CAUSAL INFERENCE: TIGRAMITE
We contributed to the continuous development of the tigramite (https://github.com/jakobrunge/tigramite/) Python package for causal inference methods.
This package provides a wide range of constraint-based causal discovery and causal effect estimation methods.
Description
A particular focus in the XAIDA-related developments was the implementation of mixed-type non-parametric conditional independence tests applicable also to synergistic problems, non-stationary causal discovery methods, and non-parametric causal mediation methods for the estimation of direct and indirect effects in mixed-type data; mediation analysis can also inform about which pathways a particular effect should be attributed to.
Potential User Groups
- Researchers, in applied packages of XAIDA or otherwise concerned with causal relations in climate (or similar) data.
- Technically interested planners or engineers who wish to quantify the effect of interventions or supplement their causal understanding of a problem.
Guide
An extensive guide and many tutorials can be found in the GitHub repository https://github.com/jakobrunge/tigramite/.
Availability
The tool is a pip-installable Python package. It can be used with basic knowledge of the Python programming language.
Use Cases
For a list of in-depth tutorials as well as use cases see https://github.com/jakobrunge/tigramite/tree/master/tutorials/.
References
Detecting causal associations in large nonlinear time series datasets. J. Runge, P. Nowack, M. Kretschmer, S. Flaxman, and D. Sejdinovic. Science Advances 5(11): eaau4996 (2019).
Causal network reconstruction from time series: From theoretical assumptions to practical estimation. J. Runge. Chaos: An Interdisciplinary Journal of Nonlinear Science, 28:7 (2018).
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101003469.
Tools
Ensemble boosting uses climate models to efficiently generate very intense and rare weather and climate extremes that can be analyzed for planning and stress testing of critical infrastructure.