# oegedijk/explainerdashboard

Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.

Repository: https://github.com/oegedijk/explainerdashboard
Canonical: https://ross.abutalabs.com/products/explainerdashboard
Homepage: http://explainerdashboard.readthedocs.io
Language: Python
License: MIT
License Family: permissive
Topics: dash, shap-values, dashboard, model-predictions, data-scientists, explainer, interactive-dashboards, permutation-importances, shap, plotly, inner-workings, interactive-plots, xai-library, xai
Last push: 2026-02-11T19:52:59+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 69, longevity 100
- inputs: {"age_days": 2499, "days_push": 203, "days_rel": 206, "gap_med": 2.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2510, forks 348 (observed 2026-08-28T04:06:57.351386+00:00)

## What it is
A Python library for quickly building interactive Explainable AI dashboards that explain the inner workings of scikit-learn compatible machine learning models. It provides interactive plots for model performance, feature importances, SHAP values, partial dependence, and individual prediction explanations, deployable as Dash web apps or static HTML.

## Use cases
- explain a blackbox machine learning model with an interactive dashboard
- show shap values and feature contributions for individual predictions
- visualize feature importances and permutation importance for a model
- build a what-if analysis tool for model predictions
- deploy a model explanation web app for stakeholders
- export model explanation dashboards to static html in ci/cd
- combine multiple model dashboards into a single hub

## When to choose
- you have a scikit-learn, xgboost, lightgbm, or catboost model and need explainability visuals with minimal code
- you want an interactive web dashboard or notebook exploration of model behavior without building a frontend
- you need SHAP values, partial dependence, and decision tree visualizations in one tool

## When to avoid
- you need explainability for non-tabular models like images or text transformers
- you want a fully custom dashboard UI beyond the library's modular components
- your model is not scikit-learn compatible

## Facets
- artifact type: library
- maturity: active
- function: data-visualization, machine-learning, web-framework, charts
- domain: machine-learning, data-science, data-visualization, web-development
- platform: python, cross-platform
- tags: explainable-ai, shap, dash, plotly, model-interpretability, xai, scikit-learn, feature-importance, web-server

## Member repositories
- oegedijk/explainerdashboard (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.351386+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:26.534361+00:00, confidence not recorded.
  - readme: https://github.com/oegedijk/explainerdashboard (fetched 2026-08-28T04:06:57.351386+00:00, sha cd91cff778cf)
  - registry_pypi: https://pypi.org/pypi/explainerdashboard/json (fetched 2026-08-29T10:09:29.416533+00:00, sha 7bf061d30d30)
- Data as of 2026-08-30T08:39:29.467469+00:00.