Add comp #57
Merged
Add comp #57
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
added 7 commits
February 19, 2024 18:04
- start to get rid of AnalyzePeptides class
- base filtering on number of quantified samples (sample completness)
- 🔥 remove old funtions which are obsolete - 🎨 rename fake_na to simulated_na (to do everywhere) - clean-up fastai imports and assign parts explicitly for linting
- 🔥 remove one subclassing level, commented code - 🎨 rename fake to simulated NA and clean-up notebook
- if there will be a command line interface, then it will be defined in __main__.py
- 🎨 remove one level of inheritence - 🎨 rename fake to simulated NA
Idea: Only use a subset of samples to generate simulated validation and test data from. Performance is then split by validation and test samples, although the remaining data can be used at training time. (will be compared to setup where simulated missing values are sampled from all samples)
enryH
force-pushed
the
add_comp
branch
2 times, most recently
from
ebb42d1 to
651f6bc
Compare
- fastai routine needs always a validation dataset, but it can be empty.
added 5 commits
February 24, 2024 09:45
- set fastai defaults to cpu
- compare two sampling strategies
|
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Outdated suggestions cannot be applied.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.
Streamline comparison and add new ways of sampling simulated missing values.
fixed that DAE and VAE can also be trained without a validation split
cleaned up model classes, started to get ride of PeptideAnalyzer (also moving code)
no dependency on Thermo specific metadata (basic quality control by number of features in sample)