when using weka.classifiers.meta.FilteredClassifier with Randomforest got error

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

when using weka.classifiers.meta.FilteredClassifier with Randomforest got error

linlin
when using weka commandline

java -cp ./weka.jar weka.classifiers.meta.FilteredClassifier  -t
/home/rhlin/Master/data/weka_arff/2type/bl_2y_change/RID_only_gene_BL_2y_2type_change_82_train_chi2_250_.arff
-c 1 >
/home/rhlin/Master/weka_output/wrapper/2y_2type/train/bl_2y_82_RF_chi2_250__wrap_20__train.out
-F "weka.filters.supervised.attribute.AttributeSelection -E
\"weka.attributeSelection.WrapperSubsetEval -B
weka.classifiers.trees.RandomForest  -F 10 -T 0.01 -R 1 -E AUC \" -S
\"weka.attributeSelection.BestFirst -D 1 -N 20\"" -S 1 -W
weka.classifiers.trees.RandomForest

i got this error

"Cannot build model (only class attribute present in data!), using ZeroR
model instead!"

I am sure that my data is ok ,and  using  others algorithm is also ok ,only
error on RandomForest ...


thank you



--
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: when using weka.classifiers.meta.FilteredClassifier with Randomforest got error

Eibe Frank-2
Administrator
That’s fine. When performing the search through the space of attribute subsets to evaluate, BestFirst search will generate the empty predictor set as a candidate attribute subset (i.e., there will be only the class attribute in the data passed to the RandomForest for that “subset"). ZeroR is the right model to use in that case.

Cheers,
Eibe

> On 7/03/2021, at 8:40 PM, linlin <[hidden email]> wrote:
>
> when using weka commandline
>
> java -cp ./weka.jar weka.classifiers.meta.FilteredClassifier  -t
> /home/rhlin/Master/data/weka_arff/2type/bl_2y_change/RID_only_gene_BL_2y_2type_change_82_train_chi2_250_.arff
> -c 1 >
> /home/rhlin/Master/weka_output/wrapper/2y_2type/train/bl_2y_82_RF_chi2_250__wrap_20__train.out
> -F "weka.filters.supervised.attribute.AttributeSelection -E
> \"weka.attributeSelection.WrapperSubsetEval -B
> weka.classifiers.trees.RandomForest  -F 10 -T 0.01 -R 1 -E AUC \" -S
> \"weka.attributeSelection.BestFirst -D 1 -N 20\"" -S 1 -W
> weka.classifiers.trees.RandomForest
>
> i got this error
>
> "Cannot build model (only class attribute present in data!), using ZeroR
> model instead!"
>
> I am sure that my data is ok ,and  using  others algorithm is also ok ,only
> error on RandomForest ...
>
>
> thank you
>
>
>
> --
> 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
_______________________________________________
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