Recent Releases of yaib

yaib - Refactoring and feature additions

New Features

  • Polars backend for preprocessing (significantly faster preprocessing)
  • Modality selection (for doing experiments that need to show modality contributions)
  • Optuna optimization with visualization and checkpointing
  • Options to use SHAP or other explainers (improved support pending)
  • Introduced configuration settings for multiple classifiers including Balanced Random Forest, CatBoost, XGBoost, and RUSBClassifier.
  • Refactored RNN, GRU, TCN, and Transformer.
  • Enhanced capabilities for binary classification, regression, and dataset imputation tasks.
  • Added new configuration for benchmarking experiments.
  • Enhanced error handling in cross-validation processes.

Chores - Updated dependencies and package versions for better compatibility.

What's Changed

  • Requirements and setup update by @rvandewater in https://github.com/rvandewater/YAIB/pull/120
  • reformat by @rvandewater in https://github.com/rvandewater/YAIB/pull/121
  • Pypi readme fixes by @rvandewater in https://github.com/rvandewater/YAIB/pull/122
  • Recipies update by @rvandewater in https://github.com/rvandewater/YAIB/pull/124
  • Dataset fix and small setup/readme adjustments by @rvandewater in https://github.com/rvandewater/YAIB/pull/126
  • Use correct (?) scaling in DefaultRegressionPreprocessor by @mlondschien in https://github.com/rvandewater/YAIB/pull/127
  • Fix commands flags by @HendrikSchmidt in https://github.com/rvandewater/YAIB/pull/133
  • logging fix by @rvandewater in https://github.com/rvandewater/YAIB/pull/134
  • Added metrics by @rvandewater in https://github.com/rvandewater/YAIB/pull/135
  • Fix regular ML model training by @rvandewater in https://github.com/rvandewater/YAIB/pull/132
  • comment in ontestepoch_start by @rvandewater in https://github.com/rvandewater/YAIB/pull/137
  • By default, use quicker versions of nafill recently added to ReciPys by @prockenschaub in https://github.com/rvandewater/YAIB/pull/139
  • Pooled experiments by @rvandewater in https://github.com/rvandewater/YAIB/pull/140
  • Transfer learning by @rvandewater in https://github.com/rvandewater/YAIB/pull/136
  • Rename kf to kidney_function by @prockenschaub in https://github.com/rvandewater/YAIB/pull/145
  • Hyperparameter opt by @rvandewater in https://github.com/rvandewater/YAIB/pull/147
  • Bump pyarrow from 11.0.0 to 14.0.1 by @dependabot in https://github.com/rvandewater/YAIB/pull/148
  • Bump scikit-learn from 1.2.2 to 1.5.0 by @dependabot in https://github.com/rvandewater/YAIB/pull/149
  • Bump black from 24.2.0 to 24.3.0 by @dependabot in https://github.com/rvandewater/YAIB/pull/150
  • Bump tqdm from 4.64.1 to 4.66.3 by @dependabot in https://github.com/rvandewater/YAIB/pull/151
  • Polars by @rvandewater in https://github.com/rvandewater/YAIB/pull/152
  • Bump lightning from 2.3.0 to 2.3.3 by @dependabot in https://github.com/rvandewater/YAIB/pull/156
  • Version release based on practice Cassandra use by @rvandewater in https://github.com/rvandewater/YAIB/pull/155

New Contributors

  • @mlondschien made their first contribution in https://github.com/rvandewater/YAIB/pull/127
  • @dependabot made their first contribution in https://github.com/rvandewater/YAIB/pull/148

Full Changelog: https://github.com/rvandewater/YAIB/compare/v0.3.0...v1.0.0

- Python
Published by rvandewater almost 2 years ago

yaib - YAIB Public Release

The public release contains a lot of fixes and refactoring.

- Python
Published by rvandewater about 3 years ago

yaib - YAIB Imputation Update

This version of YAIB adds Pytorch Lightning training, Wandb logging, and a range of imputation methods.

What's Changed

  • Imputation Models, Processing, and Refactorings
  • Refactoring updates

Full Changelog: https://github.com/rvandewater/YAIB/compare/latest...v0.2.0

- Python
Published by rvandewater over 3 years ago

yaib - YAIB v0.1.0

First public release of Yet Another ICU Benchmark (YAIB).

- Python
Published by rvandewater over 3 years ago