Ananke: A module for causal inference

Ananke, named for the Greek primordial goddess of necessity and causality, is a Python package for causal inference using the language of graphical models.

Ananke provides a Python implementation of causal graphical models with and without unmeasured confounding, with a particular focus on causal identification, semiparametric estimation, and parametric likelihood methods.

Ananke is licensed under Apache 2.0 and source code is available at gitlab.


If you enjoyed this package, we would appreciate the following citation:


Jaron J. R. Lee, Rohit Bhattacharya, Razieh Nabi, and Ilya Shpitser. Ananke: a python package for causal inference using graphical models. 2023. arXiv:2301.11477.

Additional relevant citations also include:


Rohit Bhattacharya, Razieh Nabi, and Ilya Shpitser. Semiparametric inference for causal effects in graphical models with hidden variables. arXiv preprint arXiv:2003.12659, 2020.


Jaron J. R. Lee and Ilya Shpitser. Identification Methods With Arbitrary Interventional Distributions as Inputs. arXiv preprint arXiv:2004.01157 [cs, stat], 2020.


Razieh Nabi, Rohit Bhattacharya, and Ilya Shpitser. Full law identification in graphical models of missing data: completeness results. arXiv preprint arXiv:2004.04872, 2020.


  • Rohit Bhattacharya

  • Jaron Lee

  • Razieh Nabi

  • Preethi Prakash

  • Ranjani Srinivasan


Getting Started

Indices and Tables