The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"Decision Tree problems"
Contributor I
Hi everyone,
Couldn't find this question answered anywhere and not sure if you can help.
Trying to run a simple decision tree. No errors, but all I get is the first stub and that stub is the 'label' variable. And it doesn't even look like its been properly assessed (base don stats in performance analysis module).
I've been through all relevant videos (even the neural marketing guy's stuff which is very good) and manuals, but can't see what I am doing wrong. Been at this better part of a day.
BTW, took the same data and reinstalled an old version of Cognos Scenario (an old IDT) and got results in about 10 minutes (including install time).
Can anyone help me?
Cheers,
Ray
Couldn't find this question answered anywhere and not sure if you can help.
Trying to run a simple decision tree. No errors, but all I get is the first stub and that stub is the 'label' variable. And it doesn't even look like its been properly assessed (base don stats in performance analysis module).
I've been through all relevant videos (even the neural marketing guy's stuff which is very good) and manuals, but can't see what I am doing wrong. Been at this better part of a day.
BTW, took the same data and reinstalled an old version of Cognos Scenario (an old IDT) and got results in about 10 minutes (including install time).
Can anyone help me?
Cheers,
Ray
Tagged:
0
Answers
without seeing your data and your RapidMiner process for decision tree induction, I can only guess possible reasons for the failure of your RapidMiner process...
So let me start with a few questions:
- Did you set the role of the attribute 'label' to 'label'?
- Did you play a little with the paramters of the decision tree learner?
You may for example want to try different values for the parameter 'mininal gain'. Relaxing this constraining requirement from the default value of '0.1' to for example '0.01' often helps. You may also want to turn the pruning off. Do you now obtain a real decision tree as result?Best regards,
Ralf
It was one of those 2 things. The pruning issue seems counter-intuitive to me, but I'll have to read up on both issues.
Thanks
Ray