🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉
Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.
"Feature selection step by step choice"
does anybody know if you can choose step by step an attributes subset with FeatureSelection operator? My problem is that FeatureSelection operator doesn't allow me to choose the new attributes which don't increase performance. It is done automatically, so I can't explain its choice when it finds an higher performance after some generations.
For example, I want my model makes a fixed number of maximum_number_of_generation and I know that k of these generations in the first part of the running don't increase the model accuracy. As FeatureSelection operator already makes in the last population with user_result_individual_selection checked, I would like to decide it step by step.