0.4.0

This version includes a brand-new polarizability model based on a graph neural network architecture!

New Features

• PotGNN, a polarizability model based on a graph neural network architecture and implemented using PyTorch and PyTorch-Geometric.
  • ramannoodle.dataset.torch.PolarizabilityDataset for training and evaluating PotGNN d118aee
  • ramannoodle.pmodel.torch.train module for convenient training of PotGNN. b24a7a4
• [torch] install options for pip. Installing ramannoodle with these options (after installing the requisite PyTorch packages) gives access to PyTorch model functionality. 6a6a4c2
• read_structure_and_polarizability function for vasprun.xml files. 738d6f4

API Changes

• Renamed UsageError toUserError b7b08dd
• Renamed most *utils modules to simply utils. 4c67d49
• Renamed globals module to constants to avoid conflicts with the build-in globals() function
• Renamed polarizability package to pmodel 7aa554b

Enhancements and Bugfixes

• Added robot.txt for documentation 7984559
• Exception is now raised when filepaths parameters are empty (filepaths=[]) 10ce3ed
• Public API is now exposed from the root package. 7844905
• Replaced np.close(...).all() with np.allclose(...) 4ac7389
• Added a progress bar for Trajectory.get_spectrum, which can take a while depending on the speed of the provided polarizability model 6c0567c

Documentation

• Cleaned up documentation
• Updated installation guide and citation in README.
• Added machine learning tutorial