Pages: [1]
  Print  
Author Topic: [SOLVED] Replace Apply Model  (Read 465 times)
memvis70
Newbie
*
Posts: 8


« on: April 09, 2014, 04:28:10 PM »

Hello,

Is there any operator I can use instead of Apply Model that doesnīt improve the classification?
Because I just want the predicted label for each row in the example set after the validation operator.



Thanks in advance.
« Last Edit: April 11, 2014, 02:59:07 PM by memvis70 » Logged
Marius
Administrator
Hero Member
*****
Posts: 1794



WWW
« Reply #1 on: April 10, 2014, 09:56:25 AM »

Hm, can you refine your question? In how far does Apply Model improve the classification?

Ok, in you case you are applying the model on the training data. You could use a X-Prediction - it works the same way as the cross validation, but it delivers the predicted values instead of the performance.

Best regards,
Marius
Logged

Please add [SOLVED] to the topic title when your problem has been solved! (do so by editing the first post in the thread and modifying the title)
Please click here before posting.
memvis70
Newbie
*
Posts: 8


« Reply #2 on: April 11, 2014, 02:22:56 PM »


Thanks for your advice. But after testing the operator as you can see in the picture, now my question is why are the confusion matrices different, although I used the same operators in X-Validation and X-Prediction?




Thank you in advance.



Logged
Marius
Administrator
Hero Member
*****
Posts: 1794



WWW
« Reply #3 on: April 11, 2014, 02:44:16 PM »

Do you use the same local random seed in both X-Validation and X-Prediction? Otherwise the splits can be different resulting in different results.

Best regards,
Marius
Logged

Please add [SOLVED] to the topic title when your problem has been solved! (do so by editing the first post in the thread and modifying the title)
Please click here before posting.
memvis70
Newbie
*
Posts: 8


« Reply #4 on: April 11, 2014, 02:58:05 PM »

Thank you  Smiley.Now itīs working.
Logged
Pages: [1]
  Print  
 
Jump to: