v3.2.1

Release of code version 3.2.1

v3.2.0

New version 3.2.0 to incorporate domain of applicability approaches, updates to UQ plotting, many small bug fixes and updates

v3.1.7

Bug fixes for compatibility with python 3.10 (current standard for Google Colab)

v3.1.3

Changes since v3.1.2:

• Minor update to fix issue with model saving paths

v3.1.2

Changes since v3.1.1:

Updates to Tutorial 7 to fix issues with hosting models on Foundry/DLHub

A number of misc bug fixes

v3.1.1

Changes since v3.0.3:

Refinement of tutorials, addition of Tutorial 7, Colab links as badges added for easier use.

mastml_predictor module added to help streamline making predictions (with option to include error bars) on new test data.

Basic parallelization added, which is especially useful for speeding up nested CV runs with many inner splits.

EnsembleModel now handles ensembles of GPR and XGBoost models.

Numerous improvements to plotting, including new plots (QQ plot), better axis handling and error bars (RvE plot), plotting and stats separated per group if groups are specified.

Improvements to feature selection methods. EnsembleModelFeatureSelector includes dummy feature references, added SHAP-based selector

Added assessment of baseline tests like comparing metrics to predicting the data average or permuted data test

Many miscellaneous bug fixes.

v3.0.3

Updates since v3.0.1:

• Many small bug fixes
• Extensive run metadata now written to mastml metadata json file for each run
• Error bars added on RvE plots
• Now writes more data files, such as Xextra and leave out data, to files
• Cleans up non-best models to conserve storage space
• More flexible metrics to be used to discern best models in data splitter test
• Enhancements to LeaveOutClusterCV and EnsembleModelFeatureSelector routines

v3.0.1

MAST-ML version 3.x Major Updates (starting with v3.0.1)

• MAST-ML no longer uses an input file. The core functionality and workflow of MAST-ML has been rewritten to be more conducive to use in a Jupyter notebook environment. This major change has made the code more modular and transparent, and we believe more intuitive and easier to use in a research setting. The last version of MAST-ML to have input file support was version 2.0.20 on PyPi.

• Each component of MAST-ML can be run in a Jupyter notebook environment, either locally or through a cloud-based service like Google Colab. As a result, we have completely reworked our use-case tutorials and examples. All of these MAST-ML tutorials are in the form of Jupyter notebooks and can be found in the mastml/examples folder on Github.

• An active part of improving MAST-ML is to provide an automated, quantitative analysis of model domain assessement and model prediction uncertainty quantification (UQ). Version 3.x of MAST-ML includes more detailed implementation of model UQ using new and established techniques.