3
$\begingroup$

I know that with Orange it is possible, using the 'Test & Score" widget, to test the performance of a classifier trained on a specific training set using a different test set ('Test on test data' option).

My question is: is it possible to use a training set to train a classifier, tune its hyperparameters through cross validation on a separate validation set, and, finally, test the classification performance on a third, separate set using the already trained classifier?

How this can be achieved?

$\endgroup$
3
$\begingroup$

A scheme like this should work. Namely, you pass training data directly into the the learner widget and pass its trained Model into Predictions widget along with labeled test data.

enter image description here

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.