Unified IG

Unified IG provides one small, SHAP-like API for Integrated Gradients across model families. The first implementation supports closed-form attributions for scikit-learn linear models and multilayer perceptrons.

import unifiedig as uig

explainer = uig.Explainer(model, baseline)
explanation = explainer(X)

For numerical backends, the quadrature resolution is configurable:

explainer = uig.Explainer(model, baseline, n_steps=128)

Explanation is lightweight and has SHAP-compatible fields. SHAP remains an optional dependency; call explanation.to_shap() to use its plotting tools.

Installation

During development, install the project and its test dependencies with:

python -m pip install -e ".[test]"

Output semantics

For regression, attributions sum to the difference between the prediction and the baseline prediction. Binary classifiers are explained on their decision-score (logit) scale; probability attributions are not part of V1. See docs/semantics.md for the complete array-shape and output contract.

Numerical explanations expose their observed completeness residual:

explanation.completeness_error
explanation.max_abs_completeness_error

Unified IG warns when this error exceeds the configured tolerance. Increasing n_steps usually improves it. See the examples/ directory for complete linear, logistic, MLP regression, and MLP classification programs.

Supported models

sklearn.linear_model.LinearRegression (closed form)
Binary sklearn.linear_model.LogisticRegression (closed form)
sklearn.neural_network.MLPRegressor (analytic gradients and quadrature)
Binary sklearn.neural_network.MLPClassifier (analytic logit gradients and quadrature)

Development

Run the tests and validate distribution artifacts with:

pytest
python -m build
python -m twine check dist/*

See CONTRIBUTING.md for the development workflow.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

unifiedig-0.1.0.dev1.tar.gz (15.5 kB view details)

Uploaded Aug 2, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

unifiedig-0.1.0.dev1-py3-none-any.whl (10.6 kB view details)

Uploaded Aug 2, 2026 Python 3

File details

Details for the file unifiedig-0.1.0.dev1.tar.gz.

File metadata

Download URL: unifiedig-0.1.0.dev1.tar.gz
Upload date: Aug 2, 2026
Size: 15.5 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for unifiedig-0.1.0.dev1.tar.gz
Algorithm	Hash digest
SHA256	`d35f53a594c6bf70d2dfedbcdbf265a508c85188fb6f2e279884713521fd7186`
MD5	`62f20eae8bf30b2334450182b499cdf9`
BLAKE2b-256	`c218b4ec4a903e6038cbb6eae7c658e650afd545d4fc502a1b46166fd29beb4a`

See more details on using hashes here.

Provenance

The following attestation bundles were made for unifiedig-0.1.0.dev1.tar.gz:

Publisher: release.yml on LudgerHentschel/unifiedig

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: unifiedig-0.1.0.dev1.tar.gz
- Subject digest: d35f53a594c6bf70d2dfedbcdbf265a508c85188fb6f2e279884713521fd7186
- Sigstore transparency entry: 2317048418
- Sigstore integration time: Aug 2, 2026
Source repository:
- Permalink: LudgerHentschel/unifiedig@789a307cab35d2c1c1b7354e28997030d461613c
- Branch / Tag: refs/tags/v0.1.0.dev1
- Owner: https://github.com/LudgerHentschel
- Access: private
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@789a307cab35d2c1c1b7354e28997030d461613c
- Trigger Event: push