What is a performance vector

TeeHTeeH Member Posts: 18 Contributor II
edited December 2018 in Help
I want to produce performance results set using sliding window validation and neural net, but the output for the validation process cannot accept the the output of of the regression performance function, says it is expecting the performance vector. So which function to use so I can produce the the example data set
Tagged:

Answers

  • Telcontar120Telcontar120 Moderator, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,635 Unicorn
    Did you look at the tutorial process for the Cross Validation operator?  That shows the typical setup, where you have the model development in the training window on the left and the Apply Model and Performance in the testing window on the right, with all the output ports connected.  That should hopefully clarify.  If not, perhaps you can make your question more specific?

    Brian T.
    Lindon Ventures 
    Data Science Consulting from Certified RapidMiner Experts
  • rfuentealbarfuentealba Moderator, RapidMiner Certified Analyst, Member, University Professor Posts: 568 Unicorn
    Hi Thabo,

    Do you mind to share your process, to see what is happening? When you do validation, you have two windows, right?

    The left one (training) contains your model. The right one (testing) contains the operators for testing your model. Most of the time, Apply Model followed by a Performance (Classification). I am not sure if the Performance (Regression) operator has the same outputs. Assuming it does have these outputs, you should be aware that the performance vector can be obtained from the per output, not the other one that usually contains your model.

    All the best,

    Rodrigo.
Sign In or Register to comment.