[Mne_analysis] GSoC Idea, Improving decode module

Thu Mar 10 13:37:51 EST 2016

Hi Asish,

let me reply inline

On Thu, Mar 10, 2016 at 7:24 PM, Asish Panda <asishrocks95 at gmail.com> wrote:

> Hi Jean,
>
> I have been going through the idea list and I felt that a discussion is
> needed  before I start drafting the proposal. From what I have understood
> so far, we have to:
> 1) Refactor `decoding` objects, GAT and EMS so that it works with `cross
> validation` and `grid search` of scikit-learn. They should also work with
> multiclass problems.
> 2) Simplify user interface by calling `EpochsVectorizer` internally.
>
> Is that the main goal that should be achieved by the end of GSoC? Or is
> there anything else that is expected?
>

this would be one important element of the GSOC, but as you may have
noticed the entire decoding module needs some love and care.

> In summary, this project will involve a series of usability improvements
>> for the decoding module and extend its functionality.
>
> I feel the above statement is quite vague for writing a detailed plan in
> the proposal. Or perhaps the "improvements" can only be known while the
> objectives(listed above) are being fulfilled?
> Lastly, going a little out of topic, could you now please elaborate on how
> to set up the cleaner framework of the decoding module, that you mentioned
> in the last message?
>
>
For example, currently we have the problem that some parts of the MNE tools
are not nicely pluggable into the scikit-learn Pipeline objects. We have
all over the place functions that return numpy arrays, others return Epochs
or Raw. There is a lot of work to be done to unify the APIs. So fare the
admittedly vague idea is to make it fun to use the decoding module to
combine different elements of MNE processing functions into powerful
scikit-learn pipelines. Another issue that we have is that we don't have
any nice persistance mechanism to store classifiers and outputs from our
decoding objects. There is also more to do on vizualization. E.g. make it
easy to visualize standard ML diagnostics like leanring curves, etc. If you
want to get the intuition the idea is to make the coding gap between
sklearn and MNE significantly tighter. But once we decide to go in this
direction we will of course agree on a detailed proposal.

I hope this is somewhat satisfying while stimulating your curiosity.

--Denis

> Thank you
> Asish Panda
>
> On Fri, Feb 26, 2016 at 9:50 PM, Asish Panda <asishrocks95 at gmail.com>
> wrote:
>
>> Hello Jean
>>
>> Thank you very much for your response and the issues. I will get my hand
>> dirty right away! :)
>>
>> Thank you
>> Asish Panda
>>
>> On Fri, Feb 26, 2016 at 8:37 PM, JR KING <jeanremi.king at gmail.com> wrote:
>>
>>> Hi Asish,
>>>
>>> Thanks for your interest!.
>>>
>>> You can start with one of these easy PR:
>>> https://github.com/mne-tools/mne-python/issues/2874
>>> https://github.com/mne-tools/mne-python/issues/2176
>>> https://github.com/mne-tools/mne-python/issues/2189 (probably needs a
>>> bit of discussion)
>>>
>>> Once you're there I can suggest you some more fun things that you could
>>> do to set up a cleaner framework for the decoding module.
>>>
>>> All the best,
>>>
>>> Jean-Rémi
>>>
>>> On 26 February 2016 at 09:57, Asish Panda <asishrocks95 at gmail.com>
>>> wrote:
>>>
>>>> Hello everyone,
>>>>
>>>> I am looking forward to participate in GSoC and I am interested in the
>>>> idea of improving the decode module
>>>> <https://github.com/mne-tools/mne-python/wiki/GSOC-Ideas#3-improve-the-decoding-module>.
>>>> I have installed and set up the development environment and have been
>>>> trying to get familiar with various modules. However being quite new to
>>>> MEG, EEG I'm looking for some pointers to start as well as prerequisites to
>>>> work on decode module.
>>>> Lastly I apologize if I have been rude in any manner.
>>>>
>>>> Thank you
>>>> Asish Panda
>>>>
>>>> _______________________________________________
>>>> Mne_analysis mailing list
>>>> Mne_analysis at nmr.mgh.harvard.edu
>>>> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
>>>>
>>>>
>>>> The information in this e-mail is intended only for the person to whom
>>>> it is
>>>> addressed. If you believe this e-mail was sent to you in error and the
>>>> e-mail
>>>> contains patient information, please contact the Partners Compliance
>>>> HelpLine at
>>>> http://www.partners.org/complianceline . If the e-mail was sent to you
>>>> in error
>>>> but does not contain patient information, please contact the sender and
>>>> properly
>>>> dispose of the e-mail.
>>>>
>>>>
>>>
>>> _______________________________________________
>>> Mne_analysis mailing list
>>> Mne_analysis at nmr.mgh.harvard.edu
>>> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
>>>
>>>
>>> The information in this e-mail is intended only for the person to whom
>>> it is
>>> addressed. If you believe this e-mail was sent to you in error and the
>>> e-mail
>>> contains patient information, please contact the Partners Compliance
>>> HelpLine at
>>> http://www.partners.org/complianceline . If the e-mail was sent to you
>>> in error
>>> but does not contain patient information, please contact the sender and
>>> properly
>>> dispose of the e-mail.
>>>
>>>
>>
>
> _______________________________________________
> Mne_analysis mailing list
> Mne_analysis at nmr.mgh.harvard.edu
> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/mne_analysis
>
>
> The information in this e-mail is intended only for the person to whom it
> is
> addressed. If you believe this e-mail was sent to you in error and the
> e-mail
> contains patient information, please contact the Partners Compliance
> HelpLine at
> http://www.partners.org/complianceline . If the e-mail was sent to you in
> error
> but does not contain patient information, please contact the sender and
> properly
> dispose of the e-mail.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.nmr.mgh.harvard.edu/pipermail/mne_analysis/attachments/20160310/3d90ca5e/attachment-0001.html 