XGBoost Optimal Partitioning

Newer version of XGBoost have an “Optimal Partitioning” methodology for handling categorical features.
Does Knime, or will Knime, have an option for implementing this “Optimal Partitioning” methodology in the XGBoost integration extension?
What version of XGBoost is used under the hood?


Dear @bradmc2,

the underlying versions are
xgboost4j_2.12-1.5.1 and scala-library-2.12.14
We currently do not plan to integrate this feature but I’ve recorded your request in the ticket AP-20957.

Best regards


This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.