From jeremie.du-boisberranger at inria.fr Wed Jul 3 05:23:17 2024 From: jeremie.du-boisberranger at inria.fr (=?UTF-8?Q?J=C3=A9r=C3=A9mie_du_Boisberranger?=) Date: Wed, 3 Jul 2024 11:23:17 +0200 Subject: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! Message-ID: Hello everyone, We're happy to announce the 1.5.1 release ! It contains fixes for a few regressions introduced in 1.5. You can see the changelog here: https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 You can upgrade with pip as usual: ``` pip install -U scikit-learn ``` The conda-forge builds can be installed using: ``` conda install -c conda-forge scikit-learn ``` Thanks to everyone who contributed to this release ! J?r?mie, on behalf of the Scikit-learn maintainers team. From g.lemaitre58 at gmail.com Wed Jul 3 05:28:31 2024 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Wed, 3 Jul 2024 11:28:31 +0200 Subject: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! In-Reply-To: References: Message-ID: Thanks J?r?mie for this one. On Wed, 3 Jul 2024 at 11:26, J?r?mie du Boisberranger < jeremie.du-boisberranger at inria.fr> wrote: > Hello everyone, > > We're happy to announce the 1.5.1 release ! > > > It contains fixes for a few regressions introduced in 1.5. > > You can see the changelog here: > https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 > > > You can upgrade with pip as usual: > > ``` > pip install -U scikit-learn > ``` > > The conda-forge builds can be installed using: > > ``` > conda install -c conda-forge scikit-learn > ``` > > > Thanks to everyone who contributed to this release ! > > J?r?mie, on behalf of the Scikit-learn maintainers team. > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre Open source engineer at :probabl. -------------- next part -------------- An HTML attachment was scrubbed... URL: From gael.varoquaux at normalesup.org Wed Jul 3 09:04:48 2024 From: gael.varoquaux at normalesup.org (Gael Varoquaux) Date: Wed, 3 Jul 2024 15:04:48 +0200 Subject: [scikit-learn] Skrub 0.2.0: tabular learning made easy Message-ID: Hi scikit-learn'ers We just released skrub 0.2.0: https://skrub-data.org. This release markedly simplifies learning on complex dataframes. # `model = tabular_learner('classifier')` The highlight of the release is the `tabular_learner` function, which facilitates creating pipelines that readily perform machine learning on dataframes, adding preprocessing to a scikit-learn compatible learner. The function basically packs defaults and heuristics to transform all forms of dataframes to a representation that is well suited to a learner, and it can adapt these transformation: tabular_learner(HistGradientBoostingClassifier()) encodes categories differently than tabular_learner(LogisticRegression()). The heuristics are tuned based on much benchmarking and experience shows that they give good tradeoffs. The default `tabular_learner('classifier')` is often a strong baseline. # `transformer = TableVectorizer()` Behind the hood, the work is done by the `skrub.TableVectorizer()`, a scikit-learn compatible transformer that facilitates combining multiple transformations on the different columns of a dataframe. The TableVectorizer is not new in the 0.2.0 release, but we have completely revamped its internals to cover really well edge cases. Indeed, one challenge is to make sure that nothing different or strange happens at test time. Actually, enforcing consistency between train-time and test-time transformation is the real value of skrub compared to using pandas or polars to do transformation. # Increasing support of polars We have implemented a new mechanism for supporting both pandas and polars. It has not been applied on all the codebase, hence the support is still imperfect. However, we are seeing increasing support for polars in skrub, and our goal in the short term is to provide rock-solid polar support. Try skrub out! It's still young, but in mind opinion, it provides a lot of value to tabular learning. Cheers, Ga?l From gael.varoquaux at normalesup.org