08:36 < jenkins-mlpack2> Project mlpack - git commit test build #85: STILL UNSTABLE in 1 hr 10 min: http://ci.mlpack.org/job/mlpack%20-%20git%20commit%20test/85/

08:36 < jenkins-mlpack2> noreply: Merge pull request #1649 from KimSangYeon-DGU/develop-mc

09:47 < rajiv_> The chat logs of 16/1/19 is not found in http://www.mlpack.org/irc/

09:57 < jenkins-mlpack2> Project docker mlpack nightly build build #189: FAILURE in 1 day 4 hr: http://ci.mlpack.org/job/docker%20mlpack%20nightly%20build/189/

14:03 < Toshal> privmsg nickserv : HI

14:38 < rcurtin> rajiv_: I will look into that

14:39 < Toshal> Hi,I am working on #1483 issue Adapt classifiers to return final objective value from train().

14:42 < rcurtin> Toshal: sounds good, when you have a working PR I'm happy to review it

14:44 < Toshal> I have gone through decision tree .In this algorithm's training is done with gini impurity and we try to optimize it. so do we need to return that as our objective value from train? This may be a silly question.

14:45 < Toshal> I have seen that it is not having any loss function like logistic regression

14:47 < rcurtin> with a decision tree we're maximizing entropy, so maybe returning negative entropy is reasonable

14:47 < rcurtin> (negative so that smaller means better, which it usually would with a model that's minimizing an objective function)

15:11 < rcurtin> rajiv_: fixed now... no idea what went wrong

15:11 < rcurtin> I just rebuilt the pages

15:13 < rcurtin> ShikharJ: let me know what you're thinking about #1301 (KDE)---I'd like to merge it, but I'm happy to wait for your review to be done

15:18 < Toshal> Can I make a PR step-wise that means after updating one or two classifiers so that I will know my errors quickly?

15:20 < rcurtin> you shouldn't use Travis as something to check for errors

15:21 < rcurtin> instead you should compile locally, and only once you have it working locally should you open a PR

15:21 < rcurtin> I'm not sure if that's what you meant

15:21 < rcurtin> but like I said in the PM, I'm happy to review a PR once it passes all the CI tests

15:35 < Toshal> No no that is not what i am saying. Actually, I am quite new to these algorithms . So I may return something wrong . So I thought that it will be better that if I work on two three classifiers and then shift towards newer ones.

15:43 < rcurtin> Toshal: ok, I see you what you mean, and that sounds fine to me

15:44 < rcurtin> zoq: I have a problem I was hoping you could help with

15:44 < rcurtin> I'm looking for more things like Moderat to listen to, but they only made three albums

15:45 < rcurtin> so I'm curious if you have any related recommendations... :)

15:52 < jenkins-mlpack2> Yippee, build fixed!

15:52 < jenkins-mlpack2> Project mlpack - git commit test build #86: FIXED in 50 min: http://ci.mlpack.org/job/mlpack%20-%20git%20commit%20test/86/

18:35 < jenkins-mlpack2> Project docker mlpack nightly build build #191: NOW UNSTABLE in 3 hr 31 min: http://ci.mlpack.org/job/docker%20mlpack%20nightly%20build/191/

19:29 < gauravcr7rm> Hello everyone, i want to write binding test for gmm_probability and gmm_generate for which i have to take a sample gmm model which i dont know how to take

19:29 < gauravcr7rm> please suggest a way to take a gmm model sample

19:48 < zoq_> rcurtin: That's difficult, Trentemoller is somewhat similar but at the same time different.

19:50 < zoq> gauravcr7rm: Hello, you can use gmm_train to get a model.

19:51 < zoq> gauravcr7rm: https://www.mlpack.org/docs/mlpack-git/man/mlpack_gmm_train.html might be helpful.

19:52 < zoq> gauravcr7rm: Or http://www.mlpack.org/docs/mlpack-3.0.4/python/gmm_train.html if you like to use python.

19:56 < zoq> ShikharJ: Sounds good to me, happy to co-mentor if you need any help. Do you have any plans in what direction you like to go?

19:57 < zoq> rajiv_: Not sure, I can follow, the log loads for me.

20:28 < ShikharJ> rcurtin: I'll provide the final review today itself. Thanks for waiting :)

20:30 < ShikharJ> zoq: I'll have to give it a thought, but one part of it quite possibly would be to wrap up on the existing PRs. I'll update the Ideas page as I get them.

20:38 < zoq> ShikharJ: Sounds good.