From gael.varoquaux at normalesup.org Thu Aug 1 02:34:48 2019 From: gael.varoquaux at normalesup.org (Gael Varoquaux) Date: Thu, 1 Aug 2019 08:34:48 +0200 Subject: [scikit-learn] cross-validated MANOVA In-Reply-To: <21b11453.1152856.16c459eca56.Coremail.charujing123@163.com> References: <21b11453.1152856.16c459eca56.Coremail.charujing123@163.com> Message-ID: <20190801063448.o73qdmlggyzzexef@phare.normalesup.org> You should ask the authors of the paper. Best, Ga?l On Wed, Jul 31, 2019 at 09:22:10AM +0800, charujing123 wrote: > Dear experts and users, > Does anyone know how to perform cross-validated multivariate analysis of > variance? This is the paper mentioned this method "Searchlight-based > multi-voxel pattern analysis of fMRI by cross-validated MANOVA". > Thanks. > Rujing > 2019-07-31 > ??????????????????????????????????????????????????????????????????????????????? > charujing123 > _______________________________________________ > 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 niourf at gmail.com Thu Aug 1 09:33:57 2019 From: niourf at gmail.com (Nicolas Hug) Date: Thu, 1 Aug 2019 09:33:57 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> Message-ID: <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> Hi everyone, Since the meeting is at 9am Monday for NYC, it'd be nice to have all cards up to date by tomorrow, so we can do our homework on Friday (and not on the week end ;) ) Please don't forget to add links to specific PR/issues so others can take a look prior to the meeting. Thanks! Nicolas project board: https://github.com/scikit-learn/scikit-learn/projects/15 Meeting link: https://appear.in/amueller. On 7/26/19 2:08 PM, Nicolas Hug wrote: > > Thanks everyone for your feedback! > > Let's try to have a meeting on Monday 5th August, and then have > meetings on the last Monday of the month? Next meeting would be on > August 26th. > > For the time: > https://www.timeanddate.com/worldclock/meetingdetails.html?year=2019&month=8&day=5&hour=13&min=0&sec=0&p1=240&p2=33&p3=37&p4=179. > This one is convenient for NY and Europe, less so for Sydney / Beijing > . We can have the next meeting accommodate for Joel / Hanmin. > > We can use Andy's appear.in : https://appear.in/amueller. I'm happy to > (try to) "lead" the discussion this first time? > > > For logistics: I created a new project board > https://github.com/scikit-learn/scikit-learn/projects/15 > > I was thinking of having one column per meeting. A few days before the > meeting, people can write down what they plan to discuss (one note per > core-dev), so others can prepare. In particular, people that are not > able to attend can leave details here (let us know in the notes!). > > One advantage of these boards is that they're searchable, we have a > clear history of meetings, and it's easy to reference PRs/issues. This > is of course only a proposal, we can try it and see whether it works > out ;) > > > @Chiara Welcome!! Thanks for offering to help! It didn't take long so > I took care of creating the board (also I would have felt bad for > making you work while you only start in Sep). > > > Thanks, > > Nicolas > > On 7/22/19 9:57 AM, Adrin wrote: >> That's kinda what I meant. I didn't mean to limit the access to the >> project to @core-devs, I meant they can be pinged. >> >> On Mon, Jul 22, 2019 at 3:56 PM Andreas Mueller > > wrote: >> >> >> On 7/22/19 9:22 AM, Adrin wrote: >>> Awesome, excited to have your help around :) >>> >>> We already have the @core-devs team on github, we can use it >>> more often/more organized.hi >> >> Why wouldn't we just use the scikit-learn repo projects? >> >> >>> >>> On Fri, Jul 19, 2019 at 2:48 PM Chiara Marmo >>> > wrote: >>> >>> Dear list, >>> >>> I'm Chiara, in September I will start to work full time for >>> the Scikit-Learn Consortium at INRIA (France). My background >>> is in Astronomy and Planetary Science: I've worked there as >>> a Research Engineer for around 15 years, writing code, >>> mining data and managing some project. >>> >>> One of my task at the Consortium will be to take care of our >>> connection with the developer community, so let me know if I >>> can help in managing those monthly meetings in some way. >>> In the meanwhile, may I suggest to create a github team for >>> core developers in the scikit-learn organization? As >>> Alexandre said, team specific projects and discussions on >>> github could be a way to efficiently prepare meetings and >>> prioritize issues. >>> >>> Thanks for listening, >>> have a nice day. >>> Chiara >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >>> >>> >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> >> >> _______________________________________________ >> 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 malik.yousef at gmail.com Thu Aug 1 16:10:26 2019 From: malik.yousef at gmail.com (Malik Yousef) Date: Thu, 1 Aug 2019 16:10:26 -0400 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' Message-ID: Hello When in using the scoring to be 'f1' then i get an error. Here is the code and the error X=data y=target_column classifier = LinearSVC() rfecv = RFECV(estimator=classifier, step=0.1, cv=StratifiedKFold(5),scoring='f1') rfecv.fit(X, y) The error is : ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], dtype=' From g.lemaitre58 at gmail.com Thu Aug 1 16:56:24 2019 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Thu, 1 Aug 2019 22:56:24 +0200 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: It looks like your data contains string. You need to make some preprocessing before to give it the linear model. On Thu, 1 Aug 2019 at 22:16, Malik Yousef wrote: > Hello > When in using the scoring to be 'f1' then i get an error. > Here is the code and the error > > X=data > y=target_column > classifier = LinearSVC() > rfecv = RFECV(estimator=classifier, step=0.1, > cv=StratifiedKFold(5),scoring='f1') > rfecv.fit(X, y) > > The error is : > ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], > dtype=' > Please your help > (I'm new to using scikit-leanr) > > --------------------------------------------------------------------------------------- > *Prof. Malik Yousef , Associate Professor * > *Zefat Academic College , Department of Information System * > Home Page: > https://malikyousef.com/ > Google Scholar Profile : > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > ---------------------------------------------------------------------------------------------------- > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From malik.yousef at gmail.com Thu Aug 1 17:02:24 2019 From: malik.yousef at gmail.com (Malik Yousef) Date: Thu, 1 Aug 2019 17:02:24 -0400 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: The only string column is the label column(class labels, n.pre, and c.pre). if the scoring = 'accuracy' then it works fine. So I think I need somehow to set up the postive_lable.. that I don't know how to do that. --------------------------------------------------------------------------------------- *Prof. Malik Yousef , Associate Professor * *Zefat Academic College , Department of Information System * Home Page: https://malikyousef.com/ Google Scholar Profile : https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao ---------------------------------------------------------------------------------------------------- On Thu, Aug 1, 2019 at 4:58 PM Guillaume Lema?tre wrote: > It looks like your data contains string. You need to make some > preprocessing before to give it the linear model. > > On Thu, 1 Aug 2019 at 22:16, Malik Yousef wrote: > >> Hello >> When in using the scoring to be 'f1' then i get an error. >> Here is the code and the error >> >> X=data >> y=target_column >> classifier = LinearSVC() >> rfecv = RFECV(estimator=classifier, step=0.1, >> cv=StratifiedKFold(5),scoring='f1') >> rfecv.fit(X, y) >> >> The error is : >> ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], >> dtype='> >> Please your help >> (I'm new to using scikit-leanr) >> >> --------------------------------------------------------------------------------------- >> *Prof. Malik Yousef , Associate Professor * >> *Zefat Academic College , Department of Information System * >> Home Page: >> https://malikyousef.com/ >> Google Scholar Profile : >> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao >> >> ---------------------------------------------------------------------------------------------------- >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > > > -- > Guillaume Lemaitre > INRIA Saclay - Parietal team > Center for Data Science Paris-Saclay > https://glemaitre.github.io/ > _______________________________________________ > 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 g.lemaitre58 at gmail.com Thu Aug 1 17:12:57 2019 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Thu, 1 Aug 2019 23:12:57 +0200 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: you can use the LabelEncoder then. It will encode the classes for you. On Thu, 1 Aug 2019 at 23:04, Malik Yousef wrote: > The only string column is the label column(class labels, n.pre, and > c.pre). if the scoring = 'accuracy' then it works fine. > So I think I need somehow to set up the postive_lable.. that I don't know > how to do that. > > > --------------------------------------------------------------------------------------- > *Prof. Malik Yousef , Associate Professor * > *Zefat Academic College , Department of Information System * > Home Page: > https://malikyousef.com/ > Google Scholar Profile : > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > ---------------------------------------------------------------------------------------------------- > > > On Thu, Aug 1, 2019 at 4:58 PM Guillaume Lema?tre > wrote: > >> It looks like your data contains string. You need to make some >> preprocessing before to give it the linear model. >> >> On Thu, 1 Aug 2019 at 22:16, Malik Yousef wrote: >> >>> Hello >>> When in using the scoring to be 'f1' then i get an error. >>> Here is the code and the error >>> >>> X=data >>> y=target_column >>> classifier = LinearSVC() >>> rfecv = RFECV(estimator=classifier, step=0.1, >>> cv=StratifiedKFold(5),scoring='f1') >>> rfecv.fit(X, y) >>> >>> The error is : >>> ValueError: pos_label=1 is not a valid label: array([u'c.pre', >>> u'n.pre'], dtype='>> >>> Please your help >>> (I'm new to using scikit-leanr) >>> >>> --------------------------------------------------------------------------------------- >>> *Prof. Malik Yousef , Associate Professor * >>> *Zefat Academic College , Department of Information System * >>> Home Page: >>> https://malikyousef.com/ >>> Google Scholar Profile : >>> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao >>> >>> ---------------------------------------------------------------------------------------------------- >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >>> >> >> >> -- >> Guillaume Lemaitre >> INRIA Saclay - Parietal team >> Center for Data Science Paris-Saclay >> https://glemaitre.github.io/ >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From malik.yousef at gmail.com Thu Aug 1 17:16:59 2019 From: malik.yousef at gmail.com (Malik Yousef) Date: Thu, 1 Aug 2019 17:16:59 -0400 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: Can you give me an example? --------------------------------------------------------------------------------------- *Prof. Malik Yousef , Associate Professor * *Zefat Academic College , Department of Information System * Home Page: https://malikyousef.com/ Google Scholar Profile : https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao ---------------------------------------------------------------------------------------------------- On Thu, Aug 1, 2019 at 5:15 PM Guillaume Lema?tre wrote: > you can use the LabelEncoder then. It will encode the classes for you. > > On Thu, 1 Aug 