mckinsey / causalnex

A Python library that helps data scientists to infer causation rather than observing correlation.

Home Page:http://causalnex.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

the same process different results

he-weisong opened this issue · comments

Run the latest version of causalnex with the same two pieces of code before and after the intervention but with different results

Hello thank you for reaching out!
Interventions can be made using the do_intervention method provided in the InferenceEngine class. They can be reversed by using the reset_intervention method. This will give you the original distribution before the intervention was made. An example can be found in the last Do Calculus section of this notebook.
We hope this helps! If not, please feel free to reach out again. You are more than welcome to share specific code snippets. This will help us understand your issue even better.