CausalForge

CausalForge is a Python package that provides a suite of modeling & causal inference methods using machine learning algorithms based on Elevence Health recent research. It provides convenient APIs that allow to estimate Propensity Score, Average Treatment Effect (ATE), Conditional Average Treatment Effect (CATE) or Individual Treatment Effect (ITE) from experimental or observational data. Methods have been redesigned for production. Check out the documentation.

conda env create -f env_mac.yml
conda activate causalforge

git clone https://github.com/anthem-ai/causalforge
cd causalforge
[sudo] pip install -e . [--trusted-host pypi.org --trusted-host files.pythonhosted.org]

pip install --upgrade git+https://github.com/anthem-ai/causalforge [--trusted-host pypi.org --trusted-host files.pythonhosted.org]

pip install causalforge

import causalforge
causalforge.__version__

cd tests
pytest --disable-warnings 

Citation

@article{tesei2023learning,
  title={Learning end-to-end patient representations through self-supervised covariate balancing for causal treatment effect estimation},
  author={Tesei, Gino and Giampanis, Stefanos and Shi, Jingpu and Norgeot, Beau},
  journal={Journal of Biomedical Informatics},
  volume={140},
  pages={104339},
  year={2023},
  publisher={Elsevier}
}