IRC logs of #shogun for Saturday, 2011-07-16

« Friday, 2011-07-15 Index Sunday, 2011-07-17 »
--- Log opened Sat Jul 16 00:00:25 2011
-!- blackburn [~blackburn@188.122.238.99] has quit [Quit: Leaving.]00:37
@sonney2khmmhhh blackburn gone already...02:01
-!- f-x` [~user@117.192.203.179] has quit [Ping timeout: 260 seconds]04:24
-!- f-x [~user@117.192.203.179] has joined #shogun06:24
[1]warpymorning07:20
-!- in3xes_ [~in3xes@180.149.49.227] has joined #shogun07:22
-!- in3xes [~in3xes@210.212.58.111] has quit [Ping timeout: 240 seconds]07:24
-!- f-x [~user@117.192.203.179] has quit [Remote host closed the connection]07:48
-!- in3xes [~in3xes@180.149.49.230] has joined #shogun08:35
-!- in3xes__ [~in3xes@59.163.196.5] has joined #shogun08:40
-!- in3xes1 [~in3xes@180.149.49.227] has joined #shogun08:40
-!- in3xes_ [~in3xes@180.149.49.227] has quit [Ping timeout: 240 seconds]08:42
-!- in3xes [~in3xes@180.149.49.230] has quit [Ping timeout: 264 seconds]08:43
-!- in3xes__ is now known as in3xes08:51
-!- gsomix [~gsomix@85.26.235.15] has joined #shogun08:58
-!- gsomix [~gsomix@85.26.235.15] has quit [Quit: Ухожу я от вас (xchat 2.4.5 или старше)]09:16
-!- alesis_ [~alesis@188.74.87.206] has joined #shogun10:00
-!- alesis-novik [~alesis@188.74.87.206] has quit [Ping timeout: 255 seconds]10:01
-!- in3xes [~in3xes@59.163.196.5] has quit [Quit: Leaving]10:32
CIA-87shogun: Shashwat Lal Das master * rca17a15 / src/libshogun/features/StreamingSparseFeatures.h : Added updating of current_num_features for StreamingSparseFeatures. - http://bit.ly/p61GnM11:24
CIA-87shogun: Shashwat Lal Das master * r8f1ed0d / src/libshogun/features/StreamingSparseFeatures.h : Added braces around for loop. - http://bit.ly/o6I0z811:24
CIA-87shogun: Shashwat Lal Das master * r563058f / (2 files): Modified bias scale value in SGD. Updated loss function to be the default used in the original svmsgd2. - http://bit.ly/pPkpfd11:24
CIA-87shogun: Soeren Sonnenburg master * r3e6d260 / (3 files in 2 dirs):11:24
CIA-87shogun: Merge pull request #205 from frx/streaming_111:24
CIA-87shogun: Added updating of current_num_features for StreamingSparseFeatures. - http://bit.ly/nBNHYa11:24
-!- blackburn [~blackburn@188.122.238.99] has joined #shogun11:34
blackburnsonney2k: have you seen that msgs from Todd_?11:35
@sonney2kblackburn, yes11:35
blackburnany candidate?11:35
blackburn:)11:35
@sonney2kblackburn, we need to recruit new people!11:36
blackburnfrom san francisco?11:36
blackburn:D11:36
blackburnif you are going to san franciscooo11:36
blackburnyou should weeeear some flowers in your hair11:36
@sonney2kI might attend the GSoC mentors meeting in october but I cannot really travel that much with kids11:37
@sonney2kw/o them in this case ...11:37
blackburnI see11:38
CIA-87shogun: Soeren Sonnenburg master * r887dcc8 / src/Makefile.template : fix java install - http://bit.ly/nsYZTr11:38
@sonney2kblackburn, btw you don't need make install for java (at least currently)11:38
blackburnyeah but I have configured it to python_modular and java_modular, so sometimes need to install ;)11:39
@sonney2kblackburn, now it works anywyas :)11:40
blackburnokay11:40
blackburnthanks11:40
@sonney2kblackburn, since you are the java expert11:41
@sonney2kwhat are modules in java?11:41
@sonney2kI just realized taht modules can implement a certain interface...11:42
@sonney2kthat is confusing me...11:42
