naywhayare 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/
< jenkins-mlpack> Yippie, build fixed!
< jenkins-mlpack> Project mlpack - svn checkin test build #2058: FIXED in 1 hr 28 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20svn%20checkin%20test/2058/
< jenkins-mlpack> * Ryan Curtin: Refactor test for changed API.
< jenkins-mlpack> * Ryan Curtin: Add some comments.
< jenkins-mlpack> Project mlpack - nightly matrix build build #537: STILL FAILING in 6 hr 28 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/537/
< jenkins-mlpack> saxena.udit: More tests for Adaboost added, with tolerance for change in rt also provided.
< marcus_zoq> Can anyone checkout the repository anonymously with the command from the website?
< jenkins-mlpack> Project mlpack - nightly matrix build build #538: STILL FAILING in 4 hr 28 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/538/
< jenkins-mlpack> * Ryan Curtin: Refactor test for changed API.
< jenkins-mlpack> * Ryan Curtin: Add some comments.
< jenkins-mlpack> * Ryan Curtin: Refactor KMeans so that the actual Lloyd iteration step is separate, since there
< jenkins-mlpack> are many ways to do a Lloyd iteration.
< marcus_zoq> Hm, how can a kmeans refactoring achieve results that are worse than before ...
< marcus_zoq> Hmm, maybe I do something wrong
< naywhayare> do you mean that it's slower, or that the results are wrong?
< marcus_zoq> The nystroem test which uses the kmeans method failed because the results are 'worse'
< marcus_zoq> The kmeans test is okay, so I think the results are okay
< marcus_zoq> We can widen the tolerance bounds but I wonder why this happens
< naywhayare> oh, I forgot to check the nystroem test
< naywhayare> I'm not quite done with the new abstraction yet
< naywhayare> so I will be sure to fix that today
< marcus_zoq> ah, okay
< marcus_zoq> are you able to checkout the repository anonymously with the command from the website?
< naywhayare> I can't seem to
< naywhayare> let me screw with the auth policy
< naywhayare> I thought I had this fixed ages ago...
< naywhayare> marcus_zoq: ok, it should be fixed now. the svn authz file is very odd and doesn't act like it's supposed to...
< marcus_zoq> naywhayare: Thanks!
sumedhghaisas has joined #mlpack
< sumedhghaisas> naywhayare: hey sorry I was little busy in college work... I am currently implementing NMF for implicit datasets...
< sumedhghaisas> did you had a chance to look at svd complete incremental learning??
< naywhayare> what do you mean by implicit datasets?
< naywhayare> marcus_zoq: I think I fixed the kmeans issue in r16926
< jenkins-mlpack> Project mlpack - nightly matrix build build #539: ABORTED in 2 hr 19 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/539/
< jenkins-mlpack> Starting build #2059 for job mlpack - svn checkin test (previous build: FIXED)
< sumedhghaisas> naywhayareexamples of implicit datasets are datasets where user did not directly voted for the item...
< sumedhghaisas> *naywhayare
< sumedhghaisas> movie rating datasets are explicit datasets right??
< sumedhghaisas> I have added the paper ... Collaborative Filtering for Implicit Feedback Datasets
< jenkins-mlpack> Project mlpack - svn checkin test build #2059: FAILURE in 7 min 45 sec: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20svn%20checkin%20test/2059/
< jenkins-mlpack> Ryan Curtin: Further refactoring of KMeans. Fix MaxVarianceNewCluster, and also change it so
< jenkins-mlpack> that assignments are not passed in (since the inner KMeans loop doesn't really
< jenkins-mlpack> keep track of these now).
< jenkins-mlpack> Starting build #2060 for job mlpack - svn checkin test (previous build: FAILURE -- last SUCCESS #2058 18 hr ago)
< jenkins-mlpack> Project mlpack - nightly matrix build build #540: ABORTED in 45 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/540/
< jenkins-mlpack> Ryan Curtin: Further refactoring of KMeans. Fix MaxVarianceNewCluster, and also change it so
< jenkins-mlpack> that assignments are not passed in (since the inner KMeans loop doesn't really
< jenkins-mlpack> keep track of these now).
< jenkins-mlpack> Project mlpack - nightly matrix build build #541: ABORTED in 57 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/541/
< jenkins-mlpack> Ryan Curtin: Fix changed API.
< jenkins-mlpack> Yippie, build fixed!
< jenkins-mlpack> Project mlpack - svn checkin test build #2060: FIXED in 1 hr 32 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20svn%20checkin%20test/2060/
< jenkins-mlpack> Ryan Curtin: Fix changed API.
< jenkins-mlpack> Starting build #2061 for job mlpack - svn checkin test (previous build: FIXED)
< jenkins-mlpack> Project mlpack - nightly matrix build build #542: ABORTED in 33 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/542/
< jenkins-mlpack> Ryan Curtin: Explicit cast for older versions of Armadillo.
< jenkins-mlpack> Project mlpack - nightly matrix build build #543: ABORTED in 37 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20nightly%20matrix%20build/543/
< jenkins-mlpack> Ryan Curtin: Explicit cast to arma::vec for old versions of Armadillo.
< jenkins-mlpack> Project mlpack - svn checkin test build #2061: SUCCESS in 1 hr 32 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20svn%20checkin%20test/2061/
< jenkins-mlpack> Ryan Curtin: Explicit cast for older versions of Armadillo.
< jenkins-mlpack> Starting build #2062 for job mlpack - svn checkin test (previous build: SUCCESS)
< marcus_zoq> naywhayare: Great, thanks for the information!
< jenkins-mlpack> Project mlpack - svn checkin test build #2062: SUCCESS in 1 hr 32 min: http://big.cc.gt.atl.ga.us:8080/job/mlpack%20-%20svn%20checkin%20test/2062/
< jenkins-mlpack> * Ryan Curtin: Yet another reverse-compatibility fix for Armadillo.
< jenkins-mlpack> * Ryan Curtin: Explicit cast to arma::vec for old versions of Armadillo.
sumedhghaisas has quit [Ping timeout: 240 seconds]