Skip to main content

ibreakdown - model agnostic explanations with interactions

Project description


ibreakdown is model agnostic predictions explainer with interactions support, library can show contribution of each feature in your prediction value.

SHAP or LIME consider only local additive feature attributions, when ibreakdown also evaluates local feature interactions.


Algorithm is based on ideas describe in paper “iBreakDown: Uncertainty of Model Explanations for Non-additive Predictive Models” and reference implementation in R (iBreakDown)

Intuition behind algorithm is following:

The algorithm works in a similar spirit as SHAP or Break Down but is not
restricted to additive effects. The intuition is the following:

1. Calculate a single-step additive contribution for each feature.
2. Calculate a single-step contribution for every pair of features. Subtract additive contribution to assess the interaction specific contribution.
3. Order interaction effects and additive effects in a list that is used to determine sequential contributions.

This simple intuition may be generalized into higher order interactions.

In depth explanation can be found in algorithm authors free book: Predictive Models: Explore, Explain, and Debug


  • Supports predictions explanations for classification and regression

  • Easy to use API.

  • Works with pandas and numpy

  • Support interactions between features


Installation process is simple, just:

$ pip install ibreakdown



Project details

Download files

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

Source Distribution

ibreakdown-0.0.1a3.tar.gz (8.7 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page