[14:04:38] wikimedia/ores#1185 (ores - 1eccd35 : Amir Sarabadani): The build passed. https://travis-ci.org/wikimedia/ores/builds/464961399 [15:57:37] 10ORES, 10Scoring-platform-team, 10Analytics, 10Dumps-Generation, and 3 others: Decide whether we will include raw features - https://phabricator.wikimedia.org/T211069 (10awight) Offsite chat suggests that there's value in actually storing the raw "root" data sources that we build the feature tree from. L... [16:24:35] 10Scoring-platform-team (Current): Post to enwiki TeaHouse about conducting AI-experiment - https://phabricator.wikimedia.org/T209608 (10notconfusing) done at https://en.wikipedia.org/wiki/Wikipedia_talk:Teahouse#Experiment%20test%20using%20AI%20to%20invite%20users%20to%20Teahouse [16:25:10] 10Scoring-platform-team (Current): create prediction function for newcomerquality package - https://phabricator.wikimedia.org/T211192 (10notconfusing) done in: https://github.com/notconfusing/newcomerquality/commit/9c7b8b3e968fa10919e866d3ae040353130674a4 [16:34:08] 10Scoring-platform-team (Current): Prototype a bot framework that utilizes newcomerquality - https://phabricator.wikimedia.org/T211434 (10notconfusing) [16:46:28] 10Scoring-platform-team (Current): Prototype a bot framework that utilizes newcomerquality - https://phabricator.wikimedia.org/T211434 (10notconfusing) Threshhold analysis from: http://localhost:8888/notebooks/determine%20bot%20thresholds.ipynb ` # to get 150 per day/ 165 to have some buffer and for control gro... [16:47:33] 10Scoring-platform-team (Current): Prototype a bot framework that utilizes newcomerquality - https://phabricator.wikimedia.org/T211434 (10notconfusing) Using min instead of mean, is better because it's A) stricter and only 30% of users end up going multi-session [16:58:06] is there a meeting in 3 minutes or did I get that wrong? [17:00:16] notconfusing: we're all in a meeting at the moment so I assume no [17:00:31] an in-person kind of meeting [17:01:06] ok, it was on the calendar, but i'm not certain theres really that point in meeting remotely now, i just wanted to do the formalities [17:03:54] maybe i'll just give a status update to the channel. I had a really good week. I created the whole Make training pipeline for newcomerquality repo, and the prediciton pipeline, and I ran it on a 3000 newcomers as a simulation. I determined the threshold that a bot would need to use for the experiment. And speaking of the experiment I sync'd with Jmo , and we have a plan. I asked the TeaHouse community for input [17:03:57] on the plan and its already been a success. All in all very good. This next week I'll be building the bot-shell that'll use newocmerquality and set-up a live-test pre-experiment. [18:06:03] 10ORES, 10Scoring-platform-team (Current), 10User-Ladsgroup: Celery task pool doesn't degrade nicely. - https://phabricator.wikimedia.org/T175875 (10Ladsgroup) a:03Ladsgroup It's done in celery4 [18:06:18] 10ORES, 10Scoring-platform-team (Current), 10User-Ladsgroup: Celery task pool doesn't degrade nicely. - https://phabricator.wikimedia.org/T175875 (10Ladsgroup) 05Open>03Resolved [18:06:38] 10ORES, 10Scoring-platform-team (Current), 10User-Ladsgroup: Tasks should not be marked permanently revoked due to high system load - https://phabricator.wikimedia.org/T175860 (10Ladsgroup) 05Open>03Resolved a:03Ladsgroup