2019 at 23:04, Malik Yousef wrote: > >> The only string column is the label column(class labels, n.pre, and >> c.pre). if the scoring = 'accuracy' then it works fine. >> So I think I need somehow to set up the postive_lable.. that I don't know >> how to do that. >> >> >> --------------------------------------------------------------------------------------- >> *Prof. Malik Yousef , Associate Professor * >> *Zefat Academic College , Department of Information System * >> Home Page: >> https://malikyousef.com/ >> Google Scholar Profile : >> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao >> >> ---------------------------------------------------------------------------------------------------- >> >> >> On Thu, Aug 1, 2019 at 4:58 PM Guillaume Lema?tre >> wrote: >> >>> It looks like your data contains string. You need to make some >>> preprocessing before to give it the linear model. >>> >>> On Thu, 1 Aug 2019 at 22:16, Malik Yousef >>> wrote: >>> >>>> Hello >>>> When in using the scoring to be 'f1' then i get an error. >>>> Here is the code and the error >>>> >>>> X=data >>>> y=target_column >>>> classifier = LinearSVC() >>>> rfecv = RFECV(estimator=classifier, step=0.1, >>>> cv=StratifiedKFold(5),scoring='f1') >>>> rfecv.fit(X, y) >>>> >>>> The error is : >>>> ValueError: pos_label=1 is not a valid label: array([u'c.pre', >>>> u'n.pre'], dtype='>>> >>>> Please your help >>>> (I'm new to using scikit-leanr) >>>> >>>> --------------------------------------------------------------------------------------- >>>> *Prof. Malik Yousef , Associate Professor * >>>> *Zefat Academic College , Department of Information System * >>>> Home Page: >>>> https://malikyousef.com/ >>>> Google Scholar Profile : >>>> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao >>>> >>>> ---------------------------------------------------------------------------------------------------- >>>> _______________________________________________ >>>> scikit-learn mailing list >>>> scikit-learn at python.org >>>> https://mail.python.org/mailman/listinfo/scikit-learn >>>> >>> >>> >>> -- >>> Guillaume Lemaitre >>> INRIA Saclay - Parietal team >>> Center for Data Science Paris-Saclay >>> https://glemaitre.github.io/ >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >>> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > > > -- > Guillaume Lemaitre > INRIA Saclay - Parietal team > Center for Data Science Paris-Saclay > https://glemaitre.github.io/ > _______________________________________________ > 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 g.lemaitre58 at gmail.com Thu Aug 1 17:32:58 2019 From: g.lemaitre58 at gmail.com (=?ISO-8859-1?Q?Guillaume_Lema=EEtre?=) Date: Thu, 01 Aug 2019 23:32:58 +0200 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: Message-ID: <5sb0ujrghf95mcq4c2s9c9nb.1564695178674@gmail.com> An HTML attachment was scrubbed... URL: From joel.nothman at gmail.com Thu Aug 1 20:41:21 2019 From: joel.nothman at gmail.com (Joel Nothman) Date: Fri, 2 Aug 2019 10:41:21 +1000 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: Or use scoring=make_scorer(f1_score, pos_label='n.pre') On Fri, 2 Aug 2019 at 06:15, Malik Yousef wrote: > Hello > When in using the scoring to be 'f1' then i get an error. > Here is the code and the error > > X=data > y=target_column > classifier = LinearSVC() > rfecv = RFECV(estimator=classifier, step=0.1, > cv=StratifiedKFold(5),scoring='f1') > rfecv.fit(X, y) > > The error is : > ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], > dtype=' > Please your help > (I'm new to using scikit-leanr) > > --------------------------------------------------------------------------------------- > *Prof. Malik Yousef , Associate Professor * > *Zefat Academic College , Department of Information System * > Home Page: > https://malikyousef.com/ > Google Scholar Profile : > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > ---------------------------------------------------------------------------------------------------- > _______________________________________________ > 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 joel.nothman at gmail.com Fri Aug 2 01:56:58 2019 From: joel.nothman at gmail.com (Joel Nothman) Date: Fri, 2 Aug 2019 15:56:58 +1000 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> Message-ID: Such meetings could go quite long. (Think those sprint meetings in Paris...) How do we time box discussions, or ensure that the most important/urgent/low-hanging things are covered? Should the objective of the meeting be firstly to prioritise or assign work, and secondarily to discuss issues? To avoid open-ended discussion, we could put topics in an order with time limits. Or we can just see how it goes. I think we also need to make it clear that non-core contributors are welcome to these meetings too! -------------- next part -------------- An HTML attachment was scrubbed... URL: From niourf at gmail.com Fri Aug 2 09:29:22 2019 From: niourf at gmail.com (Nicolas Hug) Date: Fri, 2 Aug 2019 09:29:22 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> Message-ID: <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> I don't think this would be the place for long technical discussions. I was picturing something like "IHere's what I'm working on, here's the current status, and here's what needs to be decided". Then depending on the complexity, things can be briefly discussed, or we can just prioritize and assign work. In any case the moderator is in charge of keeping the meeting < 1h. But yeah, this is a first? for everyone so we'll have to make adjustments! Nicolas On 8/2/19 1:56 AM, Joel Nothman wrote: > > Such meetings could go quite long. (Think those sprint meetings in > Paris...) How do we time box discussions, or ensure that the most > important/urgent/low-hanging things are covered? > > Should the objective of the meeting be firstly to prioritise or assign > work, and secondarily to discuss issues? > > To avoid open-ended discussion, we could put topics in an order with > time limits. > > Or we can just see how it goes. > > I think we also need to make it clear that non-core contributors are > welcome to these meetings too! > > _______________________________________________ > 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 myabakhova at gmail.com Sun Aug 4 15:27:09 2019 From: myabakhova at gmail.com (Maiia Bakhova) Date: Sun, 4 Aug 2019 12:27:09 -0700 Subject: [scikit-learn] scikit-learn Digest, Vol 41, Issue 2 In-Reply-To: References: Message-ID: You probably can use LabelEncoder with OneHotEncoder from sklearn.preprocessing to convert your string data into numerical. Best, Mya On Thu, Aug 1, 2019 at 2:02 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. SVM-RFE with scoring = 'f1' (Malik Yousef) > 2. Re: SVM-RFE with scoring = 'f1' (Guillaume Lema?tre) > 3. Re: SVM-RFE with scoring = 'f1' (Malik Yousef) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Thu, 1 Aug 2019 16:10:26 -0400 > From: Malik Yousef > To: scikit-learn at python.org > Subject: [scikit-learn] SVM-RFE with scoring = 'f1' > Message-ID: > LvS+C7X_Zw at mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Hello > When in using the scoring to be 'f1' then i get an error. > Here is the code and the error > > X=data > y=target_column > classifier = LinearSVC() > rfecv = RFECV(estimator=classifier, step=0.1, > cv=StratifiedKFold(5),scoring='f1') > rfecv.fit(X, y) > > The error is : > ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], > dtype=' > Please your help > (I'm new to using scikit-leanr) > > --------------------------------------------------------------------------------------- > *Prof. Malik Yousef , Associate Professor * > *Zefat Academic College , Department of Information System * > Home Page: > https://malikyousef.com/ > Google Scholar Profile : > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > ---------------------------------------------------------------------------------------------------- > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://mail.python.org/pipermail/scikit-learn/attachments/20190801/20fbb5fc/attachment-0001.html > > > > ------------------------------ > > Message: 2 > Date: Thu, 1 Aug 2019 22:56:24 +0200 > From: Guillaume Lema?tre > To: Scikit-learn mailing list > Subject: Re: [scikit-learn] SVM-RFE with scoring = 'f1' > Message-ID: > < > CACDxx9iN3qvuaJtXbAJPem4gZFviLVqTeoLU203gRz0_UA2Y_g at mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > It looks like your data contains string. You need to make some > preprocessing before to give it the linear model. > > On Thu, 1 Aug 2019 at 22:16, Malik Yousef wrote: > > > Hello > > When in using the scoring to be 'f1' then i get an error. > > Here is the code and the error > > > > X=data > > y=target_column > > classifier = LinearSVC() > > rfecv = RFECV(estimator=classifier, step=0.1, > > cv=StratifiedKFold(5),scoring='f1') > > rfecv.fit(X, y) > > > > The error is : > > ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], > > dtype=' > > > Please your help > > (I'm new to using scikit-leanr) > > > > > --------------------------------------------------------------------------------------- > > *Prof. Malik Yousef , Associate Professor * > > *Zefat Academic College , Department of Information System * > > Home Page: > > https://malikyousef.com/ > > Google Scholar Profile : > > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > > > > ---------------------------------------------------------------------------------------------------- > > _______________________________________________ > > scikit-learn mailing list > > scikit-learn at python.org > > https://mail.python.org/mailman/listinfo/scikit-learn > > > > > -- > Guillaume Lemaitre > INRIA Saclay - Parietal team > Center for Data Science Paris-Saclay > https://glemaitre.github.io/ > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://mail.python.org/pipermail/scikit-learn/attachments/20190801/5ed63ff1/attachment-0001.html > > > > ------------------------------ > > Message: 3 > Date: Thu, 1 Aug 2019 17:02:24 -0400 > From: Malik Yousef > To: Scikit-learn mailing list > Subject: Re: [scikit-learn] SVM-RFE with scoring = 'f1' > Message-ID: > vyFBR0v0QuGr9g9NuzOrXGV1BFiOihAH6Dt4SvYwtQ at mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > The only string column is the label column(class labels, n.pre, and c.pre). > if the scoring = 'accuracy' then it works fine. > So I think I need somehow to set up the postive_lable.. that I don't know > how to do that. > > > --------------------------------------------------------------------------------------- > *Prof. Malik Yousef , Associate Professor * > *Zefat Academic College , Department of Information System * > Home Page: > https://malikyousef.com/ > Google Scholar Profile : > https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > > ---------------------------------------------------------------------------------------------------- > > > On Thu, Aug 1, 2019 at 4:58 PM Guillaume Lema?tre > wrote: > > > It looks like your data contains string. You need to make some > > preprocessing before to give it the linear model. > > > > On Thu, 1 Aug 2019 at 22:16, Malik Yousef > wrote: > > > >> Hello > >> When in using the scoring to be 'f1' then i get an error. > >> Here is the code and the error > >> > >> X=data > >> y=target_column > >> classifier = LinearSVC() > >> rfecv = RFECV(estimator=classifier, step=0.1, > >> cv=StratifiedKFold(5),scoring='f1') > >> rfecv.fit(X, y) > >> > >> The error is : > >> ValueError: pos_label=1 is not a valid label: array([u'c.pre', > u'n.pre'], > >> dtype=' >> > >> Please your help > >> (I'm new to using scikit-leanr) > >> > >> > --------------------------------------------------------------------------------------- > >> *Prof. Malik Yousef , Associate Professor * > >> *Zefat Academic College , Department of Information System * > >> Home Page: > >> https://malikyousef.com/ > >> Google Scholar Profile : > >> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao > >> > >> > ---------------------------------------------------------------------------------------------------- > >> _______________________________________________ > >> scikit-learn mailing list > >> scikit-learn at python.org > >> https://mail.python.org/mailman/listinfo/scikit-learn > >> > > > > > > -- > > Guillaume Lemaitre > > INRIA Saclay - Parietal team > > Center for Data Science Paris-Saclay > > https://glemaitre.github.io/ > > _______________________________________________ > > 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: < > http://mail.python.org/pipermail/scikit-learn/attachments/20190801/650411b8/attachment.html > > > > ------------------------------ > > 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 41, Issue 2 > ******************************************* > -- Maiia Bakhova Mathematician in Data Science https://www.linkedin.com/in/myabakhova -------------- next part -------------- An HTML attachment was scrubbed... URL: From joel.nothman at gmail.com Mon Aug 5 10:21:29 2019 From: joel.nothman at gmail.com (Joel Nothman) Date: Tue, 6 Aug 2019 00:21:29 +1000 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> Message-ID: Yay for technology! Awesome to see you all and have some matters clarified. Adrin is right that the issue tracker is increasingly overwhelming (because there are more awesome people hired to work on the project, more frequent sprints, etc). This meeting is a useful summary. The meeting mostly focussed on big features. We should be careful to not leave behind important bugs fixes and work originating outside the core devs. Despite that: Some of Guillaume's activities got cut off. I think it would be great to progress both on stacking and resampling before the next release. I also think these meetings should, as a standing item, note the estimated upcoming release schedule, to help us remain aware of that cadence. Good night! J -------------- next part -------------- An HTML attachment was scrubbed... URL: From t3kcit at gmail.com Mon Aug 5 10:31:38 2019 From: t3kcit at gmail.com (Andreas Mueller) Date: Mon, 5 Aug 2019 10:31:38 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> Message-ID: As usual, I agree ;) I think it would be good to call out particularly important bugfixes so they get reviews. We might also want to think about how we can organize the issue tracker better. Having more full-time people on the project certainly means more activity but ideally we can use some of that time to make the issue tracker more organized. On 8/5/19 9:21 AM, Joel Nothman wrote: > Yay for technology!?Awesome to see you all and have some matters > clarified. > > Adrin is right that the issue tracker is increasingly overwhelming > (because there are more awesome people hired to work on the project, > more frequent sprints, etc). This meeting is a useful summary. > > The meeting mostly focussed on big features. We should be careful to > not leave behind important bugs fixes and work originating outside the > core devs. > > Despite that: Some of Guillaume's activities got cut off. I think it > would be great to progress both on stacking and resampling before the > next release. > > I also think these meetings should, as a standing item, note the > estimated upcoming release schedule, to help us remain aware of that > cadence. > > Good night! > > J > > _______________________________________________ > 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 charujing123 at 163.com Mon Aug 5 10:39:49 2019 From: charujing123 at 163.com (Rujing Zha) Date: Mon, 5 Aug 2019 22:39:49 +0800 (CST) Subject: [scikit-learn] Predictive probability from cross_validate In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> Message-ID: <7cd05f4c.28a.16c6238dea0.Coremail.charujing123@163.com> Hi How to acquire the probability in the cross_validate function? Thanks Rujing -- ????????????? ? 2019-08-05 22:31:38?"Andreas Mueller" ??? As usual, I agree ;) I think it would be good to call out particularly important bugfixes so they get reviews. We might also want to think about how we can organize the issue tracker better. Having more full-time people on the project certainly means more activity but ideally we can use some of that time to make the issue tracker more organized. On 8/5/19 9:21 AM, Joel Nothman wrote: Yay for technology! Awesome to see you all and have some matters clarified. Adrin is right that the issue tracker is increasingly overwhelming (because there are more awesome people hired to work on the project, more frequent sprints, etc). This meeting is a useful summary. The meeting mostly focussed on big features. We should be careful to not leave behind important bugs fixes and work originating outside the core devs. Despite that: Some of Guillaume's activities got cut off. I think it would be great to progress both on stacking and resampling before the next release. I also think these meetings should, as a standing item, note the estimated upcoming release schedule, to help us remain aware of that cadence. Good night! J _______________________________________________ scikit-learn mailing list scikit-learn at python.orghttps://mail.python.org/mailman/listinfo/scikit-learn -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: ATT00003.txt URL: From niourf at gmail.com Mon Aug 5 11:15:34 2019 From: niourf at gmail.com (Nicolas Hug) Date: Mon, 5 Aug 2019 11:15:34 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> Message-ID: <87b9909b-e635-3284-2254-1e47f086dd9d@gmail.com> Thanks everyone for joining, There's definitely room from improvement but this was still very productive I think :) The meeting notes are on the project board. I sent a google calendar invite to everyone for the next meeting: Monday 26th August, same time. If I missed you or if? you want me to use another address, let me know. Anybody interested in moderating the next one? Nicolas On 8/5/19 10:31 AM, Andreas Mueller wrote: > As usual, I agree ;) > I think it would be good to call out particularly important bugfixes > so they get reviews. > We might also want to think about how we can organize the issue > tracker better. > > Having more full-time people on the project certainly means more > activity but ideally we can use some of that time to make the issue > tracker more organized. > > > On 8/5/19 9:21 AM, Joel Nothman wrote: >> Yay for technology!?Awesome to see you all and have some matters >> clarified. >> >> Adrin is right that the issue tracker is increasingly overwhelming >> (because there are more awesome people hired to work on the project, >> more frequent sprints, etc). This meeting is a useful summary. >> >> The meeting mostly focussed on big features. We should be careful to >> not leave behind important bugs fixes and work originating outside >> the core devs. >> >> Despite that: Some of Guillaume's activities got cut off. I think it >> would be great to progress both on stacking and resampling before the >> next release. >> >> I also think these meetings should, as a standing item, note the >> estimated upcoming release schedule, to help us remain aware of that >> cadence. >> >> Good night! >> >> J >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn > > > _______________________________________________ > 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 seralouk at hotmail.com Mon Aug 5 13:57:01 2019 From: seralouk at hotmail.com (serafim loukas) Date: Mon, 5 Aug 2019 17:57:01 +0000 Subject: [scikit-learn] Question about Kmeans implementation in sklearn In-Reply-To: References: Message-ID: <61D601AD-9FF9-44F6-A9BE-408CF521723F@hotmail.com> Dear Sklearn community, I have a simple question concerning the implementation of KMeans clustering algorithm. Two of the input arguments are the ?n_init? and ?random_state?. Consider a case where ?n_init=10? and ?random_state=0?. By looking at the source code (https://github.com/scikit-learn/scikit-learn/blob/1495f69242646d239d89a5713982946b8ffcf9d9/sklearn/cluster/k_means_.py#L187), we have the following: for it in range(n_init): # run a k-means once labels, inertia, centers, n_iter_ = kmeans_single( X, sample_weight, n_clusters, max_iter=max_iter, init=init, verbose=verbose, precompute_distances=precompute_distances, tol=tol, x_squared_norms=x_squared_norms, random_state=random_state) My question is: Why the results are not going to be the same for all `n_init` iterations since `random_state` is fixed? Bests, Makis -------------- next part -------------- An HTML attachment was scrubbed... URL: From chris at aridas.eu Mon Aug 5 14:40:15 2019 From: chris at aridas.eu (Chris Aridas) Date: Mon, 5 Aug 2019 21:40:15 +0300 Subject: [scikit-learn] Question about Kmeans implementation in sklearn In-Reply-To: <61D601AD-9FF9-44F6-A9BE-408CF521723F@hotmail.com> References: <61D601AD-9FF9-44F6-A9BE-408CF521723F@hotmail.com> Message-ID: Hey Serafim, In this line https://github.com/scikit-learn/scikit-learn/blob/1495f69242646d239d89a5713982946b8ffcf9d9/sklearn/cluster/k_means_.py#L303 you can see that a randomstate object is constructed and that object is passed in the for loop that you are referring to, not the integer value that was passed in the function. Cheers, Chris On Mon, 5 Aug 2019 20:58 serafim loukas, wrote: > Dear Sklearn community, > > > I have a simple question concerning the implementation of KMeans > clustering algorithm. > Two of the input arguments are the ?n_init? and ?random_state?. > > Consider a case where *?n_init=10? and ?random_state=0?.* > > By looking at the source code ( > https://github.com/scikit-learn/scikit-learn/blob/1495f69242646d239d89a5713982946b8ffcf9d9/sklearn/cluster/k_means_.py#L187), > we have the following: > > for it in range(n_init): > # run a k-means once > labels, inertia, centers, n_iter_ = kmeans_single( > X, sample_weight, n_clusters, max_iter=max_iter, init=init, > verbose=verbose, precompute_distances=precompute_distances, > tol=tol, x_squared_norms=x_squared_norms, > random_state=random_state) > > > My question is: Why the results are not going to be the same for all > `n_init` iterations since `random_state` is fixed? > > > Bests, > Makis > _______________________________________________ > 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 rs2715 at stern.nyu.edu Tue Aug 6 17:20:42 2019 From: rs2715 at stern.nyu.edu (Reshama Shaikh) Date: Tue, 6 Aug 2019 17:20:42 -0400 Subject: [scikit-learn] Fwd: [Nairobi, Kenya WiMLDS] OS sprint (June 2019): Impact Report In-Reply-To: References: Message-ID: Hello, On March 12, 2019, I had posted to this mailing list looking for a contributor for our Nairobi, WiMLDS sprint: https://mail.python.org/pipermail/scikit-learn/2019-March/003048.html Happy to share the sprint happened (on June 22, 2019) and I just published the Impact Report: https://reshamas.github.io/nairobi-wimlds-2019-scikit-learn-sprint-impact-report/ Thanks to all contributors who assisted. Best, Reshama ---------------------------------------------- Reshama Shaikh NYC WiMLDS NYC PyLadies ---------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From joel.nothman at gmail.com Sun Aug 11 17:23:05 2019 From: joel.nothman at gmail.com (Joel Nothman) Date: Mon, 12 Aug 2019 07:23:05 +1000 Subject: [scikit-learn] Fwd: [Nairobi, Kenya WiMLDS] OS sprint (June 2019): Impact Report In-Reply-To: References: Message-ID: Awesome work and great write-up, Reshama. Thanks Andy and Adrin especially, for bringing us along in your commitment to such causes. -------------- next part -------------- An HTML attachment was scrubbed... URL: From g.lemaitre58 at gmail.com Mon Aug 12 11:16:25 2019 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Mon, 12 Aug 2019 17:16:25 +0200 Subject: [scikit-learn] Predictive probability from cross_validate In-Reply-To: <7cd05f4c.28a.16c6238dea0.Coremail.charujing123@163.com> References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> <7cd05f4c.28a.16c6238dea0.Coremail.charujing123@163.com> Message-ID: cross_validate should not be used to make predictions but to evaluate the performance, the parameter, etc of models. You probably want to check cross_val_predict to get the prediction. However, be aware of what it involves: https://scikit-learn.org/stable/modules/cross_validation.html#obtaining-predictions-by-cross-validation On Mon, 5 Aug 2019 at 16:57, Rujing Zha wrote: > > Hi > How to acquire the probability in the cross_validate function? > Thanks > Rujing > > > > -- > ????????????? > > > > ? 