Hi, and thx for ur responds. I have html-sites as input. I convert the Textinput from numerical to binominal data. I have done the same data with the Apriori-algorithm and it worked. Only the Tertius-algorithm doesn't work. I have to solve the problem with the Tertius-algorithm. I know that I can use other algorithms, but for my task it isn't allowed.
Error in: W-Tertius (W-Tertius) W-Tertius caused an error: weka.core.UnsupportedAttributeTypeException: weka.associations.Tertius: Cannot handle unary class! An external program or library has reported an error. Please see the documentation of this program or library for further information
I have found the problem. You can avoid the Exception with an operator called 'RemoveUselessAttributes'. If you add this operator to your operator tree, the Tertius-algorithm will finish without exceptions and generate association rules.
Answers
I'm not familiar with this implementation, since it's a WEKA learner. Did you try to use FP-Growth?
Just to be curious: Why do you generate Association Rules over Text Data?
Greetings,
Sebastian
and thx for ur responds. I have html-sites as input. I convert the Textinput from numerical to binominal data.
I have done the same data with the Apriori-algorithm and it worked. Only the Tertius-algorithm doesn't work.
I have to solve the problem with the Tertius-algorithm. I know that I can use other algorithms, but for my task it isn't allowed.
Thanks anyway
Edfred
can somebody explain me this exception, please:
Error in: W-Tertius (W-Tertius) W-Tertius caused an error: weka.core.UnsupportedAttributeTypeException: weka.associations.Tertius: Cannot handle unary class!
An external program or library has reported an error. Please see the documentation of this program or library for further information
This is my operator-chain now: Best regards
Edfred
I have found the problem. You can avoid the Exception with an operator called 'RemoveUselessAttributes'. If you add this operator to your operator tree, the Tertius-algorithm will finish without exceptions and generate association rules.
Thanks, to all peple who tried to help me.
Best regards,
Edfred
thank you for posting this solution. I will try to remember if another user comes up with this problem.
Greetings,
Sebastian