Wed Jul 3 08:53:00 2024 From: gael.varoquaux at normalesup.org (Gael Varoquaux) Date: Wed, 3 Jul 2024 14:53:00 +0200 Subject: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! In-Reply-To: References: Message-ID: On Wed, Jul 03, 2024 at 11:28:31AM +0200, Guillaume Lema?tre wrote: > Thanks J?r?mie for this one. +1! Thanks heaps, it's a lot of work, but so much value to the users! Ga?l > On Wed, 3 Jul 2024 at 11:26, J?r?mie du Boisberranger <[1] > jeremie.du-boisberranger at inria.fr> wrote: > Hello everyone, > We're happy to announce the 1.5.1 release ! > It contains fixes for a few regressions introduced in 1.5. > You can see the changelog here: > [2]https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 > You can upgrade with pip as usual: > ``` > pip install -U scikit-learn > ``` > The conda-forge builds can be installed using: > ``` > conda install -c conda-forge scikit-learn > ``` > Thanks to everyone who contributed to this release ! > J?r?mie, on behalf of the Scikit-learn maintainers team. > _______________________________________________ > scikit-learn mailing list > [3]scikit-learn at python.org > [4]https://mail.python.org/mailman/listinfo/scikit-learn -- Gael Varoquaux Research Director, INRIA http://gael-varoquaux.info http://twitter.com/GaelVaroquaux From mukeshmuthiyan at gmail.com Wed Jul 3 13:09:01 2024 From: mukeshmuthiyan at gmail.com (Mukesh Muthiyan) Date: Wed, 3 Jul 2024 22:39:01 +0530 Subject: [scikit-learn] scikit-learn Digest, Vol 98, Issue 1 In-Reply-To: References: Message-ID: U On Wed, Jul 3, 2024, 21:30 wrote: > Send scikit-learn mailing list submissions to > scikit-learn at python.org > > To subscribe or unsubscribe via the World Wide Web, visit > https://mail.python.org/mailman/listinfo/scikit-learn > or, via email, send a message with subject or body 'help' to > scikit-learn-request at python.org > > You can reach the person managing the list at > scikit-learn-owner at python.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of scikit-learn digest..." > > > Today's Topics: > > 1. [ANN] scikit-learn 1.5.1 is online! (J?r?mie du Boisberranger) > 2. Re: [ANN] scikit-learn 1.5.1 is online! (Guillaume Lema?tre) > 3. Skrub 0.2.0: tabular learning made easy (Gael Varoquaux) > 4. Re: [ANN] scikit-learn 1.5.1 is online! (Gael Varoquaux) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Wed, 3 Jul 2024 11:23:17 +0200 > From: J?r?mie du Boisberranger > To: scikit-learn at python.org > Subject: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! > Message-ID: > Content-Type: text/plain; charset=UTF-8; format=flowed > > Hello everyone, > > We're happy to announce the 1.5.1 release ! > > > It contains fixes for a few regressions introduced in 1.5. > > You can see the changelog here: > https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 > > > You can upgrade with pip as usual: > > ``` > pip install -U scikit-learn > ``` > > The conda-forge builds can be installed using: > > ``` > conda install -c conda-forge scikit-learn > ``` > > > Thanks to everyone who contributed to this release ! > > J?r?mie, on behalf of the Scikit-learn maintainers team. > > > > ------------------------------ > > Message: 2 > Date: Wed, 3 Jul 2024 11:28:31 +0200 > From: Guillaume Lema?tre > To: Scikit-learn mailing list > Subject: Re: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! > Message-ID: > xUtTpiw at mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Thanks J?r?mie for this one. > > On Wed, 3 Jul 2024 at 11:26, J?r?mie du Boisberranger < > jeremie.du-boisberranger at inria.fr> wrote: > > > Hello everyone, > > > > We're happy to announce the 1.5.1 release ! > > > > > > It contains fixes for a few regressions introduced in 1.5. > > > > You can see the changelog here: > > https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 > > > > > > You can upgrade with pip as usual: > > > > ``` > > pip install -U scikit-learn > > ``` > > > > The conda-forge builds can be installed using: > > > > ``` > > conda install -c conda-forge scikit-learn > > ``` > > > > > > Thanks to everyone who contributed to this release ! > > > > J?r?mie, on behalf of the Scikit-learn maintainers team. > > > > _______________________________________________ > > scikit-learn mailing list > > scikit-learn at python.org > > https://mail.python.org/mailman/listinfo/scikit-learn > > > > > -- > Guillaume Lemaitre > Open source engineer at :probabl. > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > https://mail.python.org/pipermail/scikit-learn/attachments/20240703/73c35a14/attachment-0001.html > > > > ------------------------------ > > Message: 3 > Date: Wed, 3 Jul 2024 15:04:48 +0200 > From: Gael Varoquaux > To: Scikit-learn user and developer mailing list > > Subject: [scikit-learn] Skrub 0.2.0: tabular learning made easy > Message-ID: > > Content-Type: text/plain; charset=iso-8859-1 > > Hi scikit-learn'ers > > We just released skrub 0.2.0: https://skrub-data.org. This release > markedly simplifies learning on complex dataframes. > > # `model = tabular_learner('classifier')` > > The highlight of the release is the `tabular_learner` function, which > facilitates creating pipelines that readily perform machine learning on > dataframes, adding preprocessing to a scikit-learn compatible learner. The > function basically packs defaults and heuristics to transform all forms of > dataframes to a representation that is well suited to a learner, and it can > adapt these transformation: > tabular_learner(HistGradientBoostingClassifier()) encodes categories > differently than tabular_learner(LogisticRegression()). > > The heuristics are tuned based on much benchmarking and experience shows > that they give good tradeoffs. The default `tabular_learner('classifier')` > is often a strong baseline. > > > # `transformer = TableVectorizer()` > > Behind the hood, the work is done by the `skrub.TableVectorizer()`, a > scikit-learn compatible transformer that facilitates combining multiple > transformations on the different columns of a dataframe. The > TableVectorizer is not new in the 0.2.0 release, but we have completely > revamped its internals to cover really well edge cases. Indeed, one > challenge is to make sure that nothing different or strange happens at test > time. Actually, enforcing consistency between train-time and test-time > transformation is the real value of skrub compared to using pandas or > polars to do transformation. > > # Increasing support of polars > > We have implemented a new mechanism for supporting both pandas and polars. > It has not been applied on all the codebase, hence the support is still > imperfect. However, we are seeing increasing support for polars in skrub, > and our goal in the short term is to provide rock-solid polar support. > > Try skrub out! It's still young, but in mind opinion, it provides a lot of > value to tabular learning. > > Cheers, > > Ga?l > > > ------------------------------ > > Message: 4 > Date: Wed, 3 Jul 2024 14:53:00 +0200 > From: Gael Varoquaux > To: Scikit-learn mailing list > Subject: Re: [scikit-learn] [ANN] scikit-learn 1.5.1 is online! > Message-ID: > > Content-Type: text/plain; charset=iso-8859-1 > > On Wed, Jul 03, 2024 at 11:28:31AM +0200, Guillaume Lema?tre wrote: > > Thanks J?r?mie for this one. > > +1! Thanks heaps, it's a lot of work, but so much value to the users! > > Ga?l > > > On Wed, 3 Jul 2024 at 11:26, J?r?mie du Boisberranger <[1] > > jeremie.du-boisberranger at inria.fr> wrote: > > > Hello everyone, > > > We're happy to announce the 1.5.1 release ! > > > > It contains fixes for a few regressions introduced in 1.5. > > > You can see the changelog here: > > [2]https://scikit-learn.org/stable/whats_new/v1.5.html#version-1-5-1 > > > > You can upgrade with pip as usual: > > > ``` > > pip install -U scikit-learn > > ``` > > > The conda-forge builds can be installed using: > > > ``` > > conda install -c conda-forge scikit-learn > > ``` > > > > Thanks to everyone who contributed to this release ! > > > J?r?mie, on behalf of the Scikit-learn maintainers