🌐 Mailman 3 July 2019 - scikit-learn - python.org

Test Sample Size
by Milton Pifano July 22, 2019

July 22, 2019

Dear scikit-learn subscribers. I am working on a multiclass classificacition project and I have found many resources about how to deal with an imbalaced dataset for trainning, bu I have not been able to find any reference on the test dataset size. Can anyone send some references? Thanks, Milton Pifano

2 1

Any machine learning used in storage company?
by lampahome July 19, 2019

July 19, 2019

Is there any application used in storage company? Can anyone briefly introduce what application in what company? thx

1 0

Monthly meetings between core developers
by Nicolas Hug July 18, 2019

July 18, 2019

Hi Everyone, The scikit-learn team have been expanding significantly lately: we have now 3 FTEs in NY, 1 in Berlin, and 3 (soon 4) in Paris. To scale efficiently, I think we should try to communicate more. *I'd like to propose monthly meetings* *between the core-developers*. This would be the occasion to: - communicate what everyone is currently working on - ask for feedback/reviews on some specific PRs - keep everybody apprised of the latest news/decisions regarding the project. Some discussions often take place in channels that some of us may miss. To keep it efficient, maybe we could have a hard time limit, e.g. 30 mins. One person would be in charge of conducting the meeting, and another one would take notes. We would take rounds every month. While meetings and notes would be public, only core-developers or strongly-involved members would be invited to join the discussion. I understand the time-zone differences and personal schedules will make it hard to arrange for all of us to be present. I'm not sure how to handle this equitably. We could have a document that sets the agenda and a place to take notes. For members that are not able to join, they can add items onto the agenda with their thoughts before and after the meeting. Core-devs, WDYT? Thanks! Nicolas

7 10

Multi-output regressor and sklearn's RFE module
by Navid Shervani-Tabar July 16, 2019

July 16, 2019

Hello, I have a question regarding sklearn's RFE module. I have a multi-output regressor and I would like to reduce dimensionality of input using RFE. However, it seems that it is not possible to have multi-dimensional output when using RFE. I was wondering if there is a workaround for this or there is something conceptually wrong about it. You can find a minimal working code at the following link. https://stackoverflow.com/questions/57060003/multi-output-regressor-and-skl… Thanks! Navid

1 0

how to preprocess in the cross_validate
by charujing123 July 10, 2019

July 10, 2019

Hi It's easy to preprocess when i used part of data to train and test. However, how to preprocess within the function of sklearn.model_selection.cross_validate? Thanks. Rujing 2019-07-07 charujing123

2 4

Variable kernel density estimation
by Naiping Dong July 8, 2019

July 8, 2019

How sklearn perform cross validation "GridSearchCV" for bandwidth selection? It seems that the CV for kernel density estimation is different with the one used for classification. Is it used least square errors for this aim? Second, is it possible for me to use variable bandwidth for kernel density estimation, that is, use different bandwidth for different data point? Thanks. -- Elkan Department of Chemistry, HKU, HK

2 1

Can I pre-calculate parameter threshold of Birch?
by lampahome July 8, 2019

July 8, 2019

The threshold is determined by the sphere and simulate the points into a sphere. When I tune parameters, I don't know how to set the range of threshold to tune. Can I pre-calculate the threshold?

1 0

New core developer: jeremiedbb
by Olivier Grisel July 5, 2019

July 5, 2019

The core developers of Scikit-learn have recently voted to welcome Jérémie Du Boisberranger to the team, in recognition of his efforts and trustworthiness as contributor. Jérémie's works at Inria Saclay and is supported by the scikit-learn initiative at Fondation Inria and its partners. Congratulations and welcome to the team Jérémie! -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel

2 1

What's the principle of partial_fit?
by lampahome July 2, 2019

July 2, 2019

I work with partial_fit of Birch because the dataset is too huge to load into memory. So I cluster data batch by batch. eg: I have 50000 samples and every batch contain 1000 samples. I found clustering result is better if I cluster data which contain part of last batch better than cluster data which doesn't contain previous data. So I want to know how partail_fit works.

1 0