Hi All,

 

I go through the following set of steps in WEKA:

 

1)     Load training dataset

2)     Choose classifier (say multilayer perceptron)

3)     Chose test option (cross validation x10)

4)     Start

5)     View classification output

6)     Save model

7)     Load same model

8)     Set test dataset to original training dataset

9)     Re-evaluate model on test datatset

10)  The classification result I see is different from the view 5) and is the same as if I had chosen “Use training set” in original classification instead of cross validation

 

Can anybody explain this?

 

Cheers, Dave

 

David A. Wilkinson,
Chevron ETC.
6001 Bollinger Canyon Rd.
San Ramon,
CA. 94583

Phone # 925 842-6200
Fax # 925 842-2076

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist <at> list.scms.waikato.ac.nz
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html