rguo12/awesome-causality-algorithms
An index of algorithms for learning causality with data
What it solves
This project provides a curated index of algorithms and software tools designed for causal inference and causal machine learning. It addresses the challenge of finding reliable, open-source implementations for tasks like estimating treatment effects, discovering causal relationships in data, and performing root cause analysis.
How it works
The repository acts as a structured directory. It categorizes methods into specific domains—such as causal discovery, treatment effect estimation, and uplift modeling—and links directly to the corresponding academic papers and open-source code repositories. To ensure quality and utility, the maintainers prioritize entries that include accessible, open-source implementations.
Who it’s for
It is intended for researchers, data scientists, and machine learning practitioners who need to implement causal analysis in their work. It serves as a reference for those looking to compare different methodologies or find established libraries for specific causal problems.
Highlights
- Comprehensive index of causal discovery tools and libraries.
- Extensive collection of deep learning and tree-based methods for estimating individual and average treatment effects.
- Dedicated sections for specialized tasks like instrumental variable analysis, dose-response curves, and time-series causal inference.
- Focus on reproducibility by prioritizing entries with available open-source code.
Related
- Project
- Project
- Project
- Project