cameron.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
islamfm has quit [Quit: Konversation terminated!]
islamfm has joined #mlpack
islamfm has quit [Ping timeout: 260 seconds]
islamfm has joined #mlpack
govg has quit [Quit: leaving]
< islamfm> How can I get statistical measures like precision, reacall and fmeasure for a trained classifier?
islamfm has quit [Quit: Konversation terminated!]
islamfm has joined #mlpack
govg has joined #mlpack
islamfm has quit [Ping timeout: 260 seconds]
islamfm has joined #mlpack
govg has quit [Quit: leaving]
islamfm has quit [Quit: Konversation terminated!]
islamfm has joined #mlpack
islamfm has quit [Ping timeout: 265 seconds]
hritikjain has joined #mlpack
govg has joined #mlpack
hritikjain has quit [Ping timeout: 246 seconds]
islamfm has joined #mlpack
islamfm has quit [Ping timeout: 258 seconds]
islamfm has joined #mlpack
islamfm has quit [Quit: Konversation terminated!]
islamfm has joined #mlpack
islamfm has quit [Ping timeout: 244 seconds]
islamfm has joined #mlpack
islamfm has quit [Client Quit]
govg has quit [Ping timeout: 245 seconds]
islamfm has joined #mlpack
< islamfm> Hi all, How can I get statistical measures like precision, recall and fmeasure for a trained classifier?
islamfm has quit [Client Quit]
islamfm has joined #mlpack
< naywhayare> islamfm: sorry for the slow respinse
< naywhayare> *response
< naywhayare> you'd have to calculate these measures yourself, unfortunately
< naywhayare> maybe it would be possible to design some simple classes that could calculate these types of performance metrics
< naywhayare> but at the moment we don't have anything like that implemented
< islamfm> I saw some email threads discussing that as GSoC 2014 projects, were they implemented or they were just discussions?
< naywhayare> islamfm: I'm using a phone so I can't easily open that link now, but maybe that is in reference to the automatic benchmarkong system
< naywhayare> *benchmarking
< naywhayare> developed by Marcus (zoq) and which is actually its own project on github now
< naywhayare> we had a student last summer who extended the system to evaluate the performance of various algorithms
< naywhayare> but the code to do that is in the benchmark code not mlpack
< islamfm> Thanks for your reply, will check that
< naywhayare> that's in python though so it may not be applicable to what you are trying to do
< naywhayare> but maybe it might ne helpful :)
< naywhayare> *be