Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

Measuring Cluster Validity by purity measures?

Fred12Fred12 Member Posts: 344 Unicorn
edited November 2018 in Help

hi,

I have a problem with 3 classes, and  wan to d k-means clustering, is there some way to assess cluster performance by some cluster purity criteria like Homogeneity, Entropy, or information gain?

is there some operator that does that?

Tagged:

Best Answer

  • Telcontar120Telcontar120 RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn
    Solution Accepted

    Hi @Fred12, this seems quite similar to the question you posted on Thurs.  Is it different in some way?  I posted a reply there but I didn't see a response, you might want to check it out: Thursday's post reply

     

    In any event, the operator "Item Distribution Performance" lets you look at the overall Gini coefficient based on your label across your clusters, which seems similar to what you are asking to measure. 

    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts

Answers

Sign In or Register to comment.