k-means operator in RapidMiner vs simplekmeans in weka

prat87
prat87 New Altair Community Member
edited November 2024 in Community Q&A
Hello,

I am clustering my dataset using k-means on 2 tools:
weka
rapid miner (k-means operator)

The results are very different. And the results form rapidMIner is infact the one I was looking for.

It will be very very helpful if anybody can answer my questions below:
1) What is different in weka's simplekmeans and rapidminer's k-means operator ?
2) Is there a way to know all the paramters used in rapidminer's k-means operator - so that I can replicate the same result on weka or any other tool ?
3) Is Max_runs  (max number of runs of k-Means with random initialization that are performed) = seed in weka's simpleKMeans?

Thank you. I really appreciate your time.
Tagged:

Answers

  • raazzaa
    raazzaa New Altair Community Member
    Hello Prat87,

    I've been having the same problems as yours, have you found any solutions yet?
    It'd be great if you share me what you've found since you got that problem couple months ago.

    thank you :)
  • heriyunialagus
    heriyunialagus New Altair Community Member

    Hi,

    Please share your information about this problem, becuase i want know it is different.

    Thx

  • sgenzer
    sgenzer
    Altair Employee

    hello @heriyunialagus - welcome to the community.  This is a VERY old thread.  What seems to be the issue?

     

    Scott