Published November 29, 2024 | Version v1.1.1
Software Open

manujosephv/pytorch_tabular: v1.1.1

Authors/Creators

  • 1. Walmart Global Tech
  • 2. Lightning.ai | Grid.ai
  • 3. PyMC Labs
  • 4. Kyndryl
  • 5. Indian Institute of Technology Hyderabad
  • 6. @UConnAI
  • 7. @deshaw
  • 8. Bending Spoons
  • 9. @AccelerationConsortium (UoT) @sparks-baird (UoU)
  • 10. furyhawk Pte. Ltd.

Description

Release Notes

New Features

  • Support for Multi-Model Tuning: Added support for tuning multiple models using the tuner functionality, enhancing flexibility in hyperparameter optimization.
    [Commit: 560dec6]

  • Multi-Target Classification: Introduced multi-target classification capabilities, expanding the library's support for more complex use cases.
    [Commit: 25691f5]

  • dataloader_kwargs in DataConfig: Added support for customizing dataloader_kwargs in the DataConfig module for improved data-loading flexibility.
    [Commit: caa3ea1]

Enhancements

  • Improved Informative str and repr: Added more informative str and repr methods to enhance debugging and readability of objects.
    [Commit: 495803c]

  • Bug Fixes for Categorical Dtype: Fixed issues with Categorical data type handling to ensure smoother model training and predictions.
    [Commit: cf1454a]

  • Removed Restrictions on Missing and Unknown Values: Enhanced the framework to handle missing and unknown values more robustly.
    [Commit: fc6060e]

  • Protection Against Misuse of MDN Head: Added safeguards to prevent improper usage of the MDN Head in models.
    [Commit: cc3504a]

Bug Fixes

  • Fixed an SSL finetuning bug to ensure secure operations during model fine-tuning.
    [Commit: 3d978f9]

  • Fixed errors in saving and loading custom loss functions to enhance reproducibility and reliability.
    [Commit: 3f0a15c]

  • Addressed a bug in cross-validation, ensuring accurate evaluation metrics.
    [Commit: 0d088fc]

  • Fixed a KeyError issue with nn.activation in Tab Transformer and FT Transformer models.
    [Commit: 11adefa]

Other Improvements

  • Multiple pre-commit configuration updates and enhancements for code linting and formatting.
    [Commits: f354b9c, 75b21c4, a890dda]

  • Various CI improvements, including dependency bump for gh-action-pypi-publish and caching updates.
    [Commits: cb78a6e, e49a999, da20ed3]

  • Fixed typos and minor issues in documentation and code for improved clarity and maintainability.
    [Commits: 7285787, 6586705]

For more details, you can refer to the respective commits on the library's GitHub repository.

New Contributors

  • @furyhawk made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/382
  • @HernandoR made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/410
  • @charitarthchugh made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/420
  • @abhisharsinha made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/455
  • @YonyBresler made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/441
  • @snehilchatterjee made their first contribution in https://github.com/manujosephv/pytorch_tabular/pull/492

Full Changelog: https://github.com/manujosephv/pytorch_tabular/compare/v1.1.0...v1.1.1

Files

manujosephv/pytorch_tabular-v1.1.1.zip

Files (2.8 MB)

Name Size Download all
md5:ca8f12cfcabd4e40674413990f0efb9b
2.8 MB Preview Download

Additional details

Related works

Is supplement to
Software: https://github.com/manujosephv/pytorch_tabular/tree/v1.1.1 (URL)