I wanted to know the multivariate approach to impute the categorical data. It is apparent that if I want to us sklearn.impute.IterativeImputer I need to encode the categorical variables. But by which method? Label encoding will introduce unnecessary ordinal relationship. If i use one hot encoding then what is the right procedure? (Please consider providing an example) I have been searching for long in google and chatgpt but couldn't get a satisfactory answer.
$\begingroup$ $\endgroup$
Add a comment |