Skip to content

Latest commit

 

History

History
65 lines (47 loc) · 2.6 KB

README.md

File metadata and controls

65 lines (47 loc) · 2.6 KB

Explaining AI for Construction

Welcome to the Explaining AI for Construction repository, where we focus on demonstrating machine learning techniques that enhance transparency and fairness in construction-related predictions. This repository hosts Jupyter notebooks showcasing different approaches for explainable and fair machine learning, specifically tailored to applications like concrete strength prediction.

Repository Contents

  • ExplanableAi.ipynb - A detailed notebook that walks through several machine learning models. It focuses on predicting concrete strength using various inputs and discusses the models' fairness and explainability. Techniques like SHAP, Explainable Boosting Machine (EBM), and fairness analysis using Fairlearn are covered.

Project Objectives

  • Model Transparency: Illustrate how decisions made by machine learning models can be explained using interpretability tools.
  • Fairness in AI: Assess and promote model fairness across different groups to ensure equitable outcomes.
  • Educational Insight: Provide comprehensive content for stakeholders interested in integrating fairness and explainability into their machine learning workflows.

Getting Started

Prerequisites

To run the notebooks, ensure you have the following installed:

  • Python 3.8 or higher
  • Jupyter Notebook or JupyterLab
  • Required Python libraries: pandas, matplotlib, seaborn, scikit-learn, shap, fairlearn

Installation

  1. Clone this repository: git clone https://github.com/Sparsh009/ExplainingAI-for-Construction.git

css Copy code 2. Navigate to the repository directory: cd ExplainingAI-for-Construction

markdown Copy code 3. Install the required Python libraries: pip install -r requirements.txt

mathematica Copy code

Running the Notebooks

Launch Jupyter Notebook or JupyterLab: jupyter notebook

markdown Copy code Then, open the ExplanableAi.ipynb to view and execute the cells.

Contributing

Contributions are what make the open-source community thrive. Any contributions you make are greatly appreciated.

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

This project is distributed under the MIT License - see the LICENSE file for details.

Contact

Sparsh - sparsh.edu9@gmail.com

Acknowledgments

  • Thanks to all who contribute to this enlightening project.
  • Special thanks to Fairlearn and SHAP contributors for their amazing work