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

how to watch the update of the centroids of K-mean model

MahmoudEmaraMahmoudEmara Member Posts: 1 Learner I
edited May 2020 in Help
hello everyone, I'm new to Rapidminee I was wondering how to watch or get the value of the centroids of K-mean model in each run or iteration to determine which centroid (i.e., cluster) reached a fixpoint first, and in which run? at what point (i.e, run) none of the centroids get updated anymore (i.e., all reached a fixpoint)? 
Tagged:

Answers

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,533 RM Data Scientist
    i am sorry, but i think this is not supported out of the box. you would need to run the algorithm with different iterations and export the centroids for each run.

    Cheers,
    Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • lionelderkrikorlionelderkrikor RapidMiner Certified Analyst, Member Posts: 1,195 Unicorn
    Hi @MahmoudEmara,

    I propose a partial solution to your problem : 

    Put a KMeans  + Extract Cluster Prototypes operators inside a Loop Parameters operator (loop over the max runs parameter) and then put a Merge operator at the end of the process to have the centroids according the run iteration in a unique results table .

    In attached file, the process I propose.

    Hope this helps,

    Regards,

    Lionel

    PS : To use the Merge operator, you have to install the Operator Toolbox extension from the marketplace.
Sign In or Register to comment.