New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
sklearn api #12
Comments
Hi, all the Smoother classes compute 'smooth'... this is the equivalent of 'fit_trasform' method. There is no way to operate 'fit' or 'transform' separately. For this reason, I prefer to not introduce this behavior, but you are free to create your own class in sklearn style like a wrapper of tsmoothie. If you support the project don't forget to live a star ;-) All the best |
thanks for the answer I am aware of this behavior, but I don't think you are entirely right. There are many classes where you calculate That is by definition the separation between fit (where you calculate the A similar pattern happens for the And finally for So I believe saying "There is no way to operate 'fit' or 'transform' separately" is inaccurate. That being said I love the package and I am not saying you should change the api to At the moment creating a Again just my 2 cents and congrats for the awesome work. |
Thanks for the suggestions, but I saw them not entirely applicable to all the smoother available. For the same reason, I used _store_results, as a common method for all the smoother, to make the code build in the same way (this is only a choice of mine). I also think that a dummy sklearn wrapper can be built in this simple way (also it depends on what u are looking for):
Bye |
Would you consider the possibility of making it compatible with
sklearn
usingfit
andtransform
instead ofsmooth
?Is there a specific reason why you save the transformed data as an instance attribute? (this would be against the
sklearn
API)I am thinking of doing it myself for a project I am working on but I wanted to ask you first if I missed anything obvious that would make this difficult or not possible.
Many thanks
The text was updated successfully, but these errors were encountered: