Thanks for replying. I managed to train the libsvm (-S 2) classifier for a
one class dataset. But the problem is even for the same training set,
number of correctly classified instances doesn't get over 50%. What is the
reason for this?
On Sun, May 6, 2012 at 12:43 PM, Mark Hall <mhall(a)pentaho.com> wrote:
On 1/05/12 11:55 PM, Sameendra Samarawickrama wrote:
I want to do a one class classification with SMO in Weka. That is, my
training directory has only a one folder which contains the files that I
want to train the SMO with (trainDir->class1->**trainingfiles). When I
this one, it gives me the following error:
weka.classifiers.functions.**SMO: Cannot handle unary class!
What I want to do is, train the classifier with only a single class and
then when at the testing phase when I fed a document to the classifier,
if it is in that class, say it or if can not be classified, gives
something like 'unknown'.
There is a package for Weka >= 3.7.2 called "oneClassClassifier" that
provides a facility for performing one class classification in Weka:
Or you could try libsvm, which has a one class mode.
Wekalist mailing list
Send posts to:
List info and subscription status: https://list.scms.waikato.ac.**
List etiquette: http://www.cs.waikato.ac.nz/~**