2019-08-05 22:31:38?"Andreas Mueller" ??? > > As usual, I agree ;) > I think it would be good to call out particularly important bugfixes so > they get reviews. > We might also want to think about how we can organize the issue tracker > better. > > Having more full-time people on the project certainly means more activity > but ideally we can use some of that time to make the issue tracker more > organized. > > > On 8/5/19 9:21 AM, Joel Nothman wrote: > > Yay for technology! Awesome to see you all and have some matters > clarified. > > Adrin is right that the issue tracker is increasingly overwhelming > (because there are more awesome people hired to work on the project, more > frequent sprints, etc). This meeting is a useful summary. > > The meeting mostly focussed on big features. We should be careful to not > leave behind important bugs fixes and work originating outside the core > devs. > > Despite that: Some of Guillaume's activities got cut off. I think it would > be great to progress both on stacking and resampling before the next > release. > > I also think these meetings should, as a standing item, note the estimated > upcoming release schedule, to help us remain aware of that cadence. > > Good night! > > J > > _______________________________________________ > scikit-learn mailing listscikit-learn at python.orghttps://mail.python.org/mailman/listinfo/scikit-learn > > > > > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From charujing123 at 163.com Mon Aug 12 22:13:02 2019 From: charujing123 at 163.com (charujing123) Date: Tue, 13 Aug 2019 10:13:02 +0800 Subject: [scikit-learn] Predictive probability from cross_validate In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> <7cd05f4c.28a.16c6238dea0.Coremail.charujing123@163.com> Message-ID: hi this function is exactly what i wanted. However, the description of this function contained this: Passing these predictions into an evaluation metric may not be a valid way to measure generalization performance. Could i use this prediction to calculate the accuracy? I am not sure after seeing this sentence. Thanks. 2019-08-13 charujing123 ????Guillaume Lema?tre ?????2019-08-12 23:16 ???Re: [scikit-learn] Predictive probability from cross_validate ????"Scikit-learn mailing list" ??? cross_validate should not be used to make predictions but to evaluate the performance, the parameter, etc of models. You probably want to check cross_val_predict to get the prediction. However, be aware of what it involves: https://scikit-learn.org/stable/modules/cross_validation.html#obtaining-predictions-by-cross-validation On Mon, 5 Aug 2019 at 16:57, Rujing Zha wrote: Hi How to acquire the probability in the cross_validate function? Thanks Rujing -- ????????????? ? 2019-08-05 22:31:38?"Andreas Mueller" ??? As usual, I agree ;) I think it would be good to call out particularly important bugfixes so they get reviews. We might also want to think about how we can organize the issue tracker better. Having more full-time people on the project certainly means more activity but ideally we can use some of that time to make the issue tracker more organized. On 8/5/19 9:21 AM, Joel Nothman wrote: Yay for technology! Awesome to see you all and have some matters clarified. Adrin is right that the issue tracker is increasingly overwhelming (because there are more awesome people hired to work on the project, more frequent sprints, etc). This meeting is a useful summary. The meeting mostly focussed on big features. We should be careful to not leave behind important bugs fixes and work originating outside the core devs. Despite that: Some of Guillaume's activities got cut off. I think it would be great to progress both on stacking and resampling before the next release. I also think these meetings should, as a standing item, note the estimated upcoming release schedule, to help us remain aware of that cadence. Good night! J _______________________________________________ scikit-learn mailing list scikit-learn at python.org https://mail.python.org/mailman/listinfo/scikit-learn _______________________________________________ scikit-learn mailing list scikit-learn at python.org https://mail.python.org/mailman/listinfo/scikit-learn -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From imguna2003 at gmail.com Tue Aug 13 02:59:11 2019 From: imguna2003 at gmail.com (Gunasekar K) Date: Tue, 13 Aug 2019 12:29:11 +0530 Subject: [scikit-learn] Along with Predictive probability and class name how to get the multi-text(text) belonging to that class Message-ID: Hi Team, Greetings!!! Assuming ''Humpty Dumpty" is text trained under given specific model belonging to class called "cartoon character" in multi-text classification model. *model.predict_proba([Invoice_parameter])*100* gives the probability of belongings to specific class. But how come I can retrieve the *text* for that probability hit for that class. for example, Invoice_parameter= input() ---- on the fly input "Humpty Dumpty sat on the wall" *model.predict_proba([Invoice_parameter])*100* I get probability of 99.09 (rounded to two decimal places) to character class but i also need to retrieve the text Humpty Dumpty. Any help or suggestions are appreciated. Thanks in advance. Kind regards, GK -------------- next part -------------- An HTML attachment was scrubbed... URL: From g.lemaitre58 at gmail.com Tue Aug 13 03:47:31 2019 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Tue, 13 Aug 2019 09:47:31 +0200 Subject: [scikit-learn] Predictive probability from cross_validate In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> <7cd05f4c.28a.16c6238dea0.Coremail.charujing123@163.com> Message-ID: As the note is saying, you should not use this approach to evaluate your model. You should use cross_val_score instead. On Tue, 13 Aug 2019 at 04:30, charujing123 wrote: > hi > this function is exactly what i wanted. However, the description of this > function contained this: Passing these predictions into an evaluation > metric may not be a valid way to measure generalization performance. > Could i use this prediction to calculate the accuracy? I am not sure after > seeing this sentence. > Thanks. > > 2019-08-13 > ------------------------------ > charujing123 > ------------------------------ > > *????*Guillaume Lema?tre > *?????*2019-08-12 23:16 > *???*Re: [scikit-learn] Predictive probability from cross_validate > *????*"Scikit-learn mailing list" > *???* > > cross_validate should not be used to make predictions but to evaluate the > performance, the parameter, etc of models. > You probably want to check cross_val_predict to get the prediction. > However, be aware of what it involves: > > https://scikit-learn.org/stable/modules/cross_validation.html#obtaining-predictions-by-cross-validation > > On Mon, 5 Aug 2019 at 16:57, Rujing Zha wrote: > >> >> Hi >> How to acquire the probability in the cross_validate function? >> Thanks >> Rujing >> >> >> >> -- >> ????????????? >> >> >> >> ? 2019-08-05 22:31:38?"Andreas Mueller" ??? >> >> As usual, I agree ;) >> I think it would be good to call out particularly important bugfixes so >> they get reviews. >> We might also want to think about how we can organize the issue tracker >> better. >> >> Having more full-time people on the project certainly means more activity >> but ideally we can use some of that time to make the issue tracker more >> organized. >> >> >> On 8/5/19 9:21 AM, Joel Nothman wrote: >> >> Yay for technology! Awesome to see you all and have some matters >> clarified. >> >> Adrin is right that the issue tracker is increasingly overwhelming >> (because there are more awesome people hired to work on the project, more >> frequent sprints, etc). This meeting is a useful summary. >> >> The meeting mostly focussed on big features. We should be careful to not >> leave behind important bugs fixes and work originating outside the core >> devs. >> >> Despite that: Some of Guillaume's activities got cut off. I think it >> would be great to progress both on stacking and resampling before the next >> release. >> >> I also think these meetings should, as a standing item, note the >> estimated upcoming release schedule, to help us remain aware of that >> cadence. >> >> Good night! >> >> J >> >> _______________________________________________ >> scikit-learn mailing listscikit-learn at python.orghttps://mail.python.org/mailman/listinfo/scikit-learn >> >> >> >> >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > > > -- > Guillaume Lemaitre > INRIA Saclay - Parietal team > Center for Data Science Paris-Saclay > https://glemaitre.github.io/ > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From g.lemaitre58 at gmail.com Tue Aug 13 03:50:43 2019 From: g.lemaitre58 at gmail.com (=?UTF-8?Q?Guillaume_Lema=C3=AEtre?=) Date: Tue, 13 Aug 2019 09:50:43 +0200 Subject: [scikit-learn] Along with Predictive probability and class name how to get the multi-text(text) belonging to that class In-Reply-To: References: Message-ID: I am unsure if it what you need but you can take the argmax (or call predict) and get the value of model.classes_. In short, model.classes_[model.predict([invoice_parameter])]. On Tue, 13 Aug 2019 at 09:01, Gunasekar K wrote: > Hi Team, > > Greetings!!! > > Assuming ''Humpty Dumpty" is text trained under given specific model > belonging to class called "cartoon character" in multi-text classification > model. > > *model.predict_proba([Invoice_parameter])*100* gives the probability of > belongings to specific class. > > But how come I can retrieve the *text* for that probability hit for that > class. > > for example, > > Invoice_parameter= input() ---- on the fly input > > "Humpty Dumpty sat on the wall" > > *model.predict_proba([Invoice_parameter])*100* > > I get probability of 99.09 (rounded to two decimal places) to character > class but i also need to retrieve the text Humpty Dumpty. > > Any help or suggestions are appreciated. > > Thanks in advance. > > Kind regards, > GK > > > > > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn > -- Guillaume Lemaitre INRIA Saclay - Parietal team Center for Data Science Paris-Saclay https://glemaitre.github.io/ -------------- next part -------------- An HTML attachment was scrubbed... URL: From imguna2003 at gmail.com Tue Aug 13 05:01:15 2019 From: imguna2003 at gmail.com (Gunasekar K) Date: Tue, 13 Aug 2019 14:31:15 +0530 Subject: [scikit-learn] Along with Predictive probability and class name how to get the multi-text(text) belonging to that class In-Reply-To: References: Message-ID: Thank you for your e-mail. I am not looking for class prediction, as I am using similar concept to recognize them. Exactly I am looking for the text which points to the class as identified by the model. "Humpty Dumpty sat on the wall" when above statement fed to the pre-trained/saved model it returns the class output as "Character". Also I want the text part which trained for that respective class. Assuming "Humpty Dumpty" is trained under "Character" class. Thank you, Best regards On Tue, 13 Aug 2019 at 13:21, Guillaume Lema?tre wrote: > I