Orange Forum • View topic - Kmeans Implementation - Orange and WEKA?

Kmeans Implementation - Orange and WEKA?

General discussions about Orange and with Orange connected things (data mining, machine learning, bioinformatics...).

Kmeans Implementation - Orange and WEKA?

Postby bonjovi2012 » Mon Nov 12, 2012 12:10

Hi

I have been using a number of tools (R, RapidMiner, WEKA, KNIME and Orange) for a simple k-means scenario. Basically, I am trying to find out what is the best tool for this scenario

I am using the Blood Transfusion dataset (http://archive.ics.uci.edu/ml/datasets/ ... ice+Center) and have set k equal to 2.

In my results, I found that WEKA and Orange returned identical cluster centers. I am wondering if there is a reason for this? i.e. are they based on the same implementation/library for k-means?

Thanks,
Colm

Re: Kmeans Implementation - Orange and WEKA?

Postby Ales » Wed Nov 14, 2012 11:05

bonjovi2012 wrote:I am wondering if there is a reason for this? i.e. are they based on the same implementation/library for k-means?

No. Orange has it's own implementation of k-means.


Return to General Discussions



cron