如何从python文件的命令行运行属性选择WEKA库？

Question

I follow the below structure to convert a csv file into an arff file, and it works. But for running the attribute selection library from WEKA it does not work. Does anyone know?

 java -cp ~/weka.jar weka.attributeSelection.CfsSubsetEval 1 -E 1  "weka.attributeSelection.BestFirst -D 1 -N 5" -i ~/file.arff

I also tried the flooring command:

java -cp ~/somewher/weka.jar weka.attributeSelection.InfoGainAttributeEval "weka.attributeSelection.Ranker -T -1.7976931348623157E308 -N -1" last -c -I ~/somewher/file.arff

But it gives me this error:

java.lang.Exception: 
No training file given.

General options:
-h display this help
-i <name of input file>
Sets training file.
-c <class index>
    Sets the class index for supervised attribute
    selection. Default=last column.

Answer 1

I'm aware that I'm answering an old question, but the correct way to call Weka to select features is like this:

java weka.filters.supervised.attribute.AttributeSelection -E weka.attributeSelection.CfsSubsetEval -S "weka.attributeSelection.BestFirst -D 1 -N 5"  -i input.arff  -o output.arff

(also this is not related to Python)