am unsure if it what you need but you can take the argmax (or call > predict) and get the value of model.classes_. > In short, model.classes_[model.predict([invoice_parameter])]. > > On Tue, 13 Aug 2019 at 09:01, Gunasekar K wrote: > >> Hi Team, >> >> Greetings!!! >> >> Assuming ''Humpty Dumpty" is text trained under given specific model >> belonging to class called "cartoon character" in multi-text classification >> model. >> >> *model.predict_proba([Invoice_parameter])*100* gives the probability of >> belongings to specific class. >> >> But how come I can retrieve the *text* for that probability hit for that >> class. >> >> for example, >> >> Invoice_parameter= input() ---- on the fly input >> >> "Humpty Dumpty sat on the wall" >> >> *model.predict_proba([Invoice_parameter])*100* >> >> I get probability of 99.09 (rounded to two decimal places) to character >> class but i also need to retrieve the text Humpty Dumpty. >> >> Any help or suggestions are appreciated. >> >> Thanks in advance. >> >> Kind regards, >> GK >> >> >> >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > > > -- > Guillaume Lemaitre > INRIA Saclay - Parietal team > Center for Data Science Paris-Saclay > https://glemaitre.github.io/ > _______________________________________________ > 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 rs2715 at stern.nyu.edu Tue Aug 13 09:40:29 2019 From: rs2715 at stern.nyu.edu (Reshama Shaikh) Date: Tue, 13 Aug 2019 09:40:29 -0400 Subject: [scikit-learn] Fwd: [Nairobi, Kenya WiMLDS] OS sprint (June 2019): Impact Report In-Reply-To: References: Message-ID: Hello, (I can't quite figure out how to respond to a thread on the mailing list, maybe because I receive a digest version.) Hi Joel, WiMLDS has 72 chapters worldwide... including... Australia: 1. Sydney (355 members) https://www.meetup.com/Sydney-Women-in-Machine-Learning-and-Data-Science/ 2. Melbourne (964 members) https://www.meetup.com/Melbourne-Women-in-Machine-Learning-and-Data-Science/ One day, we could have a scikit-learn sprint in Australia. :) ---------------------------------------------- Reshama Shaikh NYC WiMLDS NYC PyLadies ---------------------------------------------- ---------- Forwarded message --------- From: Reshama Shaikh Date: Tue, Aug 6, 2019 at 5:20 PM Subject: Fwd: [Nairobi, Kenya WiMLDS] OS sprint (June 2019): Impact Report To: Hello, On March 12, 2019, I had posted to this mailing list looking for a contributor for our Nairobi, WiMLDS sprint: https://mail.python.org/pipermail/scikit-learn/2019-March/003048.html Happy to share the sprint happened (on June 22, 2019) and I just published the Impact Report: https://reshamas.github.io/nairobi-wimlds-2019-scikit-learn-sprint-impact-report/ Thanks to all contributors who assisted. Best, Reshama ---------------------------------------------- Reshama Shaikh NYC WiMLDS NYC PyLadies ---------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From pahome.chen at mirlab.org Fri Aug 16 03:45:42 2019 From: pahome.chen at mirlab.org (lampahome) Date: Fri, 16 Aug 2019 15:45:42 +0800 Subject: [scikit-learn] Any recommend way to encode IP address? Message-ID: I collect data which has many access log from different IP. But I don't know what's the better way to encode it to make sure small size of train data and keep the independency of different IPs. 1. one-hot encode: If too many IP, the train data will occupy huge disk spaces. 2. category encode: IP will be encoded to 0~N, but can't show the relation between different IPs. anyone have advices? -------------- next part -------------- An HTML attachment was scrubbed... URL: From chris at aridas.eu Fri Aug 16 03:54:27 2019 From: chris at aridas.eu (Chris Aridas) Date: Fri, 16 Aug 2019 10:54:27 +0300 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: Hey, Apart from encoding you could use feature engineering. Something like this https://ipgeolocation.io/documentation/ip-geolocation-api.html Two IPs might have the same country but different city. So, you could mix and match whatever you want. Best, On Fri, Aug 16, 2019 at 10:46 AM lampahome wrote: > I collect data which has many access log from different IP. > > But I don't know what's the better way to encode it to make sure small > size of train data and keep the independency of different IPs. > > 1. one-hot encode: If too many IP, the train data will occupy huge disk > spaces. > 2. category encode: IP will be encoded to 0~N, but can't show the relation > between different IPs. > > anyone have advices? > _______________________________________________ > 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 santoshmsubedi at gmail.com Fri Aug 16 04:13:35 2019 From: santoshmsubedi at gmail.com (Santosh Subedi) Date: Fri, 16 Aug 2019 17:13:35 +0900 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: Hi guys, How can I unsubscribe myself from Scikit-learn mailing list? Thanks. On Fri, 16 Aug 2019 at 4:56 PM Chris Aridas wrote: > Hey, > > Apart from encoding you could use feature engineering. Something like this > https://ipgeolocation.io/documentation/ip-geolocation-api.html > Two IPs might have the same country but different city. So, you could mix > and match whatever you want. > > Best, > > On Fri, Aug 16, 2019 at 10:46 AM lampahome wrote: > >> I collect data which has many access log from different IP. >> >> But I don't know what's the better way to encode it to make sure small >> size of train data and keep the independency of different IPs. >> >> 1. one-hot encode: If too many IP, the train data will occupy huge disk >> spaces. >> 2. category encode: IP will be encoded to 0~N, but can't show the >> relation between different IPs. >> >> anyone have advices? >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > _______________________________________________ > 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 chris at aridas.eu Fri Aug 16 04:16:54 2019 From: chris at aridas.eu (Chris Aridas) Date: Fri, 16 Aug 2019 11:16:54 +0300 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: https://mail.python.org/mailman/listinfo/scikit-learn On Fri, Aug 16, 2019 at 11:14 AM Santosh Subedi wrote: > Hi guys, > > How can I unsubscribe myself from Scikit-learn mailing list? > > Thanks. > > On Fri, 16 Aug 2019 at 4:56 PM Chris Aridas wrote: > >> Hey, >> >> Apart from encoding you could use feature engineering. Something like >> this https://ipgeolocation.io/documentation/ip-geolocation-api.html >> Two IPs might have the same country but different city. So, you could mix >> and match whatever you want. >> >> Best, >> >> On Fri, Aug 16, 2019 at 10:46 AM lampahome >> wrote: >> >>> I collect data which has many access log from different IP. >>> >>> But I don't know what's the better way to encode it to make sure small >>> size of train data and keep the independency of different IPs. >>> >>> 1. one-hot encode: If too many IP, the train data will occupy huge disk >>> spaces. >>> 2. category encode: IP will be encoded to 0~N, but can't show the >>> relation between different IPs. >>> >>> anyone have advices? >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >>> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > _______________________________________________ > 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 pahome.chen at mirlab.org Fri Aug 16 04:53:56 2019 From: pahome.chen at mirlab.org (lampahome) Date: Fri, 16 Aug 2019 16:53:56 +0800 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: Chris Aridas ? 2019?8?16? ?? ??3:56??? > Hey, > > Apart from encoding you could use feature engineering. Something like this > https://ipgeolocation.io/documentation/ip-geolocation-api.html > Two IPs might have the same country but different city. So, you could mix > and match whatever you want. > > It seems to register to get API to use. Is it all free? -------------- next part -------------- An HTML attachment was scrubbed... URL: From chris at aridas.eu Fri Aug 16 05:23:55 2019 From: chris at aridas.eu (Chris Aridas) Date: Fri, 16 Aug 2019 12:23:55 +0300 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: It was just an idea about how you can extract features from IP addresses, not a direction to use that service. Best, Chris On Fri, Aug 16, 2019 at 11:55 AM lampahome wrote: > > > Chris Aridas ? 2019?8?16? ?? ??3:56??? > >> Hey, >> >> Apart from encoding you could use feature engineering. Something like >> this https://ipgeolocation.io/documentation/ip-geolocation-api.html >> Two IPs might have the same country but different city. So, you could mix >> and match whatever you want. >> >> > It seems to register to get API to use. > > Is it all free? > > _______________________________________________ > 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 florian.kromer at mailbox.org Sat Aug 17 05:53:41 2019 From: florian.kromer at mailbox.org (florian.kromer at mailbox.org) Date: Sat, 17 Aug 2019 11:53:41 +0200 (CEST) Subject: [scikit-learn] Awesome List Announcement In-Reply-To: <844652562.33042.1566029340949@office.mailbox.org> References: <844652562.33042.1566029340949@office.mailbox.org> Message-ID: <978431582.33405.1566035621127@office.mailbox.org> Just want to let everyone know that there is https://github.com/fkromer/awesome-scikit-learn now which summarizes resources about scikit-learn in an "awesome list" kind of way. Cheers, Florian From marmochiaskl at gmail.com Sun Aug 18 09:43:05 2019 From: marmochiaskl at gmail.com (Chiara Marmo) Date: Sun, 18 Aug 2019 15:43:05 +0200 Subject: [scikit-learn] scikit-learn website and documentation Message-ID: Dear list, dear devs, I have started to look at the scikit-learn documentation: talking with developers in July here in Paris, it seemed that you all are concerned by a reorganization / relooking of the doc and nothing is better than a na?ve beginner to check the effectiveness of a doc ... right? ;) ... and diving into the docs allows me to better familiarize with the project... :) As CSS and HTML5 are a bit more fun than reStructuredText I've started to play with styling together with the sphinx contents ... contents ask for more focusing ... I will be more serious on that starting from September ... >From the styling point of view, I am a big fan of this one [1] that you probably already know and I tried to apply those amazing styles to sphinx documentation. Then I saw the Andreas tweet [2] ... and decided to stop by to sum up. I've prepared a mock-up for the webpage available here [3]. It's a standard build of the doc with the editorial [4] styling (basic customization needs improvements). The code is available here [5]. I've tried not to move too far from the original visual ... because history is important, especially when you have one! :) I've focused on the homepage so don't expect big modifications in the doc itself. This is just a proof of concept. If you think I'm on the right track let me know... I will be happy to be useful on that. If not, or you already have someone taking care of that, please let me know too and I will find something else to do. Thanks for reading me. Best, Chiara [1] https://html5up.net/ [2] https://twitter.com/amuellerml/status/1161298913841885184 [3] https://cmarmo.github.io/mockup-skl/ [4] https://html5up.net/editorial [5] https://github.com/cmarmo/scikit-learn -------------- next part -------------- An HTML attachment was scrubbed... URL: From pahome.chen at mirlab.org Tue Aug 20 04:09:39 2019 From: pahome.chen at mirlab.org (lampahome) Date: Tue, 20 Aug 2019 16:09:39 +0800 Subject: [scikit-learn] Any recommend way to encode IP address? In-Reply-To: References: Message-ID: Chris Aridas ? 