Open in new window / Try shogun cloud
--- Log opened Sat Jan 25 00:00:07 2014
-!- FSCV [~FSCV@50.7.50.60] has joined #shogun00:30
-!- votjakovr [~votjakovr@188.134.46.30] has quit [Quit: WeeChat 0.4.0]00:33
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]00:37
-!- FSCV [~FSCV@50.7.50.60] has quit [Quit: Leaving]01:04
-!- lisitsyn [~lisitsyn@80.252.20.67] has quit [Ping timeout: 252 seconds]01:15
-!- sonne|osx_ [~sonne@f053009064.adsl.alicedsl.de] has joined #shogun03:18
-!- sonne|osx [~sonne@e179077197.adsl.alicedsl.de] has quit [Ping timeout: 264 seconds]03:19
-!- sonne|osx_ is now known as sonne|osx03:19
-!- Calvin-O [~mohit@c-24-118-110-65.hsd1.mn.comcast.net] has joined #shogun03:32
-!- Calvin-O [~mohit@c-24-118-110-65.hsd1.mn.comcast.net] has quit [Quit: Leaving.]05:26
-!- sonne|osx [~sonne@f053009064.adsl.alicedsl.de] has quit [Quit: sonne|osx]06:44
-!- lisitsyn [~lisitsyn@31-28-48-250.clients.tlt.100megabit.ru] has joined #shogun07:56
-!- zxtx [~zv@129-79-241-148.dhcp-bl.indiana.edu] has quit [Ping timeout: 272 seconds]08:41
-!- zxtx [~zv@129-79-241-148.dhcp-bl.indiana.edu] has joined #shogun09:03
-!- zxtx [~zv@129-79-241-148.dhcp-bl.indiana.edu] has quit [Ping timeout: 260 seconds]09:30
-!- votjakovr [~votjakovr@188.134.46.30] has joined #shogun09:31
-!- zxtx [~zv@c-98-223-196-32.hsd1.in.comcast.net] has joined #shogun10:19
-!- votjakovr [~votjakovr@188.134.46.30] has quit [Ping timeout: 264 seconds]10:40
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has joined #shogun13:20
-!- mode/#shogun [+o iglesiasg] by ChanServ13:20
-!- new_lido [~walid@41.218.175.100] has joined #shogun14:41
-!- shogun-notifier- [~irker@7nn.de] has joined #shogun14:58
shogun-notifier-shogun: iglesias :develop * 1552545 / tests/integration/python_modular/tester.py: https://github.com/shogun-toolbox/shogun/commit/15525454831a88ea9d7820520c85866ffa63c33214:58
shogun-notifier-shogun: Fix integration bug in call to compare method.14:58
shogun-notifier-shogun: The number of arguments increased in recent commit.14:58
shogun-buildbotbuild #2622 of deb1 - libshogun is complete: Success [build successful]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb1%20-%20libshogun/builds/262215:08
shogun-buildbotbuild #43 of deb4 - python3 is complete: Failure [failed test python modular]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb4%20-%20python3/builds/43  blamelist: iglesias <fernando.iglesiasg@gmail.com>15:30
-!- travis-ci [~travis-ci@ec2-54-224-205-193.compute-1.amazonaws.com] has joined #shogun15:48
travis-ci[travis-ci] it's iglesias's turn to pay the next round of drinks for the massacre he caused in shogun-toolbox/shogun: http://travis-ci.org/shogun-toolbox/shogun/builds/1760150615:48
-!- travis-ci [~travis-ci@ec2-54-224-205-193.compute-1.amazonaws.com] has left #shogun []15:48
shogun-buildbotbuild #2149 of deb3 - modular_interfaces is complete: Failure [failed test python modular]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb3%20-%20modular_interfaces/builds/2149  blamelist: iglesias <fernando.iglesiasg@gmail.com>15:57
@iglesiasgargh new error in the tests!16:07
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has quit [Quit: Leaving]16:38
-!- parijat [671b082a@gateway/web/freenode/ip.103.27.8.42] has joined #shogun16:49
-!- parijat [671b082a@gateway/web/freenode/ip.103.27.8.42] has quit [Quit: Page closed]17:12
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has joined #shogun17:37
-!- mode/#shogun [+o iglesiasg] by ChanServ17:37
-!- parijat [671b082a@gateway/web/freenode/ip.103.27.8.42] has joined #shogun17:56
