Skip to content

History

Certainly! Here's a release update you can use for the history.md file:

1.1.0 (2024-01-15)

New Features and Enhancements

  • Added DANet Model: Added a new model, DANet, for tabular data.
  • Explainability: Integrated Captum for explainability
  • Hyperparameter Tuner: Added Grid and Random Search functionality to search through hyperparameters and return best model.
  • Model Sweep: Added an easy "Model Sweep" method with which we can sweep a list of models with given data and quickly assess performance.
  • Documentation Enhancements: Improved documentation to make it more user-friendly and informative
  • Dependency Updates: Updated various dependencies for improved compatibility and security
  • Graceful Out-of-Memory Handling: Added graceful out-of-memory handling for tabular models
  • GhostBatchNorm: Added GhostBatchNorm to the library

Deprecations

  • Deprecations: Handled deprecations and updated the library accordingly
  • Entmax Dependency Removed: Removed dependency on entmax

Infrastructure and CI/CD

  • Continuous Integration: Improved CI with new actions and labels
  • Dependency Management: Updated dependencies and restructured requirements

API Changes

  • [BREAKING CHANGE] SSL API Change: Addressed SSL API change, along with documentation and tutorial updates.
  • Model Changes: Added is_fitted and other markers to the tabular model.
  • Custom Optimizer: Allow custom optimizer in the model config.

Contributors

Upgrading

  • Ensure to check the updated documentation for any breaking changes or new features.
  • If you are using SSL, please check the updated API and documentation.

1.0.2 (2023-05-31)

New Features:

  • Added Feature Importance: The library now includes a new method in TabularModel and BaseModel for enabling feature importance. Feature Importance has been enabled for FTTransformer and GATE models. [Commit: dc2a49e]

Enhancements:

  • Enabled two more parameters in the GATE model. [Commit: 3680413]
  • Included metric_prob_input parameter in the library configuration. This update allows for better control over metrics in the models. [Commit: 0612db5]
  • Slight improvements to the GATE model, including changes to defaults for better performance. [Commit: c30a6c3]
  • Minor bug fixes and improvements, including accelerator options in the configuration and progress bar enhancements. [Commit: f932230, bdd9adb, f932230]

Dependency Updates:

  • Updated dependencies, including docformatter, pyupgrade, and ruff-pre-commit. [Commits: 4aae9a8, b3df4ce, bdd9adb, 55e800c, c6c4679, c01154b, 107cd2f]

Documentation Updates:

  • Updated the library's README.md file. [Commits: db8f3b2, cab6bf1, 669faec, 1e6c400, 3097799, 7fabf6b]

Other Improvements:

  • Various code optimizations, bug fixes, and CI enhancements. [Commits: 5637020, e5171bf, 812b40f]

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

1.0.1 (2023-01-20)

  • Bugfix for default metric for binary classification

1.0.0 (2023-01-18)

  • Added a new task - Self Supervised Learning (SSL) and a separate training API for it.
  • Added new SOTA model - Gated Additive Tree Ensembles (GATE).
  • Added one SSL model - Denoising AutoEncoder.
  • Added lots of new tutorials and updated entire documentation.
  • Improved code documentation and type hints.
  • Separated a Model into separate Embedding, Backbone, and Head.
  • Refactored all models to separate Backbone as native PyTorch Model(nn.Module).
  • Refactored commonly used modules (layers, activations etc. to a common module).
  • Changed MixedDensityNetworks completely (breaking change). Now MDN is a head you can use with any model.
  • Enabled a low level api for training model.
  • Enabled saving and loading of datamodule.
  • Added trainer_kwargs to pass any trainer argument PyTorch Lightning supports.
  • Added Early Stopping and Model Checkpoint kwargs to use all the arguments in PyTorch Lightining.
  • Enabled prediction using GPUs in predict method.
  • Added reset_model to reset model weights to random.
  • Added many save and load functions including ONNX(experimental).
  • Added random seed as a parameter.
  • Switched over completely to Rich progressbars from tqdm.
  • Fixed class-balancing / mu propagation and set default to 1.0.
  • Added PyTorch Profiler for debugging performance issues.
  • Fixed bugs with FTTransformer and TabTransformer.
  • Updated MixedDensityNetworks fixing a bug with lambda_pi.
  • Many CI/CD improvements including complete integration with GitHub Actions.
  • Upgraded all dependencies, including PyTorch Lightning, pandas, to latest versions and added dependabot to manage it going forward.
  • Added pre-commit to ensure code integrity and standardization.

0.7.0 (2021-09-01)

  • Implemented TabTransformer and FTTransformer models
  • Included capability to save a model using GPU an load in CPU
  • Made the temp folder pytorch tabular specific to avoid conflicts with other tmp folders.
  • Some bug fixes
  • Edited an error out of Advanced Tutorial in docs

0.6.0 (2021-06-21)

  • Upgraded versions of PyTorch Lightning to 1.3.6
  • Changed the way gpus parameter is handled to avoid confusion. None is CPU, -1 is all GPUs, int is number of GPUs
  • Added a few more Trainer Params like deterministic, auto_select_gpus
  • Some bug fixes and changes to docs
  • Added seed_everything to the fit method to ensure reproducibility
  • Refactored data_aware_initialization to be part of the BaseModel. Inherited Models can override the method to implement data aware initialization techniques

0.5.0 (2021-03-18)

  • Added more documentation
  • Added Zenodo citation

0.4.0 (2021-03-18)

  • Added AutoInt Model
  • Added Mixture Density Networks
  • Refactored the classes to separate backbones from the head of the models
  • Changed the saving and loading model to work for custom parameters that you pass in fit

0.3.0 (2021-03-02)

  • Fixed a bug on inference

0.2.0 (2021-02-07)

  • Fixed an issue with torch.clip and torch version
  • Fixed an issue with gpus parameter in TrainerConfig, by setting default value to None for CPU
  • Added feature to use custom sampler in the training dataloader
  • Updated documentation and added a new tutorial for imbalanced classification

0.0.1 (2021-01-26)

  • First release on PyPI.