Hello,
I am trying to retain a couple of features (date and ID) in my data file that I would like a supervised learner to ignore during classification, but output during prediction. I understand from searching for answers to this on Stack Overflow that you can used the FilteredClassifier meta-filter when using Weka in Java, but I'm wondering if there is a way to do this in either the GUI or using the RWeka package in my R code.
Note: I did try to use the "addID" filter in the GUI but I found that, as I suspected, it negatively affected classification accuracy.
Thank you,
Nick
I am trying to retain a couple of features (date and ID) in my data file that I would like a supervised learner to ignore during classification, but output during prediction. I understand from searching for answers to this on Stack Overflow that you can used the FilteredClassifier meta-filter when using Weka in Java, but I'm wondering if there is a way to do this in either the GUI or using the RWeka package in my R code.
Note: I did try to use the "addID" filter in the GUI but I found that, as I suspected, it negatively affected classification accuracy.
Thank you,
Nick