🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

Validation tasks require prediction attribute?

ben_hben_h Member Posts: 17 Contributor II
edited November 2018 in Help
The Self-Organising Map operator does not generate a Prediction attribute, so therefore it cannot be used in validation tasks? Is there another way to achieve some sort of performance evaluation?

The SOM does return a Preprocessing Model, but I'm not sure how this can be used if I want to map new data to the trained SOM. Can anyone provide an example? I can provide a data set if that's required.

Answers

  • MariusHelfMariusHelf RapidMiner Certified Expert, Member Posts: 1,869   Unicorn
    Hi,

    what do you want to do with the SOM? What do you want to validate?

    To apply the trained SOM to new data, just use the Apply Model operator and connect the preprocessing model produced by the SOM and the new data to it.

    Best regards,
    Marius
Sign In or Register to comment.