Data found in the real world is messy; it is rare to come across or collect categorical data with perfectly even classes so it is important to learn how to deal with this kind of data. Resampling is a widely used technique for dealing with imbalanced data. This notebook will explore various methods of resampling and see how they effect an unoptimized model's ability to accurately predict a minority class.
joedorfman / imbalanced_data Goto Github PK
View Code? Open in Web Editor NEWThis project forked from aamighty/imbalanced_data