I have a text dataset of size 15MB and it has close to 27k of rows, J48 TREE and NAÏVE BAYES classifiers work just fine, but when using logistic classifier i keep getting this error enter image description here I have tried reszing the heap size but it still not working, same thing goes to deep learning and random forest. what can i do?
Does your data have nominal attributes with many values? If so, 2GB may not be enough.
Why? Logistic applies the NominalToBinary filter, which generates binary attributes from labels (absence or presence). That can generate a lot of additional attributes if you have many multi-valued nominal atttibutes.
Solution? Work with a sub-sample of your data or increase the heap size.
