I want to find some causal relationship from some cols to label what i defined by from_pandas(no tears),but i got some causal relationship from label to others about causalnex HOT 2 CLOSED

Hi @ziyuwzf,

This graph shows that the strongest conditional dependencies are present between these variables within this particular dataset. While NOTEARS provides a good starting point for structure identification, this structure captures conditional dependencies and not necessarily a causal relationship. Causal structure should be validated based on domain knowledge.

Feel free to use parameters like 'W-Threshold' , 'beta' (for from_pandas_lasso) as well as run data preprocessing (e.g. scaling, discretizing, encoding etc.) to get a graph that is the closest to your domain knowledge.

from causalnex.

Closing this for now. Do let us know if playing with the (hyper-)parameters doesn't help.

from causalnex.