--- Log opened Sun Apr 24 00:00:36 2011 | ||
-!- sploving [sploving@210.77.26.145] has joined #shogun | 02:15 | |
-!- sploving [sploving@210.77.26.145] has left #shogun [] | 02:29 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 06:35 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has left #shogun [] | 06:48 | |
-!- siddharth [~siddharth@117.211.88.150] has joined #shogun | 08:28 | |
-!- akhil_ [75d35896@gateway/web/freenode/ip.117.211.88.150] has quit [Ping timeout: 252 seconds] | 08:31 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has joined #shogun | 08:42 | |
-!- ameerkat [~ameerkat@184-98-140-155.phnx.qwest.net] has quit [Ping timeout: 252 seconds] | 09:03 | |
-!- blackburn [~qdrgsm@109.226.117.183] has joined #shogun | 09:07 | |
* siddharth exam :| | 09:21 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has quit [Read error: Connection reset by peer] | 10:12 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has joined #shogun | 10:12 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has quit [] | 11:03 | |
-!- Ziyuan [~Ziyuan@121.33.190.190] has joined #shogun | 11:06 | |
-!- Ziyuan [~Ziyuan@121.33.190.190] has quit [Remote host closed the connection] | 11:24 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has joined #shogun | 11:24 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 12:17 | |
-!- siddharth [~siddharth@117.211.88.150] has quit [Ping timeout: 260 seconds] | 12:25 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has quit [Quit: Page closed] | 12:40 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 13:34 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has quit [Quit: Page closed] | 14:31 | |
-!- sploving [sploving@210.76.202.198] has joined #shogun | 14:31 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 14:39 | |
-!- sploving [sploving@210.76.202.198] has quit [Ping timeout: 250 seconds] | 14:58 | |
-!- sploving [sploving@210.76.202.198] has joined #shogun | 15:11 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has quit [Ping timeout: 253 seconds] | 15:14 | |
-!- Ziyuan [~Ziyuan@116.22.51.87] has quit [] | 15:31 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 15:34 | |
-!- sploving [sploving@210.76.202.198] has quit [] | 15:44 | |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has quit [Quit: Page closed] | 16:35 | |
-!- serialhex [~quassel@99-101-149-136.lightspeed.wepbfl.sbcglobal.net] has joined #shogun | 17:17 | |
serialhex | man! my computer is down for a day and a half and no updates to shogun! shame on you all!!! :P | 17:28 |
---|---|---|
serialhex | sonney2k: i just read the back logs & i hope everyone feels better soon! | 17:28 |
blackburn | eh, no updates but some pulls ;) | 17:33 |
serialhex | blackburn, yeah i read about your ROC troubles... did you get it all sorted out?? | 17:36 |
blackburn | seems so :) | 17:37 |
serialhex | sounds good! | 17:37 |
blackburn | now doing some work on numerical methods, arghh, I hate it | 17:37 |
serialhex | what work?? | 17:37 |
* serialhex likes numerical methods | 17:37 | |
blackburn | have to numerical integrate :) | 17:38 |
@bettyboo | :) | 17:38 |
josip | just do the trapezoid method :D | 17:38 |
josip | for ROC | 17:38 |
serialhex | thats not too hard, what integration method you using?? | 17:39 |
blackburn | now finishing last part, kantorovich's method for integrating improper integrals | 17:39 |
* serialhex has never heard of kantorovich or his method if integration | 17:39 | |
blackburn | that is not hard at all, but many methods and spent much time to write a report | 17:39 |
serialhex | you know blackburn, you dont have to do your schoolwork, gsoc project, _and_ our gsoc projects too... :P | 17:40 |
@bettyboo | ;> serialhex | 17:40 |
