How can I handle rare levels in my categorical variables?

5 vues

Réponse

You can use the 'GROUPRARE' method. The 'preprocessRare' parameter, when set to True, groups rare levels at the start. The rarity is determined by 'rareThreshold' (a frequency count) or 'rareThresholdPercent' (a percentage of total observations). Levels falling below this threshold are combined into a single group.
Did this answer help you?
catTrans

dataPreprocess

See technical action
Other questions about catTrans
Which grouping techniques are considered supervised and what do they require? What is one-hot encoding and how is it implemented in the catTrans action? Can I generate SAS DATA step code for scoring from this action? How can I handle rare levels of a categorical variable using this action? What is the purpose of the catTrans action?
Copyright © WeAreCAS 2014-2026
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. WeAreCAS is an independent community site and is not affiliated with SAS Institute Inc.