blackburnoh okay seems I'm not an expert :D11:42
blackburnmodule - implements?11:43
@sonney2kblackburn, well just look at the generated Features.java11:44
@sonney2kanyways try to run check.sh and see how far you get...11:44
@sonney2kI didn't manage to get the base object to implement the Serializable interface11:44
@sonney2k(that statement is missing - rest would be trivial)11:44
-!- blackburn1 [~blackburn@188.122.238.99] has joined #shogun11:45
-!- blackburn [~blackburn@188.122.238.99] has quit [Quit: Leaving.]11:45
blackburn1sonney2k: I have never been using it :D11:46
blackburn1why you want to?11:46
[1]warpyhey guys11:48
blackburn1I thought swig uses packages, no surprisingly modules11:48
[1]warpydo you know when splovin is usually around here11:48
blackburn1[1]warpy: hi11:48
blackburn1can't tell for sure11:49
blackburn1well he is from china11:49
blackburn1sonney2k: java modules is a java 7 feature, are you sure you talking about modules? :)12:21
blackburn1what's up with features.java?12:24
-!- blackburn1 [~blackburn@188.122.238.99] has quit [Read error: No route to host]13:01
-!- blackburn [~blackburn@188.122.238.99] has joined #shogun13:01
[1]warpysoeren, can you explain how did you get those svm packages to learn on millions of examples and test on billions ?13:28
-!- in3xes [~in3xes@180.149.49.230] has joined #shogun14:12
-!- Netsplit *.net <-> *.split quits: @mlsec14:18
-!- Netsplit over, joins: @mlsec14:19
-!- in3xes [~in3xes@180.149.49.230] has quit [Quit: Leaving]16:14
-!- in3xes1 [~in3xes@180.149.49.227] has quit [Quit: Leaving]16:54
-!- in3xes [~in3xes@180.149.49.227] has joined #shogun16:55
-!- mrsrikanth [~mrsrikant@59.92.82.50] has joined #shogun17:23
-!- mrsrikanth [~mrsrikant@59.92.82.50] has quit [Quit: Leaving]17:56
-!- blackburn [~blackburn@188.122.238.99] has quit [Quit: Leaving.]18:25
-!- gsomix [~gsomix@85.26.234.19] has joined #shogun19:40
gsomixhi all19:40
-!- blackburn [~blackburn@188.122.238.99] has joined #shogun20:10
-!- in3xes_ [~in3xes@180.149.49.230] has joined #shogun20:34
-!- f-x [~user@117.192.223.132] has joined #shogun20:46
-!- gsomix [~gsomix@85.26.234.19] has quit [Ping timeout: 260 seconds]21:01
-!- in3xes_ [~in3xes@180.149.49.230] has quit [Ping timeout: 276 seconds]22:34
@sonney2kblackburn, around?23:15
blackburnsonney2k: yeap23:15
@sonney2kblackburn, hey hey then23:15
blackburn:D23:15
@sonney2kdid you try to run the java examples?23:15
blackburnyes, I tried23:16
blackburnsome fails, some ok23:16
blackburnI had a question23:16
blackburnminimal test fails, and it's code looks a bit strange23:16
@sonney2kclassifier_libsvm_minimal_modular ?23:17
blackburnminimal_test.java23:17
@sonney2kremove this23:18
blackburnanother question: kernel pca23:19
blackburnwhy it is commented now?23:19
@sonney2kno idea23:20
@sonney2kshouldn't be23:20
CIA-87shogun: Sergey Lisitsyn master * r4d12457 / examples/undocumented/java_modular/minimal_test.java : Removed unnecessary java example minimal_test - http://bit.ly/nXRaWz23:20
blackburnok it was since we have shogun on github23:21
blackburnI am just asking because you wrote it ;)23:21
@sonney2kplease fix then :)23:22
blackburnbtw was it working?23:22
blackburnI mean have you tested it23:22
@sonney2kblackburn, ahh the computation yes - the apply not yet23:22
blackburnwhat is the issue with apply?23:23
@sonney2kI didn't implement it yet...23:24