blackburn | eh? don't understand ;) | 17:41 |
serialhex | in other words: dont work yourself to death!!! :D | 17:41 |
blackburn | ah, I just want to free my time on next week, I don't have to do this work now | 17:43 |
serialhex | ok, i can understand that, but still, you're not a machine! | 17:44 |
serialhex | ...or are you? | 17:44 |
* blackburn looks at himself | 17:45 | |
blackburn | no, seems no ;) | 17:45 |
serialhex | ok, good! | 17:46 |
blackburn | eh! it's cold on street | 17:47 |
blackburn | want to run a little :) | 17:48 |
@bettyboo | rahaha | 17:48 |
blackburn | done that mthfcking report | 17:51 |
serialhex | it's nice here... though i kind of miss a nice brisk day where it's not too cold & theres no wind, then you can run forever! | 17:51 |
serialhex | cool! | 17:51 |
serialhex | FFS!!! WHY do all these journals have to charge an INSANE amount of money for A FSCKING PAPER!!!!!!!!!! | 17:52 |
blackburn | :D | 17:54 |
serialhex | OOOH!!!! it's like $30+ for ONE FREAKING PAPER!!! and all i'm doing is trying to find out about kantorovich and his improper integral method!!! | 17:55 |
blackburn | http://www.mathnet.ru/php/archive.phtml?wshow=paper&jrnid=tm&paperid=1054&option_lang=eng | 17:56 |
blackburn | there is no english version though | 17:57 |
blackburn | :) | 17:57 |
serialhex | ooh!!! ,lets see if google can translate!!! | 17:57 |
serialhex | oh, it's a pdf... :/ | 17:58 |
blackburn | yeap, 33 | 17:58 |
blackburn | 1933 I mean | 17:59 |
blackburn | +8C and I'm going to freeze my balls some :D | 18:00 |
serialhex | hmm... given time i _might_ be able to divine something out of this from just the math... | 18:00 |
serialhex | damn! | 18:00 |
serialhex | 46.4f!!!! ffs thats cold!!!! | 18:01 |
* blackburn is out for some 'jogging' ;) | 18:01 | |
serialhex | have fun! | 18:02 |
blackburn | rhh! not so cold when running :D | 18:36 |
serialhex | thats good to know!! | 19:04 |
blackburn | time for shogun development! | 19:11 |
-!- siddharth_ [~siddharth@117.211.88.150] has joined #shogun | 19:12 | |
serialhex | good evening siddharth_! | 19:15 |
siddharth_ | good evening | 19:15 |
siddharth_ | wassup | 19:15 |
serialhex | not too much, catching up on the things i missed out while i was wonrking on my computer | 19:16 |
serialhex | trying to install gentoo, but i think i messed up the install | 19:17 |
siddharth_ | I see | 19:18 |
serialhex | what about yourself? | 19:18 |
siddharth_ | just came back from dinner | 19:18 |
siddharth_ | so tomorrow is "the" day | 19:20 |
serialhex | yes it is! | 19:20 |
serialhex | i wonder who will get the slots | 19:21 |
siddharth_ | fingers crossed :) | 19:22 |
serialhex | same here! | 19:22 |
blackburn | it will be at 12-00 GMT-8? | 19:23 |
serialhex | i think so lemme check my calander | 19:23 |
serialhex | yeah, it says 3pm on my calendar, and it'll be 12pm there, so you're right siddharth_ | 19:24 |
serialhex | brb, laundry | 19:25 |
blackburn | ahaha I completely f-cked up with that ROC | 19:53 |
blackburn | author of perfmeasure too :D | 19:53 |
-!- ameerkat [~ameerkat@184-98-140-155.phnx.qwest.net] has joined #shogun | 20:01 | |
-!- ChanServ changed the topic of #shogun to: Shogun Machine Learning Toolbox | We participate in GSoC with 5 slots | Timeline http://bit.ly/gy7Pdi | Channel logs http://bit.ly/eQDk8Q | 20:21 | |
-!- ChanServ changed the topic of #shogun to: Shogun Machine Learning Toolbox | We participate in GSoC - student acceptance notification countdown http://goo.gl/JPGx3 5 | GSoC timeline http://bit.ly/gy7Pdi | Channel logs http://bit.ly/eQDk8Q | 20:23 | |
blackburn | hehe | 20:24 |
* sonney2k goes fixing a wheel on the baby buggy | 20:24 | |
* sonney2k dammed epic wheel fixing fail - now for the same thing again | 21:19 | |
