Using MLP classification attribute with new data

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

Using MLP classification attribute with new data

B. Smith
Hello.  I was wondering if someone could please help me.  I’m somewhat new to
Weka and have a question.  I added a classification attribute using values
derived from a three-layer MLP formula.  The input values are nine existing
numeric attributes and a numeric class attribute.  After calculating, I
delete the nine numeric attributes, leaving the MLP classification attribute
and the class attribute.  My question is, when making predictions on new
data, how do I apply my previous MLP attribute model when there are no class
(or outcome) values with the new data?  Thanks.



--
Sent from: https://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Using MLP classification attribute with new data

Peter Reutemann
> Hello.  I was wondering if someone could please help me.  I’m somewhat new to
> Weka and have a question.  I added a classification attribute using values
> derived from a three-layer MLP formula.  The input values are nine existing
> numeric attributes and a numeric class attribute.  After calculating, I
> delete the nine numeric attributes, leaving the MLP classification attribute
> and the class attribute.  My question is, when making predictions on new
> data, how do I apply my previous MLP attribute model when there are no class
> (or outcome) values with the new data?  Thanks.

You still need the same class attribute definition (in your case
numeric) in the data for making predictions.
The data rows itself will just have missing values (denoted with a
question mark in ARFF files).

Cheers, Peter
--
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 858-5174
http://www.cms.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Using MLP classification attribute with new data

B. Smith
Thanks, Peter.



--
Sent from: https://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html