Random forest to identify importance of features?

Fred12Fred12 Member Posts: 344 Unicorn
edited November 2018 in Help

hi,

Is there any way to use random forest operator to get an importance of features ranking?

 

it could keep track which of their decision trees and subset of features gives best performance on the testing data (out-of-bag-data) and print them out, I know there is a similar implementation of it in R...

Best Answer

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,453 RM Data Scientist
    Solution Accepted

    Hi,

     

    just have a look at Weight by Tree Importance.

     

    ~Martin

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany

Answers

  • Fred12Fred12 Member Posts: 344 Unicorn

    ok thanks, 

    its just really confusing that you have to piece together everything from singular operators in RapidMiner, altough it could be implemented together in the other random forest operator ;)

    quite confusing if you don't know all the operators in Rapidminer in the beginnning...

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,453 RM Data Scientist

    I agree it would be better if the rf simply also returns the weight vector directly. Not sure why it is not like this

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.