2019?8?16? ?? ??5:26??? > It was just an idea about how you can extract features from IP addresses, > not a direction to use that service. > > If I just encode the ip address, is there any efficient way? What I found reliable is arithmetic encoding and convert ip string to integer directly. -------------- next part -------------- An HTML attachment was scrubbed... URL: From niourf at gmail.com Thu Aug 22 10:11:19 2019 From: niourf at gmail.com (Nicolas Hug) Date: Thu, 22 Aug 2019 10:11:19 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> Message-ID: <92ce29e5-4a54-9545-1d51-79bda3713c25@gmail.com> Hi Everyone, Quick reminder that the next meeting is on Monday! *Please update your cards on the project board* so we can all have a look before the week-end. We decided to go for a "scrum-like" approach this time: quickly go through everyone's notes first, then discuss main issues. Anyone interested in hosting? I think we should have a new person each time, or you'll soon be fed up with me. If nobody speaks up I'll np.random.choice someone on Monday ;) ---- Time and date: https://www.timeanddate.com/worldclock/meetingdetails.html?year=2019&month=8&day=26&hour=13&min=0&sec=0&p1=240&p2=33&p3=37&p4=179 Project board: https://github.com/scikit-learn/scikit-learn/projects/15 Meeting link: https://appear.in/amueller See you on Monday! Nicolas On 8/5/19 10:31 AM, Andreas Mueller wrote: > As usual, I agree ;) > I think it would be good to call out particularly important bugfixes > so they get reviews. > We might also want to think about how we can organize the issue > tracker better. > > Having more full-time people on the project certainly means more > activity but ideally we can use some of that time to make the issue > tracker more organized. > > > On 8/5/19 9:21 AM, Joel Nothman wrote: >> Yay for technology!?Awesome to see you all and have some matters >> clarified. >> >> Adrin is right that the issue tracker is increasingly overwhelming >> (because there are more awesome people hired to work on the project, >> more frequent sprints, etc). This meeting is a useful summary. >> >> The meeting mostly focussed on big features. We should be careful to >> not leave behind important bugs fixes and work originating outside >> the core devs. >> >> Despite that: Some of Guillaume's activities got cut off. I think it >> would be great to progress both on stacking and resampling before the >> next release. >> >> I also think these meetings should, as a standing item, note the >> estimated upcoming release schedule, to help us remain aware of that >> cadence. >> >> Good night! >> >> J >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn > > > _______________________________________________ > 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 niourf at gmail.com Thu Aug 22 16:16:33 2019 From: niourf at gmail.com (Nicolas Hug) Date: Thu, 22 Aug 2019 16:16:33 -0400 Subject: [scikit-learn] scikit-learn website and documentation In-Reply-To: References: Message-ID: <66ce5be1-ec7d-6819-c8ad-cee8f3914930@gmail.com> Hi Chiara, Thanks for giving it a shot! I think we can end-up with a nice result with this theme too. Is this something you'd like to work on more seriously in the future, or just something to get you started on scikit-learn in general? (Basically, should Andy still be looking for a web-designer?) Nicolas On 8/18/19 9:43 AM, Chiara Marmo wrote: > Dear list, dear devs, > > I have started to look at the scikit-learn documentation: talking with > developers in July here in Paris, it seemed that you all are concerned > by a reorganization / relooking of the doc and nothing is better than > a na?ve beginner to check the effectiveness of a doc ... right? ;) > ... and diving into the docs allows me to better familiarize with the > project... :) > > As CSS and HTML5 are a bit more fun than reStructuredText I've started > to play with styling together with the sphinx contents ... contents > ask for more focusing ... I will be more serious on that starting from > September ... > > From the styling point of view, I am a big fan of this one [1] that > you probably already know and I tried to apply those amazing styles to > sphinx documentation. > // > Then I saw the Andreas tweet [2] ... and decided to stop by to sum up. > > I've prepared a mock-up for the webpage available here [3]. > It's a standard build of the doc with the editorial [4] styling (basic > customization needs improvements). The code is available here [5]. > I've tried not to move too far from the original visual ... because > history is important, especially when you have one! :) > > I've focused on the homepage so don't expect big modifications in the > doc itself. This is just a proof of concept. If you think I'm on the > right track let me know... I will be happy to be useful on that. > If not, or you already have someone taking care of that, please let me > know too and I will find something else to do. > > Thanks for reading me. > > Best, > > Chiara > > [1] https://html5up.net/ > [2] https://twitter.com/amuellerml/status/1161298913841885184 > [3] https://cmarmo.github.io/mockup-skl/ > [4] https://html5up.net/editorial > [5] https://github.com/cmarmo/scikit-learn > > _______________________________________________ > 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 gael.varoquaux at normalesup.org Thu Aug 22 20:15:50 2019 From: gael.varoquaux at normalesup.org (Gael Varoquaux) Date: Thu, 22 Aug 2019 20:15:50 -0400 Subject: [scikit-learn] scikit-learn website and documentation In-Reply-To: <66ce5be1-ec7d-6819-c8ad-cee8f3914930@gmail.com> References: <66ce5be1-ec7d-6819-c8ad-cee8f3914930@gmail.com> Message-ID: <36f3c879-913f-4686-8714-e03a482ce710@normalesup.org> Hi everyone, One thing to keep in mind with regards to technical solution is that it is much easier if they play well with sphinx. In other words, fully fledged frameworks tend to be harder to slot in. One tool that I really like is pure css, (https://purecss.io/), because it is very lightweight? (it's only css, a the name suggests). Ga?l ?Sent from my phone. Please forgive typos and briefness.? On Aug 22, 2019, 16:21, at 16:21, Nicolas Hug wrote: >Hi Chiara, > >Thanks for giving it a shot! I think we can end-up with a nice result >with this theme too. > >Is this something you'd like to work on more seriously in the future, >or >just something to get you started on scikit-learn in general? >(Basically, should Andy still be looking for a web-designer?) > > >Nicolas > >On 8/18/19 9:43 AM, Chiara Marmo wrote: >> Dear list, dear devs, >> >> I have started to look at the scikit-learn documentation: talking >with >> developers in July here in Paris, it seemed that you all are >concerned >> by a reorganization / relooking of the doc and nothing is better than > >> a na?ve beginner to check the effectiveness of a doc ... right? ;) >> ... and diving into the docs allows me to better familiarize with the > >> project... :) >> >> As CSS and HTML5 are a bit more fun than reStructuredText I've >started >> to play with styling together with the sphinx contents ... contents >> ask for more focusing ... I will be more serious on that starting >from >> September ... >> >> From the styling point of view, I am a big fan of this one [1] that >> you probably already know and I tried to apply those amazing styles >to >> sphinx documentation. >> // >> Then I saw the Andreas tweet [2] ... and decided to stop by to sum >up. >> >> I've prepared a mock-up for the webpage available here [3]. >> It's a standard build of the doc with the editorial [4] styling >(basic >> customization needs improvements). The code is available here [5]. >> I've tried not to move too far from the original visual ... because >> history is important, especially when you have one! :) >> >> I've focused on the homepage so don't expect big modifications in the > >> doc itself. This is just a proof of concept. If you think I'm on the >> right track let me know... I will be happy to be useful on that. >> If not, or you already have someone taking care of that, please let >me >> know too and I will find something else to do. >> >> Thanks for reading me. >> >> Best, >> >> Chiara >> >> [1] https://html5up.net/ >> [2] https://twitter.com/amuellerml/status/1161298913841885184 >> [3] https://cmarmo.github.io/mockup-skl/ >> [4] https://html5up.net/editorial >> [5] https://github.com/cmarmo/scikit-learn >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn > > >------------------------------------------------------------------------ > >_______________________________________________ >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 malik.yousef at gmail.com Fri Aug 23 20:25:55 2019 From: malik.yousef at gmail.com (Malik Yousef) Date: Fri, 23 Aug 2019 20:25:55 -0400 Subject: [scikit-learn] SVM-RFE with scoring = 'f1' In-Reply-To: References: Message-ID: Thanks for your reply. How I can set the name of the positive class in LinearSVC() for a two-class problem that when using the prediction then I will get positive scores fro that positive class? Malik --------------------------------------------------------------------------------------- *Prof. Malik Yousef , Associate Professor * *Zefat Academic College , Department of Information System * Home Page: https://malikyousef.com/ Google Scholar Profile : https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao ---------------------------------------------------------------------------------------------------- On Thu, Aug 1, 2019 at 8:43 PM Joel Nothman wrote: > Or use scoring=make_scorer(f1_score, pos_label='n.pre') > > On Fri, 2 Aug 2019 at 06:15, Malik Yousef wrote: > >> Hello >> When in using the scoring to be 'f1' then i get an error. >> Here is the code and the error >> >> X=data >> y=target_column >> classifier = LinearSVC() >> rfecv = RFECV(estimator=classifier, step=0.1, >> cv=StratifiedKFold(5),scoring='f1') >> rfecv.fit(X, y) >> >> The error is : >> ValueError: pos_label=1 is not a valid label: array([u'c.pre', u'n.pre'], >> dtype='> >> Please your help >> (I'm new to using scikit-leanr) >> >> --------------------------------------------------------------------------------------- >> *Prof. Malik Yousef , Associate Professor * >> *Zefat Academic College , Department of Information System * >> Home Page: >> https://malikyousef.com/ >> Google Scholar Profile : >> https://scholar.google.com/citations?user=9UCZ_q4AAAAJ&hl=en&oi=ao >> >> ---------------------------------------------------------------------------------------------------- >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> > _______________________________________________ > 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 marmochiaskl at gmail.com Sat Aug 24 07:53:38 2019 From: marmochiaskl at gmail.com (Chiara Marmo) Date: Sat, 24 Aug 2019 13:53:38 +0200 Subject: [scikit-learn] scikit-learn website and documentation In-Reply-To: <36f3c879-913f-4686-8714-e03a482ce710@normalesup.org> References: <66ce5be1-ec7d-6819-c8ad-cee8f3914930@gmail.com> <36f3c879-913f-4686-8714-e03a482ce710@normalesup.org> Message-ID: Hi Nicolas, Working on visual and contents of the the docs is in my skills and I'm happy to finish the job. But I'm not a web designer and I don't like to impose myself... :) Maybe you can check at the Monday meeting if everybody is ok with that and write down comments in the minutes? For the next meeting I will be available for collecting specifications, if any. Ga?l, I will check purecss.io: how much customization the basic theme needs has to be considered too. CiaoCiao Chiara On Friday, August 23, 2019, Gael Varoquaux wrote: > Hi everyone, > > One thing to keep in mind with regards to technical solution is that it is much easier if they play well with sphinx. In other words, fully fledged frameworks tend to be harder to slot in. > > One tool that I really like is pure css, (https://purecss.io/), because it is very lightweight (it's only css, a the name suggests). > > Ga?l > > Sent from my phone. Please forgive typos and briefness. > On Aug 22, 2019, at 16:21, Nicolas Hug wrote: >> >> Hi