parijatiglesiasg, hello17:57
parijatiglesiasg, I sent a fresh PR but there are additional test failures now! :(17:57
-!- shogun-notifier- [~irker@7nn.de] has quit [Quit: transmission timeout]17:58
parijatiglesiasg, specially I cant figure out the problem with evaluation_clustering_kmeans_simple, it doesnt use any external data but shows an exception18:01
@iglesiasgparijat, let me see18:03
parijatiglesiasg, sure!18:04
@iglesiasgparijat, the evaluation_clustering_kmeans_simple worked when I did it locally though18:05
@iglesiasgparijat, and the others have probably come because of the "fix" that I sent for evaluation_clustering_simple18:06
@iglesiasgwhich seems to have broken more tests actually18:06
parijatiglesiasg, same with me.18:06
@iglesiasgparijat, I would not worry too much for the moment for the travis error of evaluation_clustering_simple18:08
@iglesiasgparijat, because it does not happen either in the buildbot18:09
@iglesiasgparijat, aaah wait18:09
@iglesiasgparijat, it did not happen in the previous travis build18:09
@iglesiasgparijat, so the fail in evaluation_clustering_simple might be due to your changes18:09
parijatiglesiasg. I guess it happened.18:10
parijatiglesiasg, it shows an exception18:10
parijatiglesiasg, have a look at this log please https://travis-ci.org/shogun-toolbox/shogun/jobs/1760333318:11
@iglesiasgparijat, what line?18:13
parijatiglesiasg, there is additionally a new failure in the fresh PR in clustering_kmeans_modular18:13
@iglesiasgparijat, the one for the error in evaluation_clustering_simple?18:13
parijatiglesiasg, let me see18:13
@iglesiasgparijat, I am working on the error affecting the other integration tests, so please have a look at why the evaluation_clustering_simple fails :)18:14
parijatiglesiasg, 405618:14
parijatiglesiasg, no but this other test clustering_kmeans_modular might not be caused by your changes line 425418:16
@iglesiasgparijat, what?18:17
parijatiglesiasg, test clustering_kmeans_modular failure is caused because output doesnt match with expected data18:17
parijatiglesiasg, thats probably because I changed implementation slightly!18:18
@iglesiasgparijat, ok18:20
@iglesiasgparijat, we need to make sure that it is because of that, and not because a bug was introduced18:20
@iglesiasgparijat, what do you think you changed in the implementation that might make the output change slightly?18:20
parijatiglesiasg, earlier choosing points during updating cluster centers was done randomly, I changed it to choose points in a deterministic fashion18:23
@iglesiasgparijat, why so?18:23
parijatiglesiasg, that has improved results in my own test actually18:23
@iglesiasgparijat, in the rectangle test?18:24
parijatiglesiasg, yup18:24
@iglesiasgparijat, but we cannot tell that it is in general better to choose those points deterministically because of that18:24
parijatiglesiasg, in the random case many times the final centers were not means of clusters18:25
parijatiglesiasg, but in this case its always that!18:25
@iglesiasgparijat, I don't know right now how Lloyd's algorithm work, I would need to check18:26
@iglesiasgparijat,  how is this step normally done in other implementations or references for the algorithm?18:26
parijatiglesiasg, let me check!18:26
parijatiglesiasg, the algorithm I studied in class was deterministic like I implemented. But randomization might be some kind of heuristic added to it which might work better on larger number of points18:28
@iglesiasgparijat, yes, that makes sense18:29
parijatiglesiasg, let me check whats generally done18:29
@iglesiasgparijat, I just committed something that should fix the errors in the integration tests (except from the one you are working on)18:46
@iglesiasgparijat, feel free to rebase and update the PR18:46
parijatiglesiasg, sure!18:47
parijatiglesiasg, thanks :)18:48
@iglesiasgparijat, no problem!18:50
@iglesiasgarggh I always forget how to restart the build in the buildbot18:51
@iglesiasglisitsyn, lisitsyn1 do you happen to remember ^18:52
@iglesiasgI think I got it in the logs!18:52
@iglesiasgshogun-buildbot, force build 'deb3 - modular_interfaces'18:53
shogun-buildbotThe build has been queued, I'll give a shout when it starts18:53
@iglesiasgshogun-buildbot, aright18:53
shogun-buildbotbuild #44 of deb4 - python3 is complete: Failure [failed test python modular]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb4%20-%20python3/builds/44  blamelist: iglesias <fernando.iglesiasg@gmail.com>19:06
@iglesiasgparijat, do you close and open a new PR when you update it for any special reason??19:14
parijatiglesiasg, not always this time I got non-fastforward error so thats why I did it19:15
@iglesiasgparijat, sure, normal. It is fine to force the push in this case though. git push --force ...19:16
parijatiglesiasg, alright19:16
parijatiglesiasg, I reverted the randomization step! If need be we can change it later with proper backgroud study.19:21
@iglesiasgparijat, good idea19:21
@iglesiasgnow another two tests failing in travis....19:22
@iglesiasgI believe this is a random thing though, unrelated19:23
shogun-buildbotbuild #2150 of deb3 - modular_interfaces is complete: Failure [failed test libshogun]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb3%20-%20modular_interfaces/builds/2150  blamelist: iglesias <fernando.iglesiasg@gmail.com>19:33
shogun-buildbotbuild forced [ETA 30m35s]19:35
shogun-buildbotI'll give a shout when the build finishes19:35
-!- travis-ci [~travis-ci@ec2-54-234-103-77.compute-1.amazonaws.com] has joined #shogun19:35
travis-ci[travis-ci] it's iglesias's turn to pay the next round of drinks for the massacre he caused in shogun-toolbox/shogun: http://travis-ci.org/shogun-toolbox/shogun/builds/1760997319:35
-!- travis-ci [~travis-ci@ec2-54-234-103-77.compute-1.amazonaws.com] has left #shogun []19:35
parijatiglesiasg, all tests have passed! yippie!! :) Thanks again20:07
@iglesiasgparijat, good good20:08
@iglesiasgparijat, I will have a complete look at the PR soon, but I can't promise will do today :S20:08
-!- new_lido [~walid@41.218.175.100] has quit [Quit: Leaving]20:09
parijatiglesiasg, sure take your time. meanwhile let me find something else to work on! :)20:10
@iglesiasgparijat, all rght20:18
@iglesiasgsounds good20:18
shogun-buildbotbuild #2151 of deb3 - modular_interfaces is complete: Success [build successful]  Build details are at http://buildbot.shogun-toolbox.org/builders/deb3%20-%20modular_interfaces/builds/215120:22
@iglesiasggood good20:22
@iglesiasgshogun-buildbot, dance20:22
shogun-buildbot<(^.^<)20:22
shogun-buildbot<(^.^)>20:22
shogun-buildbot(>^.^)>20:22
shogun-buildbot(7^.^)720:22
shogun-buildbot(>^.^<)20:22
-!- parijat [671b082a@gateway/web/freenode/ip.103.27.8.42] has quit [Ping timeout: 245 seconds]20:35
-!- Marty28 [~marty@46.28.87.56] has joined #shogun21:21
-!- Marty28 [~marty@46.28.87.56] has quit [Client Quit]21:24
-!- new_lido [~walid@41.218.175.100] has joined #shogun22:34
-!- new_lido [~walid@41.218.175.100] has quit [Quit: Leaving]22:53
-!- iglesiasg [~iglesiasg@524AE0A7.cm-4-3d.dynamic.ziggo.nl] has quit [Quit: Leaving]23:16
--- Log closed Sun Jan 26 00:00:10 2014