In my dataset, I have 2 features that are not only correlated but that makes sense only in the presence of each other. For instance, one would be the number of times a task was attempted and the other one would be the number of successes.

As mentioned, it seems to be me that taken one of the 2 individually does not give any information. Should I do a scheme where if I pick one of them in a tree of my RF, I automatically include the other one?

And if so, is it possible to do so using the RF class from scikit-learn?



Are you certain the features are mathematically correlated? From what i understand, you are assuming correlation just because the features are conceptually related. If there is some skill (or even luck) involved in the process you are studying, the two features shouldn't be too strongly correlated.

It seems you want to combine the information in the two features. So why not create a new feature measuring the success rate? (# of trails / # of successes).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.