LiNG Discovery Algorithm

If you use LiNGD, install R and the muRty package and set the path to Rscript.

Installation

pip install git+https://github.com/cdt15/lingd.git

Usage

from lingd import LiNGD

# create instance and fit to the data.
model = LiNGD()
model.fit(X)

# estimated results
print(model.adjacency_matrices_)

print(model.costs_)

print(model.is_stables_)

# effects of causal effects
print(model.estimate_causal_effects(1))

Example

lingd/examples/lingd.ipynb

References

• Gustavo Lacerda, Peter Spirtes, Joseph Ramsey, and Patrik O. Hoyer. Discovering cyclic causal models by independent components analysis. In Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI'08). AUAI Press, Arlington, Virginia, USA, 366– 374.