Re: Limit number of instances when using "Supplied test set"

I can read the test data in Preprocess. Actually, I used dataset 1 (4,997 instances) as training and test on dataset 2 (3,097 instances) and vice versa, both training use the random forest and generate a model successfully. Then I use the model to re-evaluate the other dataset, and both only test the first 114 instances. When I perform re-evaluating, I got the error- "Data used to training model and test set are not compatible...", though both datasets have exact same variables with 1 class column at the end. I'm not sure if this is the case cause part of the test dataset missing.

I attached the attributes mapping result:

Model attributes             	    Incoming attributes
-----------------------------	    ----------------
(nominal) wt              	--> 1 (nominal) wt
(numeric) position           	--> 2 (numeric) position
(nominal) sub                	--> 3 (nominal) sub
(numeric) residual           	--> 4 (numeric) residual
(numeric) ep1                	--> 5 (numeric) ep1
(numeric) dist1              	--> 6 (numeric) dist1
(nominal) aa1                	--> 7 (nominal) aa1
(numeric) ep2                	--> 8 (numeric) ep2
(numeric) dist2              	--> 9 (numeric) dist2
(nominal) aa2                	--> 10 (nominal) aa2
(numeric) ep3                	--> 11 (numeric) ep3
(numeric) dist3              	--> 12 (numeric) dist3
(nominal) aa3                	--> 13 (nominal) aa3
(numeric) ep4                	--> 14 (numeric) ep4
(numeric) dist4              	--> 15 (numeric) dist4
(nominal) aa4                	--> 16 (nominal) aa4
(numeric) ep5                	--> 17 (numeric) ep5
(numeric) dist5              	--> 18 (numeric) dist5
(nominal) aa5                	--> 19 (nominal) aa5
(numeric) ep6                	--> 20 (numeric) ep6
(numeric) dist6              	--> 21 (numeric) dist6
(nominal) aa6                	--> 22 (nominal) aa6
(numeric) vol                	--> 23 (numeric) vol
(numeric) sT                 	--> 24 (numeric) sT
(nominal) loc                	--> 25 (nominal) loc
(numeric) num                	--> 26 (numeric) num
(nominal) secstr             	--> 27 (nominal) secstr
(nominal) exp_fitness_class  	--> 28 (nominal) exp_fitness_class

Thanks,
Shengyuan
_______________________________________________
Wekalist mailing list -- [email protected]
Send posts to [email protected]
To unsubscribe send an email to [email protected]
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