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

Refactoring PopMember + adding adaptive parsimony to tournament #75

Merged
merged 14 commits into from
Mar 9, 2022

Conversation

MilesCranmer
Copy link
Owner

This PR includes both:

  1. A refactor of PopMember to both include a score (which has the complexity penalty), and loss (the raw loss).
  2. Incorporation of the adaptive parsimony strategy into the tournament scoring, rather than just the simulated annealing part of the pipeline.
  3. Tweaking the adaptive parsimony to use a moving window (10 cycles window size), rather than accumulating over the entire search.

@MilesCranmer
Copy link
Owner Author

This is a breaking change to the library as it introduces the loss attribute of PopMember, as well as changes scoreFunc to output two numbers rather than one. Therefore this will bump the version to 0.8.0.

@MilesCranmer
Copy link
Owner Author

Generating random trees as one of the mutations kind of messes up the search because the trees are always size 5. Let me tweak the random tree generation mutation to be of random size - any possible size is valid.

@MilesCranmer MilesCranmer merged commit 1d0529d into master Mar 9, 2022
@MilesCranmer MilesCranmer deleted the storing_popmember_loss branch March 9, 2022 23:47
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.

None yet

1 participant