- Statistical Model-agnostic Interpretability with Local Explanations
Installation
pip install xwhy
Simple Example
import xwhy
import xgboost
# train an XGBoost model
X, y = xwhy.datasets.boston()
model = xgboost.XGBRegressor().fit(X, y)
# explain the model's predictions using xwhy
# (same syntax works for LightGBM, CatBoost, scikit-learn, transformers, Spark, etc.)
explainer = xwhy.Explainer(model)
xwhy_values = explainer(X)
# visualize the first prediction's explanation
xwhy.plots.waterfall(xwhy_values[0])
Citations
It would be appreciated a citation to our paper as follows if you use X-Why for your research:
@article{Aslansefat2021Xwhy,
author = {{Aslansefat}, Koorosh and {Hashemian}, Mojgan and {Martin}, Walker and {Papadopoulos}, Yiannis},
title = "{SMILE: Statistical Model-agnostic Interpretability with Local Explanations}",
journal = {arXiv e-prints},
year = {2021},
url = {https://arxiv.org/abs/...},
eprint = {},
}
Acknowledgment
This project is supported by the Secure and Safe Multi-Robot Systems (SESAME) H2020 Project under Grant Agreement 101017258.
Contribution
If you are interested in contributing to this project, please check the contribution guidelines.
2 maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file xwhy-0.0.3.tar.gz.
File metadata
- Download URL: xwhy-0.0.3.tar.gz
- Upload date:
- Size: 62.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bedf3575cfe15ccbcf2b7133da0dc3c62ac5381be044b9e0599215137467664c
|
|
| MD5 |
dfc181a798d205d971a4fe52dd938cb9
|
|
| BLAKE2b-256 |
a48a4d2b830bbfaf9b7a6f37d5c4c6b5be61dcf5f271fff605937dedf74a7488
|
Provenance
The following attestation bundles were made for xwhy-0.0.3.tar.gz:
Publisher:
publish.yml on Dependable-Intelligent-Systems-Lab/xwhy
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
xwhy-0.0.3.tar.gz -
Subject digest:
bedf3575cfe15ccbcf2b7133da0dc3c62ac5381be044b9e0599215137467664c - Sigstore transparency entry: 2271764543
- Sigstore integration time:
-
Permalink:
Dependable-Intelligent-Systems-Lab/xwhy@f690851aec76277fb6f32393183c823d26c1b514 -
Branch / Tag:
refs/tags/v0.0.3 - Owner: https://github.com/Dependable-Intelligent-Systems-Lab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@f690851aec76277fb6f32393183c823d26c1b514 -
Trigger Event:
push
-
Statement type:
File details
Details for the file xwhy-0.0.3-py3-none-any.whl.
File metadata
- Download URL: xwhy-0.0.3-py3-none-any.whl
- Upload date:
- Size: 98.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2deec34cba802207e2f8307c67f6018de510cfdba7c66794441cc021229c4e5a
|
|
| MD5 |
3ea7a5347490256ff45216c02cdb131e
|
|
| BLAKE2b-256 |
bd302845e443df7c99b41e6a0031506ad040f2ed1ff24813623826d864ba456f
|
Provenance
The following attestation bundles were made for xwhy-0.0.3-py3-none-any.whl:
Publisher:
publish.yml on Dependable-Intelligent-Systems-Lab/xwhy
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
xwhy-0.0.3-py3-none-any.whl -
Subject digest:
2deec34cba802207e2f8307c67f6018de510cfdba7c66794441cc021229c4e5a - Sigstore transparency entry: 2271764604
- Sigstore integration time:
-
Permalink:
Dependable-Intelligent-Systems-Lab/xwhy@f690851aec76277fb6f32393183c823d26c1b514 -
Branch / Tag:
refs/tags/v0.0.3 - Owner: https://github.com/Dependable-Intelligent-Systems-Lab
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@f690851aec76277fb6f32393183c823d26c1b514 -
Trigger Event:
push
-
Statement type:
