OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Xai

Xai is an MIT-licensed Python machine-learning library that provides tools for analysing and evaluating datasets and models, with functions for imbalance handling, correlations, balanced data splits, bias-related review and feature-importance analysis.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Xai — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Xai when an existing Python machine-learning workflow needs documented tools for examining data balance, preparing grouped splits, visualising relationships or reviewing inference results against input features.

Who it is for

  • Machine-learning engineers evaluating model behaviour
  • Data scientists analysing dataset balance and feature relationships
  • Domain experts participating in explainability and model-review work

Documented uses

  • Find class imbalances across categorical groups.
  • Prepare balanced training and validation splits.
  • Inspect correlations and group-level data patterns.
  • Relate model predictions to input features through feature-importance analysis.
  • Support explainable-ML experiments covering data and model evaluation.
Before you choose

Requirements & limits

The project is presented as a public GitHub repository with an MIT license. Installation instructions cover PyPI and editable source installation through uv. The repository identifies Python 3.5, 3.6 and 3.7 support and lists Linux, Windows and macOS platforms.

  • It combines dataset analysis and model-evaluation examples rather than focusing only on prediction.
  • The documented workflow includes imbalance plots, balancing, grouped analysis, correlation visualisations and balanced train-test splitting.
  • Permutation feature importance is shown in the model-evaluation section.
  • The repository labels the project release as alpha, so teams should review the project materials and their own environment before adopting it.
  • The documented Python versions are 3.5, 3.6 and 3.7; newer interpreter support is not established here.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Xai for explainable-ML analysis

Set up the Xai Python library using the documented package-manager or source-install route.

Before you start

  • A Python environment compatible with the repository’s documented Python 3.5, 3.6 or 3.7 support.
  • uv installed as the documented Python package manager.
  • Internet access to obtain the package or repository.

Steps

  1. Install uv using the installation method shown in the repository README.

  2. Install the package with the documented PyPI command, or clone the repository and install it in editable mode.

  3. Open the examples folder or the linked example Jupyter Notebook to continue with documented usage.

Expected outcome

Xai is installed and the documented examples are available as the next step for data and model analysis.

Guide limitations

  • The supplied installation guidance does not establish execution results, compatibility beyond the listed Python versions, or the requirements of individual examples.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
EthicalML/xai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction