✨ MOVE update #89
Open
✨ MOVE update #89
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Tasks are classes instead of function (can be instantiated by Hydra) - Encode data directly saves files as tensors - Various changes related to making
Save tensor, feature names, and mapping in a single file instead of three individual files
- Add MOVE task - Add log function to sub-tasks - Add sub-task class with CSV writer - Make training loop CSV writer sub-task
- Set up mixins for i/o directories - Make subtask a mixin - Make CSV writing a mixin
Place mixin dfn first to ensure they take precedence
- Add perturbation class and property to MOVE dataset - Add checks to ensure MOVE datasets have unique names - Add function to discrete datasets to one-hot encode - Add checks to ensure named datasets have unique features - Because MOVE dataset returns a tuple, update batch loops to take first element - Add type hints to MOVE dataloader
- Make data subset size configurable (training, test, validation size) in data config - Add option to standardize data without applying base-2 log - During encoding, generate split indices and save - When re-loading a dataset, use split indices to load a specific subset of data
Make default "all" (to not affect other tasks that do not require train/test split)
- Read "./." genotypes as NA - Reindex dataframe (include NA rows if missing samples)
Handle data loader config internally, only require users to input batch size
Keep dimensions if NaNs are present
If NaNs were present, the boxplot would not work. Remove them beforehand
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.