blackburnah okay, can I leave it now, may be some day you will? ;)23:25
@sonney2kI would prefer you doing it :)23:25
@sonney2kI can send you some matlab code from vojtech for this23:25
blackburnhmm yeah, it would be ok23:25
blackburnI just have no deep comprehension of (k)pca23:26
blackburnstrange for me, who are doing dimreduction, yes :D23:26
bettyboo<:*)23:26
blackburnI'd like to focus on it after HLLE (or in background)23:28
@sonney2ksure sure23:29
blackburnvojtech is a big fan of matlab ?23:30
blackburnlooks like he is doing everything in matlab23:30
@sonney2kblackburn, he has that big matlab toolbox23:30
@sonney2kerr wrote23:30
@sonney2knot has23:30
blackburnwhich?23:30
@sonney2khttp://cmp.felk.cvut.cz/cmp/software/stprtool/index.html23:31
@sonney2kjust look at methods...23:31
blackburnoh matlabby shogun23:32
blackburnhey it is HUGE23:33
@sonney2kblackburn, btw I have an idea for another small task23:33
@sonney2kprobabilistic outputs for svm23:33
@sonney2kthat means sigmoid fit23:33
@sonney2kor histogram based23:33
@sonney2kone could even borrow libsvm's code for the sigmoid fit :)23:34
bettyboo!!23:34
blackburnI was persuading gsomix to attach C5.023:35
blackburnsonney2k: have you any ideas how it could be done?23:35
@sonney2kC5.0?23:35
blackburnyes23:36
@sonney2knot really. I havent' looked at their code yet23:36
blackburnoh you will be astonished :D23:36
@sonney2kwhat I would do is create a new folder classifier/decisiontree23:37
@sonney2kand then move all of c5.0* sources in there and then23:37
blackburnit should be some kind of wrapper or so23:37
@sonney2kremove the main* stuff23:37
blackburnjust calling C5.0 things23:37
@sonney2kand modify the algorithm to use shogun's feature representation23:37
@sonney2kso not a really a wrapper23:38
@sonney2k(we did similar things with all the svm's)23:38
blackburncons of this way is that we have to modify that code23:38
blackburnnot just attach it somehow23:38
@sonney2kblackburn, yes - but there is no way around this23:39
@sonney2kotherwise we would have to copy the features and have everything twice in memory23:39
@sonney2kblackburn, of course one can start like this and do the required modifications later23:40
blackburnyou should take a look on C5.0 code, it is something I can't describe23:40
@sonney2kblackburn, it is from a different century...23:41
blackburnsomething like DSL for C :D23:42
@sonney2kblackburn, I mean the author is already retired by now...23:44
@sonney2kit is not too bad though23:45
@sonney2k(you haven't had a look at svmlight's source code yet :)23:45
bettyboostrange :*)23:45
blackburnwho is author of C5?23:45
@sonney2kblackburn, what are the *.i files?23:45
@sonney2kRoss Quinlan23:46
blackburnno idea, some defines here23:46
@sonney2khttp://www.rulequest.com/Personal/23:46
blackburnI didn't know he is retired23:47
@sonney2kblackburn, what is needed then is to create a wrapper class C5023:47
@sonney2kwell he got his PhD in 1968 ...23:47
blackburnhuh23:48
f-xsonney2k: hey, where do you think it would be appropriate to define all the loss functions together?23:56
@sonney2kf-x, I think this could be a new directory23:57
@sonney2klosses23:57
@sonney2kor loss23:57
f-xsonney2k: and then something like set_loss_fuction in the classifier api?23:59
f-x*function23:59
--- Log closed Sun Jul 17 00:00:24 2011
« Friday, 2011-07-15 Index Sunday, 2011-07-17 »

Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!