Causal Dataset for cause-effect pairs from Tubingen repository

Cause-effect is a two dimensional database with two-variable cause-effect pairs chosen from the different datasets created by Max-Planck-Institute for Biological Cybernetics in Tuebingen, Germany.

Size: 83 datasets of various sizes

Number of features: 2 in every datasets

Ground truth: avalaible for every dataset

Type of Graph: directed

Extension of the datasets used in CauseEffectPairs task.  Each dataset  consists of samples of a pair of statistically dependent random variables, where one variable is known to cause the other one. The task is to identify for each pair which of the two variables is the cause and which one the effect, using the observed samples only

More information about the dataset is contained in causal_description.html file.

Reference

J. M. Mooij, J. Peters, D. Janzing, J. Zscheischler, B. Schoelkopf: “Distinguishing cause from effect using observational data: methods and benchmarks”, Journal of Machine Learning Research 17(32):1-102, 2016