The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

return preprocessing model in Normalize operator

dirk120dirk120 Member Posts: 8 Contributor II
edited November 2018 in Help
I can't find the  "return preprocessing model" parameters even in expert mode. The description indictates that the operator supports this parameter. I run version 5.0.006
Does anyone have an idea?

Thanks,
Dirk

Answers

  • haddockhaddock Member Posts: 849 Maven
    Hi Dirk, and welcome!

    In short, it is not a parameter - it is boolean that you select if you want the normalisation model to be returned, You would use such a model to normalise other examplesets in a compatible way. Hope that is comprehensible  :D
  • dirk120dirk120 Member Posts: 8 Contributor II
    But how can I select it? It thus not appear on configuration menu of the operator.

    Thanks,
    Dirk
  • haddockhaddock Member Posts: 849 Maven
    Mmm, the last time I used this was under 4.6, and it looks as though the documentation is not in step with the code ( 5.006 does not have this as an option in the code and just delivers the model ). Actually given the 'ports' feature of 5.00N this makes sense.

    I should ignore this, it can hardly be material,  it would not be the first request for co-ordinated dox, but let it join the queue  >:(

    Ciao
  • dirk120dirk120 Member Posts: 8 Contributor II
    I'm not sure whether the model is returned. Export and results do not show any model data.
  • haddockhaddock Member Posts: 849 Maven
    On my setup it is returned at the lower output port - marked 'pre' ( for pre-processing model )?
  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,531 Unicorn
    Hi,
    haddock is right (as so often): The preprocessing model is now returned if the "pre" port is connected to another operator or a process sink. You might recognize that an additional parameter is simply unnecessary: If you connect the port to use it, it is generate, otherwise you cannot use it at all...

    And in near future the documentation will be maintained as a wiki: So maintaining it will become much easier. The most intriguing aspect of this solution is: I can always point you to the documentation and write: "So, now you can go ahead, go ahead and correct it yourself" :P

    Greetings,
      Sebastian
Sign In or Register to comment.