Skip to content

Conversation

@roshankern
Copy link
Member

@gwaybio This is ready for review!

@roshankern
Copy link
Member Author

Just realized it might be useful to show well or plate for UMAP colors, which could indicate/disprove any plate/image effects on features. I will implement this and let you know when done.

@roshankern roshankern requested a review from gwaybio August 9, 2022 20:43
Copy link
Member

@gwaybio gwaybio left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! A couple general comments:

  1. I like that you saved the UMAP coordinates, will you use these to generate publication-ready figures later? (I noticed that you didn't save the actual UMAP images)
  2. Does format_training_data.ipynb need a number prefix? (i.e. does it need to be executed in a specific order?)

Co-authored-by: Gregory Way <gregory.way@gmail.com>
@roshankern
Copy link
Member Author

  1. I was just being thorough saving the UMAP coordinates (in case we wanted to analyze/visualize these differently). The publication-ready figures are accessible through the executed jupyter notebook html file. Should I also save the images in results/?
  2. format_training_data.ipynb does not need to be executed in a specific order so I will remove the number prefix.

@gwaybio
Copy link
Member

gwaybio commented Aug 9, 2022

Should I also save the images in results/?

Probably. It wouldn't hurt.

@roshankern roshankern merged commit 27e3de9 into WayScience:main Aug 9, 2022
@roshankern roshankern deleted the add-analysis-module branch August 9, 2022 22:01
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.

2 participants