Will McGinnis
Will McGinnis
Hello all. First, thanks for checking out and participating in this project. I started it a few years ago and with the help of many got it into a pretty...
Historically this project has done releases based on when I felt like doing a release, or when someone explicitly opened an issue asking for one. That's not great. I'd like...
It would be great to use something like this: https://github.com/EpistasisLab/penn-ml-benchmarks to get a comprehensive view of memory usage, time-to-transform, and end-model accuracy for all encoders. It'd probably take a very...
If I have 3 competitors with scores: [10, 4, 1], I want to update an arena such that the pairwise comparisons: competitor 1 vs competitor 2 competitor 1 vs competitor...
If joblib is available, use the methods shown in tags, and branches to parallelize the calls out to child repos.
As described in issue #23, add a parameter to all of the favorite methods called "rich", defaulting to False, which toggles between returning all data (current state) and a reduced...
As described in issue #23, add a parameter to all of the timeline methods called "rich", defaulting to False, which toggles between returning all data (current state) and a reduced...
**Description:** Add support for storing and retrieving ratings from various database systems. **Tasks:** - Implement database adapters for common databases (SQL, MongoDB, etc.) - Add migration tools for schema changes...
**Description:** Add support for confidence intervals and uncertainty quantification across all rating algorithms. **Tasks:** - Implement confidence interval calculations for all rating algorithms - Add methods to query rating uncertainty...
**Description:** Implement support for multi-factor ratings that incorporate various metrics beyond win-loss records. **Tasks:** - Create a framework for multi-factor rating calculations - Implement weighting mechanisms for different factors -...