J48 doesn't do anything special with sparse data. Make sure you have set the class
index for your data correctly when you use the API.
On 12/03/2016, at 3:06 AM, A Mo
I am a final year university student using the Weka's API as art of a final year
I have run into a strange issue however. When I build a J48 classifier with my data set,
a tree of size 1 is produced (This does not happen when I use the normal WEka
My ARFF file is in sparse format and I have noticed that trying out my code on a file
that uses the standard ARFF format produces a normal tree so I am convinced this is an
issue with how J48 is coping with the sparse data.
So far, I have not been able to find any useful examples online to solve my problem. Does
anyone have any suggestions or can point me in the right direction of what to do, please?
Thanks for your time!
A stressed out student!!
Wekalist mailing list
Send posts to: Wekalist(a)list.waikato.ac.nz
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html