Re: BVDecompose Error

The setClassIndex method of BVDecompose uaes a 1-based index, not 0-based:

https://weka.sourceforge.io/doc.dev/weka/classifiers/BVDecompose.html#setClassIndex-int-

Cheers, Peter

On July 20, 2021 5:42:11 PM GMT+12:00, Warren Fernando <[email protected]> wrote:
>Hi Guys,
>
>I've been using the BVDecompose class on my datasets, and it works fine
>in
>the CLI; however, when using it in java code with the API I
>persistently
>get the error: Exception in thread "main" java.lang.Exception: Class
>attribute must be nominal. I'm confused as to how to fix this as there
>are
>no issues with any of the datasets in the WEKA GUI and the CLI. It
>should
>be noted that the class attribute is recognised as a nominal value in
>both
>the GUI and CLI.
>My attributes are as follows:
>@relation Ransomware
>@attribute NtEnumerateValueKey numeric
>@attribute SearchPathW numeric
>@attribute SetFilePointerEx  numeric
>@attribute NtGetContextThread numeric
>@attribute CreateRemoteThread numeric
>@attribute NtQueryValueKey numeric
>@attribute SetErrorMode numeric
>@attribute GetSystemMetrics numeric
>@attribute NtSetValueKey numeric
>@attribute NtDelayExecution numeric
>@attribute Thread32First numeric
>@attribute SHGetSpecialFolderLocation numeric
>@attribute NtTerminateThread numeric
>@attribute NtCreateThread numeric
>@attribute NtWriteVirtualMemory numeric
>@attribute NtOpenKeyEx numeric
>@attribute RegQueryInfoKeyW numeric
>@attribute RegEnumValueA numeric
>@attribute FindResourceExW numeric
>@attribute DrawTextExW numeric
>@attribute Class {0,1}
>
>My code is as follows:
>
>    public RF() throws IOException, Exception {
>
>        BufferedReader reader = new BufferedReader(new
>FileReader("src/MostEffective2018.arff"));
>
>        ArffLoader.ArffReader arff = new ArffLoader.ArffReader(reader);
>        int numFolds = 10;
>        data = arff.getData();
>        data.setClassIndex(data.numAttributes() - 1);
>
>        RandomForest rf = new RandomForest();
>        rf.setNumIterations(100);
>        rf.setMaxDepth(0);
>        rf.buildClassifier(data);
>
>        Evaluation eval = new Evaluation(data);
>      eval.crossValidateModel(rf, data, numFolds, new Debug.Random(1));
>        System.out.println(eval.recall(1));
>        System.out.println(eval.recall(0));
>
>        String file = new String("src/MostEffective2018.arff");
>        BVDecomposeSegCVSub bv = new BVDecomposeSegCVSub();
>        bv.setDataFileName(file);
>
>
>        bv.setClassIndex(data.numAttributes() - 1);
>        bv.setClassifier(rf);
>        System.out.println(bv.getClassIndex());
>
>        bv.decompose();
>        System.out.println(bv.toString());
>
>    }
>
>
>Any help with this would be very much appreciated!
>
>Thanks,
>Warren

--
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 577-5304
http://www.cms.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/.

_______________________________________________
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