Skip to content
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

Replace mdp.FastICANode with sklearn.decomposition.FastICA #14

Closed
emdupre opened this issue Apr 25, 2018 · 1 comment
Closed

Replace mdp.FastICANode with sklearn.decomposition.FastICA #14

emdupre opened this issue Apr 25, 2018 · 1 comment
Milestone

Comments

@emdupre
Copy link
Member

emdupre commented Apr 25, 2018

From @emdupre on November 15, 2017 16:38

After refactoring, if integration tests show that we're still achieving similar results, we should remove the mdp dependency as this library is no longer actively maintained. Instead, this should be replaced with FastICA as implemented in sklearn.

Copied from original issue: emdupre/tedana#7

@emdupre emdupre added the mozsprint Issues highlighted for the 2018 Mozilla Global Sprint label Apr 25, 2018
@emdupre
Copy link
Member Author

emdupre commented May 11, 2018

@prantikk it looks like you were the one who originally wrote the two-stage cost function into MDP— was this specifically for ME-ICA ? If so, would you rather we keep the MDP dependency, since sklearn doesn't allow for this dual staging ?

@emdupre emdupre removed the mozsprint Issues highlighted for the 2018 Mozilla Global Sprint label May 28, 2018
@tsalo tsalo added this to the 0.1.0 milestone Jul 7, 2018
@emdupre emdupre modified the milestones: 0.1.0, 1.0.0 Jul 31, 2018
@tsalo tsalo closed this as completed Nov 14, 2018
handwerkerd pushed a commit to handwerkerd/tedana that referenced this issue Sep 8, 2022
…th_main

removed unnecessary function tedana.selection.selection_utils.get_new_meanmetricrank
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants