Different Strategy For Different Column of missing values

Question

I'm think of like if I have 2 or more columns with missing values and As per my interpretation i think 1st column's NA value could be 0 (by-fillna() for better result and for 2nd column's its may be mean( or median) or May be 3rd column could be any constant value.(by simpleImputer). What would be best approach solve it. Thanks..

Answer 1

If you're trying to create something general, you're better off creating a Pipeline or ColumnTransformer from sklearn.

This answer explains it in detail.