Riid

What's Changed

Enhancements

Data

* Added data converters for some community datasets by tymorrow in https://github.com/sandialabs/PyRIID/pull/49 and https://github.com/sandialabs/PyRIID/pull/58
* Added `SampleSet.SpectraType` enum for better tracking of data state and enforcement in synthesizers by alanjvano tymorrow in https://github.com/sandialabs/PyRIID/pull/57
* Added `SampleSet.get_confidence()` method by alanjvano tymorrow in https://github.com/sandialabs/PyRIID/pull/57
* This method provides basic support for computing reconstruction-based confidence measures. It is intended as a post-processing step following model inference.
* Added `SampleSet.to_json()` and `read_json()` for convenient reading/writing of spectral data from/to JSON by tymorrow in https://github.com/sandialabs/PyRIID/pull/63

Synthesis

* Refactored static and seed synthesis output by tymorrow in https://github.com/sandialabs/PyRIID/pull/59 and https://github.com/sandialabs/PyRIID/pull/66
* Refactored `StaticSynthesizer` SNR and live time sampling by alanjvano tymorrow in https://github.com/sandialabs/PyRIID/pull/57
* Added "seed health" checks to synthesizers to better validate seeds before generating data by tymorrow in https://github.com/sandialabs/PyRIID/pull/65
* A health check is performed by default, but were later made optional in https://github.com/sandialabs/PyRIID/pull/40 so that you are able to intentionally perform synthesis with bad seeds for research purposes.
* Seed synthesis now calculates dead time, both as a convenience to the user as well as to support the health check by tymorrow https://github.com/sandialabs/PyRIID/pull/40
* Seed synthesis now supports specifying whether to include of pile-up in the GADRAS Inject by tymorrow in https://github.com/sandialabs/PyRIID/pull/40 (previously, whether pile-up could be included, like many parameters, was determined by the value in `Detector.dat`)
* Real time and distance are now properly passed through some synthesizers by alanjvano tymorrow in https://github.com/sandialabs/PyRIID/pull/40

Models

* Numerous `LabelProportionEstimator` improvements by alanjvano in https://github.com/sandialabs/PyRIID/pull/42 and https://github.com/sandialabs/PyRIID/pull/57
* Added two versions of the ARAD autoencoder as standalone TensorFlow models along with direct, optional PyRIID integration by tymorrow alanjvano in https://github.com/sandialabs/PyRIID/pull/64 (special thanks to Dr. James Ghawaly)
* Added random sampling of seed synthesizer configurations to enable specifications of variation in detector, environment, and source in a single YAML file by tymorrow alanjvano lcross-sandia in https://github.com/sandialabs/PyRIID/pull/40
* Added `ARADLatentPredictor` for performing prediction tasks from an ARAD model's latent space by tymorrow alanjvano in https://github.com/sandialabs/PyRIID/pull/40.

Docs

* Numerous improvements to docstrings and docs by tymorrow in https://github.com/sandialabs/PyRIID/pull/48

Bug fixes

* Add missing support for GADRAS 18. by tymorrow in https://github.com/sandialabs/PyRIID/pull/46
* Fixed `pyproject.toml` to find subpackages so publishing to PyPI does not produce technically broken releases by tymorrow in https://github.com/sandialabs/PyRIID/pull/61
* Fixed typo for areal density info column by tymorrow in https://github.com/sandialabs/PyRIID/pull/62
* Fixed `get_distribution_values()` 'list' type. by tymorrow in https://github.com/sandialabs/PyRIID/pull/60
* Fixed bug where neural net fitting was resorting source columns before training by alanjvano tymorrow in https://github.com/sandialabs/PyRIID/pull/57

Additional Notes

* A consequence of Apple's switch to ARM-base M* processors is that TensorFlow has stopped putting pre-built wheels on PyPI targeting MacOS with Intel processors. This means if you have a Mac with an Intel processor, this is likely the last version of PyRIID for you.

**Full Changelog**: https://github.com/sandialabs/PyRIID/compare/v2.0.0...v2.1.0

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

This release contains the following change:

- `PassbySynthesizer` now looks at the proper property to check for the presence of a background seed.

Full Changelog: https://github.com/sandialabs/PyRIID/compare/v1.0.1...v1.0.2

This release contains the following changes:

- Limits the `h5py` dependency version to < 3.0.0
- Adds support to load some newer `.smpl` files
- Changes the way the Python version is checked

**Full Changelog**: https://github.com/sandialabs/PyRIID/compare/v1.0.0...v1.0.1