team. > > > _______________________________________________ > > scikit-learn mailing list > > [3]scikit-learn at python.org > > [4]https://mail.python.org/mailman/listinfo/scikit-learn > -- > Gael Varoquaux > Research Director, INRIA > http://gael-varoquaux.info http://twitter.com/GaelVaroquaux > > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > > > ------------------------------ > > End of scikit-learn Digest, Vol 98, Issue 1 > ******************************************* > -------------- next part -------------- An HTML attachment was scrubbed... URL: From adrin.jalali at gmail.com Tue Jul 9 04:41:43 2024 From: adrin.jalali at gmail.com (Adrin) Date: Tue, 9 Jul 2024 10:41:43 +0200 Subject: [scikit-learn] Welcome Adam Li as a new maintainer Message-ID: Hi, We're delighted to announce that Adam (https://github.com/adam2392) has joined us as a new maintainer. He's been working on several aspects of the project, including the tree code base, and we're very happy to have him on board. Regards, Adrin -------------- next part -------------- An HTML attachment was scrubbed... URL: From gael.varoquaux at normalesup.org Tue Jul 9 09:25:05 2024 From: gael.varoquaux at normalesup.org (Gael Varoquaux) Date: Tue, 9 Jul 2024 15:25:05 +0200 Subject: [scikit-learn] Welcome Adam Li as a new maintainer In-Reply-To: References: Message-ID: Hurray, very happy to have Adam! Adam, thanks heaps for your work. Ga?l On Tue, Jul 09, 2024 at 10:41:43AM +0200, Adrin wrote: > Hi, > We're delighted to announce that Adam ([1]https://github.com/adam2392) has > joined us as a new maintainer. He's been working on several aspects of the > project, including the tree code base, and we're very happy to have him on > board. > Regards, > Adrin > References: > [1] https://github.com/adam2392 > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn -- Gael Varoquaux Research Director, INRIA http://gael-varoquaux.info http://twitter.com/GaelVaroquaux From adam2392 at gmail.com Tue Jul 9 12:07:41 2024 From: adam2392 at gmail.com (Adam Li) Date: Tue, 9 Jul 2024 12:07:41 -0400 Subject: [scikit-learn] scikit-learn Digest, Vol 98, Issue 3 In-Reply-To: References: Message-ID: Hi, Excited to be on board and make scikit-learn and open source even better and more exciting :). On Tue, Jul 9, 2024 at 12:03?PM wrote: > Send scikit-learn mailing list submissions to > scikit-learn at python.org > > To subscribe or unsubscribe via the World Wide Web, visit > https://mail.python.org/mailman/listinfo/scikit-learn > or, via email, send a message with subject or body 'help' to > scikit-learn-request at python.org > > You can reach the person managing the list at > scikit-learn-owner at python.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of scikit-learn digest..." > > > Today's Topics: > > 1. Welcome Adam Li as a new maintainer (Adrin) > 2. Re: Welcome Adam Li as a new maintainer (Gael Varoquaux) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Tue, 9 Jul 2024 10:41:43 +0200 > From: Adrin > To: Scikit-learn mailing list > Subject: [scikit-learn] Welcome Adam Li as a new maintainer > Message-ID: > 7W-f46ByMPM4SoEMJkGm7SDL3fgV5SQ at mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Hi, > > We're delighted to announce that Adam (https://github.com/adam2392) has > joined us as a new maintainer. He's been working on several aspects of the > project, including the tree code base, and we're very happy to have him on > board. > > Regards, > Adrin > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > https://mail.python.org/pipermail/scikit-learn/attachments/20240709/78a9aeba/attachment-0001.html > > > > ------------------------------ > > Message: 2 > Date: Tue, 9 Jul 2024 15:25:05 +0200 > From: Gael Varoquaux > To: Scikit-learn mailing list > Subject: Re: [scikit-learn] Welcome Adam Li as a new maintainer > Message-ID: > > Content-Type: text/plain; charset=iso-8859-1 > > Hurray, very happy to have Adam! > > Adam, thanks heaps for your work. > > Ga?l > > On Tue, Jul 09, 2024 at 10:41:43AM +0200, Adrin wrote: > > Hi, > > > We're delighted