save predicted labels
hi guys,
Im using a standard 'cross validation with SVM' scheme and want to get the predicted labels computed by the trained SVM on the test data set. How do I do that?
Thanks! P.
Im using a standard 'cross validation with SVM' scheme and want to get the predicted labels computed by the trained SVM on the test data set. How do I do that?
Thanks! P.
Find more posts tagged with
Sort by:
1 - 4 of
41
thanks! that helped..
How come the split validation operator can not return the labelled test set?
It only returns the full "data set". It does not return the part used for training and the part used for testing.
It only returns the full "data set". It does not return the part used for training and the part used for testing.
Hi,
Kind regards,
Tobias
that is because the main purpose of that operator is validation, i.e. computation of the performance, not the model application - normally, you would want to get the performance as main output and not the example set.
wessel wrote:
How come the split validation operator can not return the labelled test set?
It only returns the full "data set". It does not return the part used for training and the part used for testing.
Kind regards,
Tobias
simply replace the X-Validation operator by the operator X-Prediction. If you want both, predicted labels and estimated performance in a single run you would have to append the predictions after model application to a data set (via Remember, Recall, and Append or directly writing in a database for example).
Cheers,
Ingo