Mailman 3 September 2020 - scikit-learn

scikit-learn monthly meeting September 28th 2020
by Chiara Marmo Sept. 28, 2020

Sept. 28, 2020

Dear list, The next scikit-learn monthly meeting will take place on Monday September 28th at 12PM UTC: https://www.timeanddate.com/worldclock/meetingdetails.html?year=2020&month=… While these meetings are mainly for core-devs to discuss the current topics, we are also happy to welcome non-core devs and other project maintainers. Feel free to join, using the following link: https://meet.google.com/xhq-yoga-rtf If you plan to attend and you would like to discuss something specific about your contribution please add your name (or github pseudo) in the " Contributors <https://hackmd.io/YNlQz61rTvy0CgBxLeZnHw#Contributors>" section, of the public pad: https://hackmd.io/YNlQz61rTvy0CgBxLeZnHw Best, Chiara

3 2

License questions
by Hideshi Takami Sept. 23, 2020

Sept. 23, 2020

Nice to meet you. I have a question. I am creating teaching materials on machine learning for commercial purposes. Can I use screenshots from the website (https://scikit-learn.org/) for videos and presentation materials?

2 1

Sprint leaders wanted for SciPy Japan
by Juan Nunez-Iglesias Sept. 22, 2020

Sept. 22, 2020

Hello scikit-learners! I am sprints chair for the upcoming SciPy Japan virtual conference [1]. It’s running Oct 30-31 (main conference) and Nov 1-2 (sprints). This is the second SciPy Japan conference and the first with sprints. The sprints officially run from 9am to 5pm Tokyo time, which corresponds to 11am-7pm Australia Eastern time and 4pm-midnight Sat-Sun USA West Coast. (I won’t bother with the Europe time. 😂) We currently have sprints confirmed for CuPy, dask-image, Apache Arrow, scikit-image, Sphinx, and napari. It would be fantastic if we could get some scikit-learn core devs to participate. I also want to thank Reshama Shaikh for her writeup [2] about the scikit-learn online sprint in June, it is invaluable in helping me get set up for next month. (And the rest of the team for all the resources cited therein, e.g. Andy’s video intro.) If people have any additional tips not shared in that post — some of the action items are a bit open ended, e.g. “Three platforms (Zoom, Discord and Gitter) were confusing for attendees. One platform was preferred.” —, then I would definitely appreciate someone reaching out to me with more tips! Thank you, Juan.

1 1

New members of the triage team: Albert, Lucy, & Reshama
by Gael Varoquaux Sept. 17, 2020

Sept. 17, 2020

We are excited to welcome new members to the triage team: * Albert Thomas https://github.com/albertcthomas * Lucy Liu https://github.com/lucyleeow * Reshama Shaikh https://github.com/reshamas Their thorough work on helping the community is much appreciated. Thanks!! Gaël -- Gael Varoquaux Research Director, INRIA Visiting professor, McGill http://gael-varoquaux.info http://twitter.com/GaelVaroquaux

2 1

Question about n_jobs in KMeans function
by Mingzhe Hu Sept. 15, 2020

Sept. 15, 2020

Hi scikit-learn contributors, I hope you are all doing well these days. I am now working on the KMeans clustering acceleration algorithm and I would like to use your library as a reference. Your codes are amazing and inspire me a lot in developing a more efficient solution. But I still have a question about a certain parameter in sklearn.cluster.KMeans().fit(). The installed version of sklearn is 0.23.0. I noticed there is a parameter named n_jobs. When I set this to 1, the function runs faster than that equals to -1. It's confusing to me. I posted the question with more details on Stack Overflow and here is the link: https://stackoverflow.com/questions/63887062/questions-about-n-jobs-in-skle…. You can check it and we can have more discussions. Thank you for your time and looking forward to your reply. All the best, Mingzhe HU -- Mingzhe HU Columbia University in the City of New York M.S. in Electrical Engineering mh4116(a)columbia.edu

1 0

Hyperparameter range suggestion for Grid Search
by Ivomar Brito Soares Sept. 2, 2020

Sept. 2, 2020

Hi everyone, One difficulty that I had in the past while using, for example, GridSearch or Randomized Search for hyperparameter tuning is which range of values seems reasonable to be used for each different classifier or regressor for example, I always need to google example of parameters ranges to use in those searches and is not always easy to find. Have you guys never thought of adding a suggestion of the ranges of such parameters in the user guide that could give some guidance to the user in this search? Is this list the ideal place to give a suggestion like this? If no, let me know where please. Let me know what you think. Cheers, -- Ivomar Brito Soares https://www.linkedin.com/in/ivomar-brito-soares-26b3b9151/

1 0