🥳 RAPIDMINER 9.9 IS OUT!!! 🥳

The updates in 9.9 power advanced use cases and offer productivity enhancements for users who prefer to code.

CLICK HERE TO DOWNLOAD

Normalization Issue and RapidMiner Community 4.2 (Windows 32)

DarrellDarrell Member Posts: 16  Maven
edited November 2018 in Help
I cannot get RapidMiner Community 4.2 (Windows 32) to properly normalize output variables.  I've created identical Operator Trees in versions 4.1 and 4.2, and while version 4.1 will properly normalize output values, version 4.2 will not.  To test, create a simple linear regression problem then save the output model.  Then create another tree to import the saved model and data--when the program is run the results will not be normalized.  Has anyone else had this same problem in v 4.2?  Thanks...

Answers

  • TobiasMalbrechtTobiasMalbrecht Moderator, Employee, Member Posts: 291  RM Product Management
    Hi Darrell,

    unfortunately I do not quite understand your problem. What exactly is not normalized? It would be great, if you could explain it a little bit more in depth. And would you mind sending us the process you consider as to give faulty results?

    Thanks!

    Regards,
    Tobias
  • IngoRMIngoRM Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, Community Manager, RMResearcher, Member, University Professor Posts: 1,750  RM Founder
    Hi,

    I think I have a clue which makes the difference between 4.1 and 4.2: did you activate the "create_preprocessing_model" parameter for the Normalization operator? In versions < 4.2 you did not have to combine the models (the preprocessing model and the prediction model) yourself but this was done automatically by RapidMiner. Unfortunately, this automatic combination was rather restrictive for more complex models and so we replaced the automatic combinations with two operators "GroupModel" and "UngroupModel" (see the change log for version 4.2) which can be used to group two or more models (like the grouping in powerpoint etc.). This gives you more flexibility in creating and, well, grouping your models.

    If you have a setup like

    - Load Data
    - Normalize Data and create preprocessing model
    - Learn Prediction Model
    - Save (automatically combined) Model

    you can simply add the model grouping operator like in this example:

    - Load Data
    - Normalize Data and create preprocessing model
    - Learn Prediction Model
    - apply "GroupModel"    <-- new step
    - Save (automatically combined) Model


    Hope that helps,
    Ingo
Sign In or Register to comment.