This repository contains Python notebooks and SAS programs that demonstrate key principles of Trustworthy AI, including fairness, robustness, and explainability. The examples use publicly available datasets across multiple sectors such as financial services, education, healthcare, and the public sector.
The examples require access to the SAS® Viya® Workbench.
Clone the examples repository into the root of your workspace:
git clone https://github.com/sassoftware/sas-trustworthy-ai-examples.git
cd sas-trustworthy-ai-examples- Create a Virtual Environment
python -m venv venv- Activate the Virtual Environment
On macOS/Linux:
source venv/bin/activateOn Windows:
venv\Scripts\activate- Install Required Python Packages
pip install -r requirements.txt- Run Examples
Navigate to the python/ directory and open a notebook or script.
The repository is organized into the following folders:
data/— Contains datasets for all 4python/— Contains Python-based Trustworthy AI examplesas/— Contains equivalent SAS code examples
Example datasets include:
- Adult Dataset
- Student Performance Dataset
- German Credit Data
- CDC Diabetes Health Indicators
Maintainers are not currently accepting contributions to this project.
This project is licensed under the Apache 2.0 License. See LICENSE for details.