to announce that Adam ([1]https://github.com/adam2392) > has > > joined us as a new maintainer. He's been working on several aspects of > the > > project, including the tree code base, and we're very happy to have him > on > > board. > > > Regards, > > Adrin > > > References: > > > [1] https://github.com/adam2392 > > > _______________________________________________ > > scikit-learn mailing list > > scikit-learn at python.org > > https://mail.python.org/mailman/listinfo/scikit-learn > > > -- > Gael Varoquaux > Research Director, INRIA > http://gael-varoquaux.info http://twitter.com/GaelVaroquaux > > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > > > ------------------------------ > > End of scikit-learn Digest, Vol 98, Issue 3 > ******************************************* > -- Best Regards, Adam Li (he/him), PhD in Biomedical Engineering Postdoctoral Researcher at Columbia University Causal AI Lab LinkedIn | Personal Website | ali39 at jhu.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: From reshama.stat at gmail.com Thu Jul 18 13:25:19 2024 From: reshama.stat at gmail.com (Reshama Shaikh) Date: Thu, 18 Jul 2024 13:25:19 -0400 Subject: [scikit-learn] [ANN] New core contributor: Yao Xiao In-Reply-To: <87v86kg4ag.fsf@ymail.com> References: <20240219082852.xrocwsxrdjhngb62@gaellaptop> <87v86kg4ag.fsf@ymail.com> Message-ID: Hello, Check out the Interview with Yao Xiao, scikit-learn Team Member who joined in February 2024: https://blog.scikit-learn.org/team/yao-interview/ Best, Reshama --- Reshama Shaikh On Mon, Feb 19, 2024 at 5:05?AM Lo?c Est?ve via scikit-learn < scikit-learn at python.org> wrote: > Welcome Xiao, great to have you on board! > > Cheers, > Lo?c > > > I'm also super happy to have you around Yao! I've really enjoyed your > work. > > > > Ga?l > > > > On Mon, Feb 19, 2024 at 09:04:10AM +0100, Adrin wrote: > >> Excited to have you on board Yao! Thanks for your contributions. > > > >> On Mon, Feb 19, 2024, 08:37 Guillaume Lema?tre <[1] > g.lemaitre58 at gmail.com> > >> wrote: > > > >> We are excited to welcome Yao Xiao ([2] > https://github.com/Charlie-XIAO) as > >> a core contributor of the scikit-learn project. > > > >> Your past contributions are greatly appreciated, and I'm looking > forward to > >> working further with you. > > > >> On behalf of the scikit-learn team. > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -------------- next part -------------- An HTML attachment was scrubbed... URL: From reshama.stat at gmail.com Tue Jul 30 10:04:28 2024 From: reshama.stat at gmail.com (Reshama Shaikh) Date: Tue, 30 Jul 2024 10:04:28 -0400 Subject: [scikit-learn] Welcome Adam Li as a new maintainer In-Reply-To: References: Message-ID: Hello, Learn more about Adam Li who joined the scikit-learn team in July 2024. Adam is currently a Postdoctoral Research Scientist at Columbia University in the Causal Artificial Intelligence Lab. Learn about his path through open source to scikit-learn as well as his current research: https://blog.scikit-learn.org/team/adam-li-interview/ Best, Reshama --- Reshama Shaikh On Tue, Jul 9, 2024 at 9:27?AM Gael Varoquaux wrote: > Hurray, very happy to have Adam! > > Adam, thanks heaps for your work. > > Ga?l > > On Tue, Jul 09, 2024 at 10:41:43AM +0200, Adrin wrote: > > Hi, > > > We're delighted to announce that Adam ([1]https://github.com/adam2392) > has > > joined us as a new maintainer. He's been working on several aspects of > the > > project, including the tree code base, and we're very happy to have him > on > > board. > > > Regards, > > Adrin > > > References: > > > [1] https://github.com/adam2392 > > > _______________________________________________ > > scikit-learn mailing list > > scikit-learn at python.org > > https://mail.python.org/mailman/listinfo/scikit-learn > > > -- > Gael Varoquaux > Research Director, INRIA > http://gael-varoquaux.info http://twitter.com/GaelVaroquaux > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -------------- next part -------------- An HTML attachment was scrubbed... URL: