K Means Clusting - too few examples

thatsbhavikthatsbhavik MemberPosts:2Contributor I
edited November 2018 inHelp 





<宏/ >




<参数键=“repository_entry”值= " / /当地Repository/data/SAA/HW 2a_Regression"/>




























Hi - I am new to the Rapid Miner community and have a question on how to remove the error in the following k-means clustering process. The error I get is "Example Set contains not enough examples to perform this operation. Needs atleast 5 examples." (I set k=5) even if I increase the examples to 20 or 100. I want to see clusters - both supervised (identifying k= "x" or unsupervised (Agglomerative).

Attached is the process file.

Please help!

Thanks

Tagged:

Answers

  • Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, MemberPosts:1,635Unicorn

    It's hard to diagnose this without seeing your data sample. I do see you have a "Filter Examples" operator before the K-means. Are you sure that the filter criteria you have in there is not leading to a reduction in number of examples available downstream so it falls below 5?

    Brian T.
    Lindon Ventures
    Data Science Consulting from Certified RapidMiner Experts
  • thatsbhavikthatsbhavik MemberPosts:2Contributor I

    Thanks - See attached. The filter was "no missing attributes". This runs well on the second sheet, which has a smaller sample - I need it to run on the first sheet. I am still unable to see the "Cluster Diagram" - how do i do that?

  • sgenzersgenzer Administrator, Moderator, Employee, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM ModeratorPosts:2,959Community Manager

    嗨@thatsbhavik- welcome to the community. So my first question is why are you running RapidMiner 7.1? Version 8.1 is our current version so any help I can post will be incompatible with your version. Maybeupdate?:)

    Scott

Sign InorRegisterto comment.