Yujia Zheng
Yujia Zheng
Thanks for reporting. Let us work on this and get back to you soon.
Hi @nataliaglazman , could you please try the following code to see if that works in your case? ``` bk = BackgroundKnowledge() \ .add_forbidden_by_node(nodes[0], nodes[1]) \ .add_forbidden_by_node(nodes[1], nodes[0]) \ .add_forbidden_by_node(nodes[1],...
#202 this is a good example written by @OliverSchacht
Yeah I understand that. In order to use a custom CI test, you need to wrap it as a class in [cit.py](https://github.com/py-why/causal-learn/blob/main/causallearn/utils/cit.py), and then directly call it by changing the...
Thanks for the great suggestion. The CI test classes in cit.py just take X, Y and condition set as input and output the p-value, for example: https://github.com/py-why/causal-learn/blob/e4b5f120256b86b9b9656dfbf1ba9e948b1d56ec/causallearn/utils/cit.py#L148 So, including a...
Thanks for reporting this! We are looking into it and will let you know asap.
I guess it is related to the calculations based on covariance in BIC, which may fail due to singularity. Could you please try adding a small Gaussian noise to the...
Honestly, I'm not sure what would be the best way to avoid it--the algorithm does not work if we have singular covariance, which indicates one or more variables might be...
FastKCI is an ongoing work by @OliverSchacht and @Biwei-Huang , so the current implementation might not be the final version. For very large nonlinear datasets, RCIT may also be worth...
aha I see, thanks for reporting. Perhaps @OliverSchacht has more intuition on this?