blackburn | good luck to you :) | 21:20 |
-!- dvevre [b49531e3@gateway/web/freenode/ip.180.149.49.227] has joined #shogun | 21:49 | |
blackburn | sonney2k: hurray! http://dl.dropbox.com/u/10139213/share/eq.png | 21:54 |
* sonney2k *sigh* another fail | 22:01 | |
* sonney2k gives up | 22:01 | |
@sonney2k | could be right... | 22:01 |
blackburn | sonney2k: it is equal to one mldata-utils made | 22:02 |
@sonney2k | ahh - then great :) | 22:03 |
@sonney2k | is this in the code from the pull request yesterday? | 22:03 |
blackburn | yeap, I fixed it and then fixed the fixes :D | 22:03 |
@sonney2k | blackburn, sounds like what I usually do :) | 22:04 |
@sonney2k | blackburn, I am looking at your pull request right now | 22:04 |
blackburn | today was tangled with some issues with it | 22:04 |
@sonney2k | do you want comments here or there? | 22:04 |
blackburn | I don't, just for you ;) | 22:05 |
@bettyboo | :Q | 22:05 |
blackburn | will remove it just before you will merge | 22:05 |
@sonney2k | blackburn, I don't understand... | 22:05 |
blackburn | ah | 22:06 |
blackburn | HEHEEH | 22:06 |
blackburn | was thinking about comments in .cpp | 22:06 |
blackburn | :D | 22:06 |
blackburn | sonney2k: as you wish | 22:06 |
@sonney2k | blackburn, then here: after for loops, please have one blank line | 22:07 |
blackburn | okay | 22:07 |
@sonney2k | blackburn, add a link or reference to the fawcett paper in the documentation | 22:08 |
blackburn | sonney2k: to .cpp or .h? | 22:08 |
@sonney2k | .h | 22:08 |
@sonney2k | in .cpp I don't care that much about documentation | 22:09 |
@sonney2k | only if you do hard to grasp stuff comments are welcome - otherwise having comments there hints that your code is unreadable. | 22:10 |
blackburn | sonney2k: should I remove it in .cpp? | 22:10 |
@sonney2k | blackburn, no it is ok | 22:13 |
@sonney2k | blackburn, then if you do a for loop and a more complex if statement inside it (or another for loop inside) - please use { } to make it more readable | 22:14 |
@sonney2k | (line 67) | 22:14 |
blackburn | fixed | 22:15 |
@sonney2k | blackburn, the pos_count*neg_count is dangerous - please use a cast to float64_t(pos_count)*neg_count | 22:17 |
blackburn | sonney2k: okay | 22:18 |
blackburn | sonney2k: is it ok? | 22:18 |
blackburn | Tom Fawcett "An Introduction to ROC analysis" | 22:18 |
@sonney2k | yes | 22:18 |
blackburn | should I write some more information, e.g. journal or etc | 22:18 |
@sonney2k | blackburn, yeah - copy the reference from wikipedia | 22:19 |
blackburn | hehe, good idea | 22:19 |
@sonney2k | the get_ROC will crash - but that is ok for now - until the swig issue is fixed | 22:19 |
blackburn | sonney2k: why it will? | 22:20 |
@sonney2k | blackburn, memory not copied | 22:20 |
blackburn | ah.. I had a lot of problems during testing and etc | 22:20 |
@sonney2k | blackburn, well if you want to have it work reliably you have to copy | 22:21 |
@sonney2k | look at e.g. line 361 in SimpleFeatures.h | 22:21 |
@sonney2k | for how to do it | 22:21 |
blackburn | sonney2k: oh, thank you | 22:21 |
blackburn | will do it now | 22:21 |
@sonney2k | but as I said at some point we have to fix this | 22:22 |
blackburn | sonney2k: why it use malloc? | 22:24 |
blackburn | ah | 22:25 |
blackburn | sorry ;) | 22:25 |
@sonney2k | blackburn, python uses it to alloc things... | 22:25 |
blackburn | sonney2k: meant why not new | 22:26 |
@sonney2k | blackburn, python is not c++ | 22:26 |
blackburn | eh.. okay | 22:26 |
blackburn | sonney2k: have you any more remarks? | 22:29 |
blackburn | hm.. it fails now | 22:29 |
@sonney2k | blackburn, also spaces after if () | 22:31 |
@sonney2k | { | 22:31 |
@sonney2k | } | 22:31 |
@sonney2k | err new lines | 22:31 |
blackburn | sonney2k: done | 22:36 |
blackburn | pushed | 22:36 |
