The RapidMiner community is on read-only mode until further notice. Technical support via cases will continue to work as is. For any urgent licensing related requests from Students/Faculty members, please use the Altair academic forum here.
Best Answer
-
MartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,525
RM Data Scientist
danzgb,
you can simply copy the xml code and hit ctrl+v to put it into RM. I do not get the error so this is a bit confusing.
On the decision tree: decision trees are one of the standard ways to do classification. In fact this is only a default comment. Since the i treated the label as numerical (not really needed) i used a SVM in regression mode. That's why i did not need to say 10-13 is enough. I simply try to predict the actual number.
~Martin
- Sr. Director Data Solutions, Altair RapidMiner -
Dortmund, Germany0
Answers
Hi danzgb,
have you tried something like this? I might have done something wrong, but this process gives an absolute error of 1.8. Which sounds fine?
~Martin
Dortmund, Germany
First of all thanks a lot for your reply @mschmitz.
I'm really newbie in RapidMiner.. Where should i paste that code you gave me? In the "XML view"? I can't find where is the xml view...
Thanks one more time.
Ok
!
.
Thanks again Martin, you're really helping me out!
.
Hi danzg,
the key operator is aggregate. You can built of those values with a combination of Generate Attributes, Aggregate, and Filter Examples. I built the number of people below 10 process and attached it.
Edit: Oops, the processes are obviously only counting how often you have them in the data. To forecast you would simply take < 10 as a label and learn a model to predict. You can apply the model then on the new data and use the aggregate to count on the prediction
Best,
Martin
Dortmund, Germany