Mailman 3 May 2020 - scikit-learn

ANN scikit-learn 0.23.0 release
by Adrin May 13, 2020

May 13, 2020

We're happy to announce the 0.23.0 release. You can read the release highlights under https://scikit-learn.org/stable/auto_examples/release_highlights/plot_relea… and the long version of the change log under https://scikit-learn.org/stable/whats_new/v0.23.html#version-0-23-0 On top of a few exciting features, we're also deprecating positional arguments in many places where the constructor/method accepts many arguments. for example, SVC(.5, "poly") will need to be expressed as SVC(C=.5, kernel="poly"), and SVC(C, kernel) as SVC(C=C, kernel=kernel). This version supports Python versions 3.6 to 3.8. You can give it a go using `pip install -U scikit-learn` or alternatively `conda install -c conda-forge scikit-learn` which should be there soon. Regards, Adrin, on behalf of the scikit-learn maintainer team.

4 3

Announcing the 2020 John Hunter Excellence in Plotting Contest
by Nelle Varoquaux May 13, 2020

May 13, 2020

Dear all, I apologize for the cross posting. This is a reminder for the John Hunter Excellence in Plotting Contest. In memory of John Hunter, we are pleased to announce the John Hunter Excellence in Plotting Contest for 2020. This open competition aims to highlight the importance of data visualization to scientific progress and showcase the capabilities of open source software. Participants are invited to submit scientific plots to be judged by a panel. The winning entries will be announced and displayed at SciPy 2020 or announced in the John Hunter Excellence in Plotting Contest website and youtube channel. John Hunter’s family are graciously sponsoring cash prizes for the winners in the following amounts: - 1st prize: $1000 - 2nd prize: $750 - 3rd prize: $500 - Entries must be submitted by June 1st to the form at https://forms.gle/SrexmkDwiAmDc7ej7 - Winners will be announced at Scipy 2020 in Austin, TX or publicly on the John Hunter Excellence in Plotting Contest website and youtube channel - Participants do not need to attend the Scipy conference. - Entries may take the definition of “visualization” rather broadly. Entries may be, for example, a traditional printed plot, an interactive visualization for the web, a dashboard, or an animation. - Source code for the plot must be provided, in the form of Python code and/or a Jupyter notebook, along with a rendering of the plot in a widely used format. The rendering may be, for example, PDF for print, standalone HTML and Javascript for an interactive plot, or MPEG-4 for a video. If the original data can not be shared for reasons of size or licensing, "fake" data may be substituted, along with an image of the plot using real data. - Each entry must include a 300-500 word abstract describing the plot and its importance for a general scientific audience. - Entries will be judged on their clarity, innovation and aesthetics, but most importantly for their effectiveness in communicating a real-world problem. Entrants are encouraged to submit plots that were used during the course of research or work, rather than merely being hypothetical. - SciPy and the John Hunter Excellence in Plotting Contest organizers reserves the right to display any and all entries, whether prize-winning or not, at the conference, use in any materials or on its website, with attribution to the original author(s). - Past entries can be found at https://jhepc.github.io/ - Questions regarding the contest can be sent to jhepc.organizers(a)gmail.com John Hunter Excellence in Plotting Contest Co-Chairs Madicken Munk Nelle Varoquaux

1 0

Why the default max_samples of Random Forest is X.shape[0]?
by Fernando Marcos Wittmann May 11, 2020

May 11, 2020

When reading the documentation of Random Forest, I got the following: ``` max_samples : int or float, default=None If bootstrap is True, the number of samples to draw from X to train each base estimator. - *If None (default), then draw `X.shape[0]` samples.* - If int, then draw `max_samples` samples. - If float, then draw `max_samples * X.shape[0]` samples. Thus, `max_samples` should be in the interval `(0, 1)`. ``` Why does the whole dataset (i.e. X.shape[0] samples from X) is used to build each tree? That would be equivalent to bootstrap to be False, right? Wouldn't it be better practices to use as default 2/3 of the size of the dataset?

2 4

[CFP] The 3rd International workshop on Machine Learning in Clinical Neuroimaging (MLCN 2020)
by MLCN Workshop May 9, 2020

May 9, 2020

*Please find below the call for papers for the International Workshop of Machine Learning in Clinical Neuroimaging (MLCN) on 4 October 2020 at MICCAI 2020 in Lima, Peru. We welcome contributions on novel machine learning methods and their applications to clinical neuroimaging data.* The submission deadline is *30 June 2020*, and all MLCN accepted papers will be eligible for the best paper award of 500 USD. For more information, please visit https://mlcnws.com/. Best wishes, The MLCN 2020 committee Christos Davatzikos Andre Marquand Jonas Richiardi Emma Robinson Ahmed Abdulkadir Cher Bass Mohamad Habes Seyed Mostafa Kia Jane Maryam Rondina Chantal Tax Hongzhi Wang Thomas Wolfers International Workshop on Machine Learning in Clinical Neuroimaging 4 October 2020 in Lima, Peru The International Workshop of Machine Learning in Clinical Neuroimaging ( https://mlcnws.com/), a satellite event of MICCAI (https://miccai2020.org), calls for original papers in the field of clinical neuroimaging data analysis with machine learning. The two tracks of the workshop include methodological innovations as well as clinical applications. This highly interdisciplinary topic provides an excellent platform to connect researchers of varying disciplines and to collectively advance the field in multiple directions. For the machine learning track, we seek contributions with substantial methodological novelty in analyzing high-dimensional, longitudinal, and heterogeneous neuroimaging data using stable, scalable, and interpretable machine learning models. Topics of interest include but are not limited to: - Spatio-temporal brain data analysis - Structural data analysis - Graph theory and complex network analysis - Longitudinal data analysis - Model stability and interpretability - Model scalability in large neuroimaging datasets - Multi-source data integration and multi-view learning - Multi-site data analysis, from preprocessing to modeling - Domain adaptation, data harmonization, and transfer learning in neuroimaging - Unsupervised methods for stratifying brain disorders - Deep learning in clinical neuroimaging - Model uncertainty in clinical predictions - ... In the clinical neuroimaging track, we seek contributions that explore how the application of advanced machine learning methods help us to move towards precision medicine for complex brain disorders. Topics of interest include but are not limited to: - Biomarker discovery - Refinement of nosology and diagnostics - Biological validation of clinical syndromes - Treatment outcome prediction - Course prediction - Analysis of wearable sensors - Neurogenetics and brain imaging genetics - Mechanistic modeling - Brain aging - ... Submission Process: The workshop seeks high quality, original, and unpublished work that addresses one or more challenges described above. Papers should be submitted electronically in Springer Lecture Notes in Computer Science (LCNS) style (see https://www.miccai2020.org/en/PAPER-SUBMISSION-GUIDELINE.html#manuscript-fo… for detailed author guidelines) using the CMT system at https://cmt3.research.microsoft.com/MLCN2020. The page limit is 8-pages (text, figures, and tables) plus up to 2-pages of references. We review the submissions in a double-blind process. Please make sure that your submission is anonymous. Accepted papers will be published in a joint proceeding with the MICCAI 2020 conference. Best Paper Award: This year, all MLCN accepted papers will be eligible for the best paper award. The recipient of the award will be chosen by the MLCN scientific committee based on the scientific quality and novelty of contributions. The winner will be announced at the end of the workshop and will receive 500 USD honorarium. Important Dates: - Paper submission deadline: June 30th, 2020 - Notification of Acceptance: July 24th, 2020 - Camera-ready Submission: July 31st, 2020 - Workshop Date: 4 October 2020

1 0

Why does sklearn require one-hot-encoding for categorical features? Can we have a "factor" data type?
by C W May 6, 2020

May 6, 2020

Hello everyone, I am frustrated with the one-hot-encoding requirement for categorical feature. Why? I've used R and Stata software, none needs such transformation. They have a data type called "factors", which is different from "numeric". My problem with OHE: One-hot-encoding results in large number of features. This really blows up quickly. And I have to fight curse of dimensionality with PCA reduction. That's not cool! Can sklearn have a "factor" data type in the future? It would make life so much easier. Thanks a lot!

7 8

ANN: scikit-learn 0.23 RC1
by Adrin May 6, 2020

May 6, 2020

Thanks to all our 200+ contributors, we are announcing a release candidate for the upcoming release. On top of a few exciting features, we're also deprecating positional arguments in many places where the constructor/method accepts many arguments. for example, SVC(.5, "poly") will need to be expressed as SVC(C=.5, kernel="poly"), and SVC(C, kernel) as SVC(C=C, kernel=kernel). Please give it a try and let us know if there are any issues for us to fix them for the final release. Release highlights: https://scikit-learn.org/0.23/auto_examples/release_highlights/plot_release… Changelog: https://scikit-learn.org/0.23/whats_new/v0.23.html#changes-0-23 Happy testing, Adrin On behalf of the scikit-learn team

1 0

StackingClassifier
by Andrew Howe May 5, 2020

May 5, 2020

Hi All Quick question about the stacking classifier <https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.Stacking…>. How do I know the order of the features that the final estimator uses? I've got an example which I've created like this (the LGRG and KSVM objects were previously defined, but as they seem they would be): passThrough = True finalEstim = DecisionTreeClassifier(random_state=42) stkClas = StackingClassifier(estimators=[('Logistic Regression', LGRG), ('Kernel SVM', KSVM)], cv=crossValInput, passthrough=passThrough, final_estimator=finalEstim, n_jobs=-1) Given this setup, I *think* the features input to the final estimator are - Logistic regression prediction probabilities for all classes - Kernel SVM prediction probabilities for all classes - original features of data passed into the stacking classifier I can find no documentation on this, though, and don't know of any relevant attribute on the final estimator. I need this to help interpret the final estimator tree - and specifically to provide feature labels for plot_tree. Thanks! Andrew <~~~~~~~~~~~~~~~~~~~~~~~~~~~> J. Andrew Howe, PhD LinkedIn Profile <http://www.linkedin.com/in/ahowe42> ResearchGate Profile <http://www.researchgate.net/profile/John_Howe12/> Open Researcher and Contributor ID (ORCID) <http://orcid.org/0000-0002-3553-1990> Github Profile <http://github.com/ahowe42> Personal Website <http://www.andrewhowe.com> I live to learn, so I can learn to live. - me <~~~~~~~~~~~~~~~~~~~~~~~~~~~>

2 3

Vote: Add Adrin Jalali to the scikit-learn technical committee
by Andreas Mueller May 2, 2020

May 2, 2020

Hi All. Given all his recent contributions, I want to nominate Adrin Jalali to the Technical Committee: https://scikit-learn.org/stable/governance.html#technical-committee According to the governance document, this will require a discussion and vote. I think we can move to the vote immediately unless someone objects. Thanks for all your work Adrin! Cheers, Andy

13 14