@sonney2k | looks good | 22:45 |
@sonney2k | I was for the last 10 minutes looking for the merge help buttong - which apparently disappeard http://support.github.com/discussions/site/3548-merge-help-button-missing | 22:46 |
blackburn | someone stealed it? | 22:46 |
CIA-110 | shogun: lionelc master * rbd60ad6 / (3 files): minor changes -- fixed whitespace issues - http://bit.ly/eI6CnY | 22:48 |
CIA-110 | shogun: Soeren Sonnenburg master * r7e1214f / (22 files): Merge branch 'master' of https://github.com/lionelc/shogun - http://bit.ly/hDAtci | 22:48 |
CIA-110 | shogun: Christian Widmer master * re6cec42 / (4 files): merged old changes from local svn repo into git repo - http://bit.ly/ffm6K6 | 22:48 |
CIA-110 | shogun: Soeren Sonnenburg master * rf75fb0b / (4 files): Merge branch 'master' of git://github.com/cwidmer/shogun - http://bit.ly/gOScuF | 22:48 |
blackburn | the big merge | 22:49 |
CIA-110 | shogun: Soeren Sonnenburg master * rea04aef / (3 files in 2 dirs): Merge git://github.com/SergeyLisitsyn/shogun - http://bit.ly/hLejTa | 22:49 |
blackburn | sonney2k: thanks for remarks and for example of copying especially, I was struggling two days long with some memory errors | 22:52 |
blackburn | 22 hours! | 22:53 |
@sonney2k | blackburn, ask if you get stuck - better than wasting time | 22:58 |
@sonney2k | but right I might not always be responsive :( | 22:58 |
blackburn | sonney2k: I tried but you wasn't there sometimes ;) | 22:58 |
blackburn | and at least I did other work I should do | 22:59 |
blackburn | sonney2k: is PRC similar to ROC? | 23:01 |
@sonney2k | sorry about that... | 23:01 |
blackburn | sonney2k: you don't have to sorry you have your affairs | 23:01 |
@sonney2k | blackburn, just implement the python code for now... I don't really know how to properly deal with the case when multiple outputs are the same | 23:01 |
blackburn | may be the same? | 23:03 |
blackburn | we have to ask fawcett about this :D | 23:03 |
blackburn | sonney2k: do we need DET? | 23:03 |
@sonney2k | blackburn, I mean I know that one can translate any point in ROC space to PR space | 23:03 |
@sonney2k | blackburn, wasn't DET not just 1-auROC or so? | 23:04 |
blackburn | it is, but graph will be not same, may be one couldn't want to translate it this way | 23:04 |
@sonney2k | blackburn, I don't care about it | 23:04 |
blackburn | ok, so I will not too | 23:05 |
blackburn | omg | 23:05 |
blackburn | precision=numpy.cumsum(pmap)/(numpy.arange(len(pmap),dtype=numpy.double)+1.0) | 23:05 |
blackburn | what a code! ;) | 23:05 |
blackburn | sonney2k: is there any way to fix some comment without new pull? | 23:14 |
@sonney2k | blackburn, just tell me which one and I hack it in | 23:15 |
@sonney2k | hmmhh seems like what I've just pushed doesn't build | 23:15 |
blackburn | sonney2k: ROCEvaluation.h line 70 | 23:16 |
blackburn | please fix it to | 23:16 |
blackburn | /** number of ROC graph points */ | 23:16 |
blackburn | sonney2k: hm. what error? | 23:16 |
@sonney2k | blackburn, some ifdef / etc not in your code | 23:16 |
@sonney2k | but cwidmer's... | 23:17 |
blackburn | hehe | 23:17 |
@sonney2k | your potential mentor =:-) | 23:17 |
blackburn | aha | 23:18 |
blackburn | assume he forgot to test it ;) | 23:18 |
@sonney2k | seems to be a common problem | 23:19 |
@sonney2k | would be your duty to teach him then ;-) | 23:20 |
blackburn | :D | 23:20 |
blackburn | sonney2k: btw, are applications working on your shogun? | 23:22 |
@sonney2k | you mean there are some real applications? like the ocr thingy on the homepage? | 23:22 |
blackburn | aha, I will write an error just after compile it | 23:23 |
@sonney2k | I guess most of them are now broken due to us changing too much | 23:23 |
blackburn | some issue with stringfeatures, iirc | 23:23 |
