Version 0.2.0

• add type hint for all codes
• rewrite model and parameter modules to simplify them
• add more docstring for undocumented class and functions

Version 0.1.7

• Add GitHub Actions
• Update README

Version 0.1.6

• bug fix of version 0.1.5 in which a *.h file is forgotten to be included in the PyPI sdist

Version 0.1.5

• add neighborlist utility, making NN model independent on kimpy
• add calculator to deal with multiple species for NN model
• update dropout layer to be compatible with the pytorch1.3

Version 0.1.4

• add support for the geodesic Levenberg-Marquardt minimization algorithm

• add command line tool model to inquire available parameters of KIM model

Version 0.1.3

• add RMSE and Fisher information analyzers
• allow configuration weight for ML models
• add write optimizer state dictionary for ML models
• combine functions generate_training_fingerprints() and generate_test_fingerprints() of descriptor to generate_fingerprints() (supporting passing mean and stdev file)
• rewrite symmetry descriptors to share with KIM driver

Version 0.1.2

• MPI parallelization for physics-based models
• reorganize machine learning related files
• various bug fixes
• API changes
  • class DataSet renamed to Dataset
  • class Calculator moved to module calculators from module calculator

Version 0.1.1

• KLIFF available from PyPI now. Using $pip install kliff to install.

• Use SW model from the KIM website in tutorial.

• Format code with black.