What's Changed
* Development was moved to GitHub.
* Supported Python versions, operating systems, and dependencies have been upgraded. Thank you to Aislinn Handley.
* The structure of DataFrames in `SampleSet`, as well as methods contained within, were significantly changed, eliminating things that are no longer used and introducing new features.
* Information present in saved models was expanded. Thank you to Aislinn Handley.
* Static synthesis was reworked to provide better ground truth tracking for both single- and multi-isotope (i.e., mixture) spectra. Thank you to Paul Thelen for providing category mappings.
* Static synthesis now returns net, background, and gross spectra.
* Neutron synthesis, which was part of static synthesis, was removed (possibly returning in a future release).
* Mixture synthesis was removed from static synthesis and implemented as a preliminary step of "seed mixing" which produces seeds you pass to a static synthesizer. Thank you to alanjvano
* Expanded tests for regression checking throughout the package, notably as it applies to getting labels and predictions.
* Initial implementation of a Multi-Event Classifier. Thank you to Nathan Price.
* Modification of `MlpClassifier` to support source spectra concatenated with background spectra as input. Thank you to Nathan Price.
* Basic seed synthesis utilizing GADRAS Inject was introduced.
* Added an anomaly detection algorithm for use on sequences of spectra.
* Added visualizations and metrics were added. Thank you tylerganter.
* Added methods for describing and comparing `SampleSet`s. Thank you to anbusto and lcross-sandia.
* TensorFlow implementation of Poisson-Bayes classifier refactored. Thank you to lcross-sandia.
* Added methods for limited adding and subtracting of `SampleSet`s.
* A semi-supervised neural network approach using sparsemax activation and providing out-of-distribution detection was added based on alanjvano's thesis work (https://dx.doi.org/10.7302/7200)
* Expanded unit testing (and coverage), most notably for `visualize` module. Thank you to anbusto
* Examples and linting checks added to GitHub Actions workflows. Thank you to anbusto and alanjvano
Moving forward, with development having moved to GitHub, changes will be more easily enumerated here and more detailed credit will be given to authors.
Thank you again to everyone who contributed to this release; see the `pyproject.toml` for all authors.
**Full Changelog**: https://github.com/sandialabs/PyRIID/compare/v1.0.2...v2.0.0