@sonney2k | could very well be | 23:23 |
blackburn | shogun is compiling very slow on my notebook! | 23:24 |
@sonney2k | I expect many more changes anyways so I won't bother about these yet | 23:24 |
@sonney2k | blackburn, use ccache and ./configure --enable-debug --disable-optimization | 23:24 |
@sonney2k | and only the interface you need | 23:24 |
@sonney2k | otherwise it is hell(tm) | 23:24 |
blackburn | i don't know what is ccache :) | 23:25 |
blackburn | debug is enabled | 23:25 |
blackburn | sonney2k: you said about 'steppiness' of ROC I showed you yesterday or so | 23:26 |
@sonney2k | blackburn, install and compile shogun twice and you will realize what ccache does :) | 23:26 |
@sonney2k | yes | 23:26 |
blackburn | seems it will be 'steppy' almost in every case | 23:27 |
blackburn | because it will have diag line only if there are equal labels | 23:27 |
blackburn | sonney2k: that picture I showed you today with ROC is for some noised random labels | 23:27 |
blackburn | it is 'steppy' if zoomed in | 23:28 |
@sonney2k | blackburn, ahh right - the convex hull thingy is just sth that can be done on top - the steppy one is the one that belongs to the classifier | 23:28 |
blackburn | Konrad said me about some averaging of ROC graph | 23:29 |
blackburn | if it was he :D | 23:29 |
@sonney2k | blackburn, mlsec ... yes | 23:29 |
blackburn | if averaging is necessary I could work on it too | 23:30 |
@sonney2k | that issue could come up when we do cross validation | 23:30 |
@sonney2k | not sure if it is necessary right now though | 23:30 |
blackburn | ok. it's good to me, because I want to get rid of evaluation and start working on CGraph class | 23:31 |
@sonney2k | blackburn, yes do what you prefer to work on! | 23:31 |
blackburn | but at first will implement PRC :) | 23:31 |
@sonney2k | thanks! | 23:31 |
blackburn | I have to finish or it will be unfinished | 23:32 |
blackburn | all things from perfmeasures are now implemented more 'modular', but not PRC | 23:32 |
blackburn | last one :) | 23:33 |
blackburn | it is compiling still.. | 23:33 |
blackburn | hurray | 23:38 |
@sonney2k | btw, mlsec mentioned yesterday (chat logs rule!) that roc shouldn't be computed on discrete outputs - true in general but not when you want to test that everything is ok :) | 23:41 |
@bettyboo | *g* | 23:41 |
blackburn | sonney2k: but what's up with ifdef in Chris' commits? | 23:42 |
@sonney2k | blackburn, I have fixed this but not yet pushed... | 23:42 |
@sonney2k | did you pull again? | 23:42 |
blackburn | sonney2k: I mean he don't fixed anything | 23:42 |
blackburn | with #ifdef | 23:43 |
blackburn | sonney2k: what you mean? | 23:43 |
@sonney2k | I don't know what you are saying | 23:43 |
* sonney2k is confused? | 23:43 | |
blackburn | :D | 23:43 |
blackburn | sorry | 23:43 |
blackburn | I mean Chris don't fixed any preprocessor things | 23:43 |
blackburn | why it is failing now? | 23:43 |
blackburn | didn't* | 23:44 |
@sonney2k | no idea.... | 23:44 |
blackburn | will fetch it and test | 23:45 |
blackburn | 21 hours left | 23:45 |
blackburn | :D | 23:45 |
blackburn | Ш рфму штыефддув | 23:48 |
blackburn | damn | 23:48 |
blackburn | I have installed ccache | 23:48 |
blackburn | but it is slow though | 23:48 |
blackburn | sonney2k: ah.. unterminated #ifdef | 23:56 |
@sonney2k | blackburn, did you enable it? yeah | 23:56 |
blackburn | enable what? | 23:56 |
@sonney2k | ccache? | 23:57 |
blackburn | nope, how I should? :D | 23:57 |
@sonney2k | read the docs :) | 23:57 |
@sonney2k | of ccache | 23:57 |
@sonney2k | /usr/share/doc/ccache/README.Debian in my case | 23:57 |
blackburn | thank you | 23:58 |
--- Log closed Mon Apr 25 00:00:37 2011 |
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!