could someone tell me how to use marker values to deal efficiently with missing values for numerical and categorical features ? I am mainly working with pandas and sklearn libraries.

  • $\begingroup$ I have to mention the reason why I am asking that question. I have to deal with a numerical feature with natural Nan values I cannot impute (for example it could be a measure made after a particular event occurred but before a given time. If the event did not happen there is no measure and there will never be any). $\endgroup$ – Fabrice BOUCHAREL May 6 '19 at 20:02

Your Answer

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

Browse other questions tagged or ask your own question.