Re: [scikit-learn] Contribution

@Jacob, I understand your concern about the new algorithms. It will be lost effort to make coding, updating, documentation for a unsuccessful algorithm. Thanks for the tips. @federico, lightning library is, close to what in my mind but not the same. I think, there should be an easy way to see how

Re: [scikit-learn] Contribution - Markov Clustering

I've added this PR, and I addressed in the comments some of your concerns (publications, comparison to affinity propagation, etc). https://github.com/scikit-learn/scikit-learn/pull/9329 I'd love for you to review, since this is my first PR in the scikit learn repository On Wed, Jul 12, 2017 at 1

Re: [scikit-learn] Contribution - Markov Clustering

If this is the first time you contribute, please make sure to carefully read the contributors guide till the end: http://scikit-learn.org/stable/developers/contributing.html In particular, make sure to follow the estimators API conventions for your PR to get a chance to be reviewed. In particular

Re: [scikit-learn] Contribution - Markov Clustering

You don't need our permission to submit a PR, go ahead! We welcome PRs. On Mon, Jul 10, 2017 at 9:36 PM, Uri Goren wrote: > I have, > The only criterion that I am unsure about is the number citations. > > In the literature Markov clustering is usually compared to affinity > prolongation, which a

Re: [scikit-learn] Contribution - Markov Clustering

I have, The only criterion that I am unsure about is the number citations. In the literature Markov clustering is usually compared to affinity prolongation, which also has a similar number of citations. I have attached my implementation in my github account for you to review. Do I have your appr

Re: [scikit-learn] Contribution - Markov Clustering

hi, did you have a look at : http://scikit-learn.org/stable/faq.html#what-are-the-inclusion-criteria-for-new-algorithms Alex ___ scikit-learn mailing list scikit-learn@python.org https://mail.python.org/mailman/listinfo/scikit-learn

[scikit-learn] Contribution - Markov Clustering

Hi, I've been advised to contact you before working on an implementation of a new feature. I am thinking of implementing the Markov clustering and add it to sklearn.cluster module. See: https://micans.org/mcl/ https://gist.github.com/urigoren/1f76567f3af56ed8c33f076537768a60 Do you know if anyo

Re: [scikit-learn] Contribution

On Mon, Jul 10, 2017 at 04:10:09PM +, federico vaggi wrote: > There is a fantastic library called lightning where the optimization > routines are first class citizens: > http://contrib.scikit-learn.org/lightning/ - you can take a look there. > However, lightning focuses on convex optimization,

Re: [scikit-learn] Contribution

Hi, I'd like to implement the Markov clustering algorithm, Any objections? On Jul 10, 2017 7:10 PM, "federico vaggi" wrote: Hey Gurhan, sklearn doesn't really neatly separate optimizers from the models they optimize at the level of API (except in a few cases). In order to make the package mor

Re: [scikit-learn] Contribution

Hey Gurhan, sklearn doesn't really neatly separate optimizers from the models they optimize at the level of API (except in a few cases). In order to make the package more friendly to newer user, each model has excellent optimizer defaults that you can use, and only in a few cases does it make sen

Re: [scikit-learn] Contribution

Howdy This question and the one right after in the FAQ are probably relevant re: inclusion of new algorithms: http://scikit-learn.org/stable/faq.html#what-are-the-inclusion-criteria-for-new-algorithms. The gist is that we only include well established algorithms, and there are no end to those. I t

[scikit-learn] Contribution

Hi everyone, I am wondering, How can I use external optimization algorithms with scikit-learn, for instance neural network , instead of defined algorithms ( Stochastic Gradient Descent, Adam, or L-BFGS). Furtherm

Re: [scikit-learn] Contribution to sklearn: Cross validation of time series

p. m. Para: Scikit-learn user and developer mailing list Asunto: Re: [scikit-learn] Contribution to sklearn: Cross validation of time series Hey Andres. I think there might be a PR for that. Can you explain the minimum size of the training set? How is that used? I thought the other main option would b

Re: [scikit-learn] Contribution to sklearn: Cross validation of time series

Hi Andres, hi Andy, Indeed in real life I also needed to cross-validate time series in a different manner than TimeSeriesSplit implemented in sklearn does. I fully support the idea of such a contribution Andres. As Andy mentioned, the main option would be a « rolling window » or as I use to say

Re: [scikit-learn] Contribution to sklearn: Cross validation of time series

Hey Andres. I think there might be a PR for that. Can you explain the minimum size of the training set? How is that used? I thought the other main option would be "rolling window" cross validation to use a fixed length cv training set. So the two options to me were rolling window and what we're d

[scikit-learn] Contribution to sklearn: Cross validation of time series

Hello, I'd like to contribute with a new functionality in sklearn. It's the cross validation of time series. It's an evolution of the current functionality, implemented by TimeSeriesSplit. TimeSeriesSplit only allows the user to set the number of folds. In real life, when performing the c

Re: [scikit-learn] contribution to scikit-learn - questions

Hi Konstantinos. There is an IRC channel but it's not that busy any more. You could try the gitter channel at http://gitter.im/scikit-learn/scikit-learn The issue that you cited is ok, but this one might be easier to start with: https://github.com/scikit-learn/scikit-learn/issues/8194 You need

[scikit-learn] contribution to scikit-learn - questions

Hello all, My name is Konstantinos and I would like to contribute to scikit-learn. I am relatively new to open source development and I want to work on some easy bug-fixing to get used to the github workflow. Firstly, is this issue open and should I try working on it? https://github.com/scik

Re: [scikit-learn] Contribution project proposal

Hi, Thank you all for the info. It is not my first contribution to a project (I made little contributions to xgboost and tensorflow), even though I think it is really interesting what Oliver said, specially because of the very curated structure and guidelines of the project. BTW, I’ve found su

Re: [scikit-learn] Contribution project proposal

If this is your first contribution to the project, I would strongly suggest to start by contributing a small bug fix or improvement to get accustomed to the kind of things the core devs expect when reviewing a PR. Also please read the contributors guide : http://scikit-learn.org/dev/developers/co

Re: [scikit-learn] Contribution project proposal

I remember that there was a discussion regarding stacking in general after we implemented the majority voting classifier, and I just found a PR with some stacking implementation that seems to be in progress https://github.com/scikit-learn/scikit-learn/pull/6674 > On Sep 20, 2016, at 8:02 PM, J

Re: [scikit-learn] Contribution project proposal

Have you searched the issue tracker for Stacking and the relationship between your proposal and others in the works? https://github.com/scikit-learn/scikit-learn/search?q=stacking&type=Issues&utf8=%E2%9C%93 On 21 September 2016 at 02:04, Iván Vallés Pérez wrote: > Hello, > > My name is Iván Val

[scikit-learn] Contribution project proposal

Hello, My name is Iván Vallés and I am Data Scientist. I am really interested in contributing to the Scikit-Learn project by writing a new feature: Stacked Generalization Ensemble. I would like to know if it is being developed and if you think it is worth. Of course it is a long-term project due t