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

Update Phase I learning code to latest master #54

Open
wants to merge 19 commits into
base: master
Choose a base branch
from

Conversation

dzenanz
Copy link
Member

@dzenanz dzenanz commented Feb 4, 2021

Supersedes and closes #52.

matthewma7 and others added 19 commits January 12, 2021 20:45
active learning with girder worker

Show good_prob row

Add active learning persisted state
Add a note indicating that the slash is needed at the end of the mriqc
path (we should fix this, but it works this way for now).

Also, I added the --no-sub argument when running mriqc so that we avoid
submission of the computed metrics back to mriqc.nimh.nih.gov, at least
while we are doing a lot of testing of our workflow.
: used in time separation (e.g. 16:10:20) is not allowed in file name on Windows.
This adds a radio group to the retrain dialog, allowing the user to
select neural network or random forest classifaction.  Also adds a
placeholder for neural network learning in the tasks.py module.

Also fixes the bug where the retrain dialog "Cancel" button does
not work, and adds a note to dev doc on running "data2mriqc.py".
WARNING/MainProcess] m:\dev\zarr\miqa\mriqc\mriqc\data_loader.py:112: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  self.data['good_prob'][i] = predictions[ind]
@dzenanz dzenanz mentioned this pull request Feb 4, 2021
@aashish24 aashish24 changed the title Add ability to parse and display MRIQC metrics Update Phase I learning code to latest master May 6, 2021
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

Successfully merging this pull request may close these issues.

3 participants