Get the "wei" from Decision Tree within a Split Validation Operator

pedroomac

Hello,
Currently, I have a simple model with a decision tree that looks like this:


In my Split Validation, currently I have the following operators:


I want to get the "wei" from my decision tree, so that I can see the Feature Importance Table in the Results.

I tried this way:


But it is throwing an error when I run it:



Do you recommend any workaround?

Thank you!

ruhaila

Hi.

I used the SPLIT VALIDATION sample in Rapidminer and the successfully generated the weights. It may relate to your  dataset. Perhaps share the .rpm and data files? hth

BalazsBarany

Hi!

Use the "Remember" operator to remember the weight result inside the validation and then "Recall" to get it outside the process.

You could also store it in the repository (using Store) and retrieve (using Retrieve) later if you wanted to store it anyway.

Regards,
Balázs

pedroomac

I don't think it would be because of the dataset... If I tried to get the "wei" from the decision tree outside the split validation operator I would be able to see the Feature Importance Table in the results.
@BalazsBarany, your suggestion worked. Thanks a lot!

By the way, is there any way I could also retrieve the parameters that I am setting in my decision tree?

ceaperez

Hi @pedroomac,
For  retrieve the parameters you can use the log operator.

best,

cesar