Chiara, >> >> Thanks for giving it a shot! I think we can end-up with a nice result with this theme too. >> >> Is this something you'd like to work on more seriously in the future, or just something to get you started on scikit-learn in general? (Basically, should Andy still be looking for a web-designer?) >> >> Nicolas >> >> On 8/18/19 9:43 AM, Chiara Marmo wrote: >> >> Dear list, dear devs, >> I have started to look at the scikit-learn documentation: talking with developers in July here in Paris, it seemed that you all are concerned by a reorganization / relooking of the doc and nothing is better than a na?ve beginner to check the effectiveness of a doc ... right? ;) >> ... and diving into the docs allows me to better familiarize with the project... :) >> >> As CSS and HTML5 are a bit more fun than reStructuredText I've started to play with styling together with the sphinx contents ... contents ask for more focusing ... I will be more serious on that starting from September ... >> >> From the styling point of view, I am a big fan of this one [1] that you probably already know and I tried to apply those amazing styles to sphinx documentation. >> Then I saw the Andreas tweet [2] ... and decided to stop by to sum up. >> >> I've prepared a mock-up for the webpage available here [3]. >> It's a standard build of the doc with the editorial [4] styling (basic customization needs improvements). The code is available here [5]. >> I've tried not to move too far from the original visual ... because history is important, especially when you have one! :) >> >> I've focused on the homepage so don't expect big modifications in the doc itself. This is just a proof of concept. If you think I'm on the right track let me know... I will be happy to be useful on that. >> If not, or you already have someone taking care of that, please let me know too and I will find something else to do. >> >> Thanks for reading me. >> Best, >> Chiara >> >> [1] https://html5up.net/ >> [2] https://twitter.com/amuellerml/status/1161298913841885184 >> [3] https://cmarmo.github.io/mockup-skl/ >> [4] https://html5up.net/editorial >> [5] https://github.com/cmarmo/scikit-learn >> >> _______________________________________________ >> scikit-learn mailing list >> scikit-learn at python.org >> https://mail.python.org/mailman/listinfo/scikit-learn >> >> ________________________________ >> 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 niourf at gmail.com Mon Aug 26 08:54:21 2019 From: niourf at gmail.com (Nicolas Hug) Date: Mon, 26 Aug 2019 08:54:21 -0400 Subject: [scikit-learn] Monthly meetings between core developers + "Hello World" In-Reply-To: <92ce29e5-4a54-9545-1d51-79bda3713c25@gmail.com> References: <20190718100451.B608918C0090@webmail.sinamail.sina.com.cn> <08716118-a3a8-0131-aeca-f97a8aba3f25@gmail.com> <60f8ad16-3e13-765a-4c4a-6a80f7a4d998@gmail.com> <1e489f79-ebb5-b394-c99c-ed71bce1e607@gmail.com> <92ce29e5-4a54-9545-1d51-79bda3713c25@gmail.com> Message-ID: <136faf1a-5514-1c21-7514-0673b4ddde81@gmail.com> Meeting is in 5 minutes everyone! Prepare to be np.random.choice'd? :) https://appear.in/amueller On 8/22/19 10:11 AM, Nicolas Hug wrote: > > Hi Everyone, > > Quick reminder that the next meeting is on Monday! *Please update your > cards on the project board* so we can all have a look before the week-end. > > We decided to go for a "scrum-like" approach this time: quickly go > through everyone's notes first, then discuss main issues. > > Anyone interested in hosting? I think we should have a new person each > time, or you'll soon be fed up with me. If nobody speaks up I'll > np.random.choice someone on Monday ;) > > ---- > > Time and date: > https://www.timeanddate.com/worldclock/meetingdetails.html?year=2019&month=8&day=26&hour=13&min=0&sec=0&p1=240&p2=33&p3=37&p4=179 > > Project board: > https://github.com/scikit-learn/scikit-learn/projects/15 > > > Meeting link: https://appear.in/amueller > > > > See you on Monday! > > Nicolas > > > On 8/5/19 10:31 AM, Andreas Mueller wrote: >> As usual, I agree ;) >> I think it would be good to call out particularly important bugfixes >> so they get reviews. >> We might also want to think about how we can organize the issue >> tracker better. >> >> Having more full-time people on the project certainly means more >> activity but ideally we can use some of that time to make the issue >> tracker more organized. >> >> >> On 8/5/19 9:21 AM, Joel Nothman wrote: >>> Yay for technology!?Awesome to see you all and have some matters >>> clarified. >>> >>> Adrin is right that the issue tracker is increasingly overwhelming >>> (because there are more awesome people hired to work on the project, >>> more frequent sprints, etc). This meeting is a useful summary. >>> >>> The meeting mostly focussed on big features. We should be careful to >>> not leave behind important bugs fixes and work originating outside >>> the core devs. >>> >>> Despite that: Some of Guillaume's activities got cut off. I think it >>> would be great to progress both on stacking and resampling before >>> the next release. >>> >>> I also think these meetings should, as a standing item, note the >>> estimated upcoming release schedule, to help us remain aware of that >>> cadence. >>> >>> Good night! >>> >>> J >>> >>> _______________________________________________ >>> scikit-learn mailing list >>> scikit-learn at python.org >>> https://mail.python.org/mailman/listinfo/scikit-learn >> >> >> _______________________________________________ >> 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 surya.dheeshjith at gmail.com Mon Aug 26 12:07:30 2019 From: surya.dheeshjith at gmail.com (Surya D) Date: Mon, 26 Aug 2019 21:37:30 +0530 Subject: [scikit-learn] Forest Decision path Message-ID: Hello! I am Surya, a student of the machine learning world. I am currently working on a project to obtain the values of nodes that are parents of the leaf nodes in the decision path of each tree. I have seen stack overflow and have tried out the solutions but for my project, it is not fast enough. Is there any other way I can access the ?values? in these parent nodes? Regards Surya Dheeshjith -------------- next part -------------- An HTML attachment was scrubbed... URL: From javaeurusd at gmail.com Mon Aug 26 13:09:44 2019 From: javaeurusd at gmail.com (Mike Smith) Date: Mon, 26 Aug 2019 10:09:44 -0700 Subject: [scikit-learn] scikit-learn Digest, Vol 41, Issue 21 In-Reply-To: References: Message-ID: Hi, I have been scouring around everywhere to volunteer. I took a one month python course from a training company that promised me a job in two months but they're still working on it after 3. So I decide to volunteer. I'm looking to use python with DS, ML, AI, etc, I love neural nets, then it hit me that I get the scikit mailing list and opened it up and you guys are talking about volunteers. I would love to volunteer for scikit. But I just have one month training in python. I have prior experience with java and javascript, some computer science education, How can I start volunteering? On Mon, Aug 26, 2019 at 9:03 AM 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. Re: Monthly meetings between core developers + "Hello World" > (Nicolas Hug) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Mon, 26 Aug 2019 08:54:21 -0400 > From: Nicolas Hug > To: scikit-learn at python.org > Subject: Re: [scikit-learn] Monthly meetings between core developers + > "Hello World" > Message-ID: <136faf1a-5514-1c21-7514-0673b4ddde81 at gmail.com> > Content-Type: text/plain; charset="utf-8"; Format="flowed" > > Meeting is in 5 minutes everyone! Prepare to be np.random.choice'd? :) > > https://appear.in/amueller > < > https://www.google.com/url?q=https://appear.in/amueller&sa=D&ust=1566914386036000&usg=AOvVaw2rS1k5NlK35I-_dSoJLgt2 > > > > > On 8/22/19 10:11 AM, Nicolas Hug wrote: > > > > Hi Everyone, > > > > Quick reminder that the next meeting is on Monday! *Please update your > > cards on the project board* so we can all have a look before the > week-end. > > > > We decided to go for a "scrum-like" approach this time: quickly go > > through everyone's notes first, then discuss main issues. > > > > Anyone interested in hosting? I think we should have a new person each > > time, or you'll soon be fed up with me. If nobody speaks up I'll > > np.random.choice someone on Monday ;) > > > > ---- > > > > Time and date: > > > https://www.timeanddate.com/worldclock/meetingdetails.html?year=2019&month=8&day=26&hour=13&min=0&sec=0&p1=240&p2=33&p3=37&p4=179 > > > > Project board: > > https://github.com/scikit-learn/scikit-learn/projects/15 > > < > https://www.google.com/url?q=https://github.com/scikit-learn/scikit-learn/projects/15&sa=D&ust=1566914386036000&usg=AOvVaw15duAHoylKYpdBsYgogoOQ > > > > > > Meeting link: https://appear.in/amueller > > < > https://www.google.com/url?q=https://appear.in/amueller&sa=D&ust=1566914386036000&usg=AOvVaw2rS1k5NlK35I-_dSoJLgt2 > > > > > > > > See you on Monday! > > > > Nicolas > > > > > > On 8/5/19 10:31 AM, Andreas Mueller wrote: > >> As usual, I agree ;) > >> I think it would be good to call out particularly important bugfixes > >> so they get reviews. > >> We might also want to think about how we can organize the issue > >> tracker better. > >> > >> Having more full-time people on the project certainly means more > >> activity but ideally we can use some of that time to make the issue > >> tracker more organized. > >> > >> > >> On 8/5/19 9:21 AM, Joel Nothman wrote: > >>> Yay for technology!?Awesome to see you all and have some matters > >>> clarified. > >>> > >>> Adrin is right that the issue tracker is increasingly overwhelming > >>> (because there are more awesome people hired to work on the project, > >>> more frequent sprints, etc). This meeting is a useful summary. > >>> > >>> The meeting mostly focussed on big features. We should be careful to > >>> not leave behind important bugs fixes and work originating outside > >>> the core devs. > >>> > >>> Despite that: Some of Guillaume's activities got cut off. I think it > >>> would be great to progress both on stacking and resampling before > >>> the next release. > >>> > >>> I also think these meetings should, as a standing item, note the > >>> estimated upcoming release schedule, to help us remain aware of that > >>> cadence. > >>> > >>> Good night! > >>> > >>> J > >>> > >>> _______________________________________________ > >>> scikit-learn mailing list > >>> scikit-learn at python.org > >>> https://mail.python.org/mailman/listinfo/scikit-learn > >> > >> > >> _______________________________________________ > >> 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: < > http://mail.python.org/pipermail/scikit-learn/attachments/20190826/dd8e23fb/attachment-0001.html > > > > ------------------------------ > > 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 41, Issue 21 > ******************************************** > -------------- next part -------------- An HTML attachment was scrubbed... URL: From adrin.jalali at gmail.com Tue Aug 27 04:28:56 2019 From: adrin.jalali at gmail.com (Adrin) Date: Tue, 27 Aug 2019 10:28:56 +0200 Subject: [scikit-learn] Forest Decision path In-Reply-To: References: Message-ID: Hi, Not sure what you've done and what exactly you need, but for a "fast" solution, you probably need to dig into `sklearn/tree/_tree.pyx`. Adrin/ On Mon, Aug 26, 2019 at 6:08 PM Surya D wrote: > Hello! I am Surya, a student of the machine learning world. I am currently > working on a project to obtain the values of nodes that are parents of the > leaf nodes in the decision path of each tree. I have seen stack overflow > and have tried out the solutions but for my project, it is not fast enough. > Is there any other way I can access the ?values? in these parent nodes? > > > Regards > Surya Dheeshjith > _______________________________________________ > 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 gryllosprokopis at gmail.com Wed Aug 28 06:16:14 2019 From: gryllosprokopis at gmail.com (Prokopis Gryllos) Date: Wed, 28 Aug 2019 12:16:14 +0200 Subject: [scikit-learn] Interest in decision thresholding and fairness ? pr [10117] Message-ID: Dear sklearn folks, Some time ago (almost two years now :D) I started working on this pr https://github.com/scikit-learn/scikit-learn/pull/10117 ; The starting point was an issue created by Andreas Mueller https://github.com/scikit-learn/scikit-learn/issues/8614. Andreas and Joel Nothman helped with reviewing all iterations up to a few months ago but for the most part the pr has been stalled. I'd like to ask the community if there is still interest for this to move forward? I think in today's state of ML decision thresholding is important; Day to day data science work frequently requires thinking about thresholds and many times people settle for intuitive solutions or thresholds that are not tested for generalisation. Furthermore using more advanced ways for choosing thresholds is not trivial. The increased interest in fairness in ML also points to the idea that thresholding is important. I am not sure if this is the best place to ask but I wasn't sure how else I could find out if people are interested in reviewing the work. I'd like to put some effort into finalising the feature and potentially adapt it to the current state of the art. Would something like that http://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning.pdf be of interest? Looking forward to your responses Gr, Prokopis -------------- next part -------------- An HTML attachment was scrubbed... URL: From benoit.presles at u-bourgogne.fr Fri Aug 30 10:52:30 2019 From: benoit.presles at u-bourgogne.fr (=?UTF-8?Q?Beno=c3=aet_Presles?=) Date: Fri, 30 Aug 2019 16:52:30 +0200 Subject: [scikit-learn] No convergence warning in logistic regression Message-ID: <58775d9b-bf80-c0f4-f696-b1470cb37745@u-bourgogne.fr> Dear all, I compared the logistic regression of statsmodels (Logit) with the logistic regression of sklearn (LogisticRegression). As I do not do regularization, I use the fit method with statsmodels and set penalty='none' in sklearn. Most of the time, I have got the same results between the two packages. However, when data are correlated, it is not the case. In fact, I have got a very useful convergence warning with statsmodel (ConvergenceWarning: Maximum Likelihood optimization failed to converge) that I do not have with sklearn? Is it normal that I do not have any convergence warning with sklearn even if I put verbose=1? I guess sklearn did not converge either. Thanks for your help, Best regards, Ben From marmochiaskl at gmail.com Fri Aug 30 12:58:12 2019 From: marmochiaskl at gmail.com (Chiara Marmo) Date: Fri, 30 Aug 2019 18:58:12 +0200 Subject: [scikit-learn] scikit-learn website and documentation In-Reply-To: References: <66ce5be1-ec7d-6819-c8ad-cee8f3914930@gmail.com> <36f3c879-913f-4686-8714-e03a482ce710@normalesup.org> Message-ID: Hello, Should I consider this PR [1] as an answer? ;) Cheers, Chiara [1] https://github.com/scikit-learn/scikit-learn/pull/14849 On Sat, Aug 24, 2019 at 1:53 PM Chiara Marmo wrote: > Hi Nicolas, > > Working on visual and contents of the the docs is in my skills and I'm > happy to finish the job. > But I'm not a web designer and I don't like to impose myself... :) > > Maybe you can check at the Monday meeting if everybody is ok with that and > write down comments in the minutes? For the next meeting I will be > available for collecting specifications, if any. > > Ga?l, I will check purecss.io: how much customization the basic theme > needs has to be considered too. > > CiaoCiao > > Chiara > -------------- next part -------------- An HTML attachment was scrubbed... URL: From mail at sebastianraschka.com Fri Aug 30 12:29:34 2019 From: mail at sebastianraschka.com (Sebastian Raschka) Date: Fri, 30 Aug 2019 11:29:34 -0500 Subject: [scikit-learn] No convergence warning in logistic regression In-Reply-To: <58775d9b-bf80-c0f4-f696-b1470cb37745@u-bourgogne.fr> References: <58775d9b-bf80-c0f4-f696-b1470cb37745@u-bourgogne.fr> Message-ID: Hi Ben, I can recall seeing convergence warnings for scikit-learn's logistic regression model on datasets in the past as well. Which solver did you use for LogisticRegression in sklearn? If you haven't done so, have used the lbfgs solver? I.e., LogisticRegression(..., solver='lbfgs')? Best, Sebastian > On Aug 30, 2019, at 9:52 AM, Beno?t Presles wrote: > > Dear all, > > I compared the logistic regression of statsmodels (Logit) with the logistic regression of sklearn (LogisticRegression). As I do not do regularization, I use the fit method with statsmodels and set penalty='none' in sklearn. Most of the time, I have got the same results between the two packages. > > However, when data are correlated, it is not the case. In fact, I have got a very useful convergence warning with statsmodel (ConvergenceWarning: Maximum Likelihood optimization failed to converge) that I do not have with sklearn? Is it normal that I do not have any convergence warning with sklearn even if I put verbose=1? I guess sklearn did not converge either. > > > Thanks for your help, > Best regards, > Ben > _______________________________________________ > scikit-learn mailing list > scikit-learn at python.org > https://mail.python.org/mailman/listinfo/scikit-learn From garyfallidis at gmail.com Fri Aug 16 16:46:44 2019 From: garyfallidis at gmail.com (Eleftherios Garyfallidis) Date: Fri, 16 Aug 2019 20:46:44 -0000 Subject: [scikit-learn] ANN: DIPY 1.0.0 - a historic release Message-ID: We are excited to announce a new major and historic release of Diffusion Imaging in Python (DIPY). DIPY 1.0.0 is out! Please cite using the following DOI: 10.3389/fninf.2014.00008 DIPY 1.0.0 (Monday, 5 August 2019) This release received contributions from 17 developers (the full release notes are at: https://dipy.org/documentation/1.0.0./release_notes/release1.0/). Thank you all for your contributions and feedback! A new DIPY era is starting: this release is compatible with python 3.5+ and breaks backward compatibility with 0.x.x. Please click here to check API changes or look at the end of this email. The 0.16.x series will have extended bug-fix-only support for Python 2.7 until June 2020. Highlights of this release include: - Critical API changes - New awesome website - Large refactoring of tracking API - New denoising algorithm: MP-PCA - New Gibbs ringing removal - New interpolation module: dipy.core.interpolation - New reconstruction models: Mean Signal DKI, MTMS-CSD - Increased coordinate systems consistency - New object to manage safely tractography data: StatefulTractogram - New command line interface for downloading datasets: FetchFlow - Horizon updated, medical visualization interface powered by QuickBundlesX - Removed all deprecated functions and parameters - Removed compatibility with Python 2.7 - Updated minimum dependencies version (Numpy, Scipy) - All tutorials updated to API changes and 3 new added - Large documentation update - Closed 289 issues and merged 98 pull requests Note: - DIPY 0.16.x will be the last series to support python 2. The next release, DIPY 1.0, will support python 3 only. To upgrade or install DIPY Run the following command in your terminal: pip install --upgrade dipy or conda install -c conda-forge dipy This version of DIPY depends on nibabel (2.4.0+). For visualization you need FURY (0.3.0+). Questions or suggestions? For any questions go to http://dipy.org, or send an e-mail to dipy at python.org We also have an instant messaging service and chat room available at https://gitter.im/nipy/dipy On behalf of the DIPY developers, Eleftherios Garyfallidis, Ariel Rokem, Serge Koudoro https://dipy.org/contributors API Changes Some of the changes introduced in the 1.0 release will break backwards compatibility with previous versions. This release is compatible with Python 3.5+ Reconstruction The spherical harmonics bases mrtrix and fibernav have been renamed to tournier07 and descoteaux07 after the deprecation cycle started in the 0.15 release. We changed dipy.data.default_sphere from symmetric724 to repulsion724 which is more evenly distributed. Segmentation The API of dipy.segment.mask.median_otsu has changed in the following ways: if you are providing a 4D volume, vol_idx is now a required argument. The order of parameters has also changed. Tractogram loading and saving The API of dipy.io.streamlines.load_tractogram and dipy.io.streamlines.save_tractogram has changed in the following ways: When loading trk, tck, vtk, fib, or dpy) a reference nifti file is needed to guarantee proper spatial transformation handling. Spatial transformation handling Functions from dipy.tracking.streamlines were modified to enforce the affine parameter and uniform docstrings. deform_streamlines select_by_rois, orient_by_rois, _extract_vals and values_from_volume. Functions from dipy.tracking.utils were modified to enforce the affine parameter and uniform docstring. density_map connectivity_matrix, seeds_from_mask, random_seeds_from_mask, target, target_line_based, near_roi, length and path_length were all modified. The function affine_for_trackvis, move_streamlines, flexi_tvis_affine and get_flexi_tvis_affine were deleted. Functions from dipy.tracking.life were modified to enforce the affine parameter and uniform docstring. voxel2streamline, setup and fit from class FiberModel were all modified. afq_profile from dipy.stats.analysis was modified in a similar way. Simulations - dipy.sims.voxel.SingleTensor has been replaced by dipy.sims.voxel.single_tensor - dipy.sims.voxel.MultiTensor has been replaced by dipy.sims.voxel.multi_tensor - dipy.sims.voxel.SticksAndBall has been replaced by dipy.sims.voxel.sticks_and_ball Interpolation All interpolation functions have been moved to a new module name dipy.core.interpolation Tracking The voxel_size parameter has been removed from the following function: - dipy.tracking.utils.connectivity_matrix - dipy.tracking.utils.density_map - dipy.tracking.utils.stremline_mapping - dipy.tracking._util._mapping_to_voxel The dipy.reconst.peak_direction_getter.PeaksAndMetricsDirectionGetter has been renamed dipy.reconst.peak_direction_getter.EuDXDirectionGetter. The LocalTracking and ParticleFilteringTracking functions were moved from dipy.tracking.local.localtrackingto dipy.tracking.local_tracking. They now need to be imported from dipy.tracking.local_tracking. - functions argument tissue_classifier were renamed stopping_criterion The TissueClassifier were renamed StoppingCriterion and moved from dipy.tracking.local.tissue_classifier to dipy.tracking.stopping_criterion. They now need to be imported from dipy.tracking.stopping_criterion. - TissueClassifier -> StoppingCriterion - BinaryTissueClassifier -> BinaryStoppingCriterion - ThresholdTissueClassifier -> ThresholdStoppingCriterion - ConstrainedTissueClassifier -> AnatomicalStoppingCriterion - ActTissueClassifier -> ActStoppingCriterion - CmcTissueClassifier -> CmcStoppingCriterion The dipy.tracking.local.tissue_classifier.TissueClass was renamed dipy.tracking.stopping_criterion.StreamlineStatus. The EuDX tracking function has been removed. EuDX tractography can be performed using dipy.tracking.local_tracking using dipy.reconst.peak_direction_getter.EuDXDirectionGetter. Streamlines dipy.io.trackvis has been removed. Use dipy.io.streamline instead. Other - dipy.external package has been removed. - dipy.fixes package has been removed. - dipy.segment.quickbundes module has been removed. - dipy.reconst.peaks module has been removed. - Compatibility with Python 2.7 has been removed -------------- next part -------------- An HTML attachment was scrubbed... URL: