This library provides an up-to-date implementation of Relational Causal Model [1,2,3,4], which provides classes for presenting relational schema, skeleton, and ground graphs. RpCD, a sound and (only) complete structure learning algorithm [4] is developed with theoretical evaluation in mind. To learn a causal structure from real data, please check out a separate library RRCD, robust relational causal discovery [5], which is dependent on this library developed by the same author.

[1] Marc Maier, Brian Taylor, Huseyin Oktay, and David Jensen (2010). AAAI. Learning Causal Models of Relational Domains.

[2] Marc Maier, Katerina Marazopoulou, David Arbour, and David Jensen (2013). UAI. A Sound and Complete Algorithm for Learning Causal Models from Relational Data

[3] Sanghack Lee and Vasant Honavar (2016). AAAI. On Learning Causal Models from Relational Data

[4] Sanghack Lee and Vasant Honavar (2016). UAI. A Characterization of Markov Equivalence Classes for Relational Causal Model with Path Semantics.

[5] Sanghack Lee and Vasant Honavar (2019). UAI. Towards Robust Relational Causal Discovery.