aiida-mlip 0.1.0a1

machine learning interatomic potentials aiida plugin

aiida-mlip

machine learning interatomic potentials aiida plugin

This plugin is the default output of the AiiDA plugin cutter, intended to help developers get started with their AiiDA plugins.

Repository contents

• .github/: Github Actions configuration
  • ci.yml: runs tests, checks test coverage and builds documentation at every new commit
  • publish-on-pypi.yml: automatically deploy git tags to PyPI - just generate a PyPI API token for your PyPI account and add it to the pypi_token secret of your github repository
• aiida_mlip/: The main source code of the plugin package
  • data/: A new DiffParameters data class, used as input to the DiffCalculation CalcJob class
  • calculations.py: A new DiffCalculation CalcJob class
  • cli.py: Extensions of the verdi data command line interface for the DiffParameters class
  • helpers.py: Helpers for setting up an AiiDA code for diff automatically
  • parsers.py: A new Parser for the DiffCalculation
• docs/: A documentation template ready for publication on Read the Docs
• examples/: An example of how to submit a calculation using this plugin
• tests/: Basic regression tests using the pytest framework (submitting a calculation, ...). Install pip install -e .[testing] and run pytest.
• .gitignore: Telling git which files to ignore
• .pre-commit-config.yaml: Configuration of pre-commit hooks that sanitize coding style and check for syntax errors. Enable via pip install -e .[pre-commit] && pre-commit install
• .readthedocs.yml: Configuration of documentation build for Read the Docs
• LICENSE: License for your plugin
• README.md: This file
• conftest.py: Configuration of fixtures for pytest
• pyproject.toml: Python package metadata for registration on PyPI and the AiiDA plugin registry (including entry points)

See also the following video sequences from the 2019-05 AiiDA tutorial:

• run aiida-diff example calculation
• aiida-diff CalcJob plugin
• aiida-diff Parser plugin
• aiida-diff computer/code helpers
• aiida-diff input data (with validation)
• aiida-diff cli
• aiida-diff tests
• Adding your plugin to the registry
• pre-commit hooks

For more information, see the developer guide of your plugin.

Features

• Add input files using SinglefileData:

  SinglefileData = DataFactory('core.singlefile')
  inputs['file1'] = SinglefileData(file='/path/to/file1')
  inputs['file2'] = SinglefileData(file='/path/to/file2')
  

• Specify command line options via a python dictionary and DiffParameters:

  d = { 'ignore-case': True }
  DiffParameters = DataFactory('mlip')
  inputs['parameters'] = DiffParameters(dict=d)
  

• DiffParameters dictionaries are validated using voluptuous. Find out about supported options:

  DiffParameters = DataFactory('mlip')
  print(DiffParameters.schema.schema)
  

Installation

pip install aiida-mlip
verdi quicksetup  # better to set up a new profile
verdi plugin list aiida.calculations  # should now show your calclulation plugins

Usage

Here goes a complete example of how to submit a test calculation using this plugin.

A quick demo of how to submit a calculation:

verdi daemon start     # make sure the daemon is running
cd examples
./example_01.py        # run test calculation
verdi process list -a  # check record of calculation

The plugin also includes verdi commands to inspect its data types:

verdi data mlip list
verdi data mlip export <PK>

Development

1. Install poetry
2. (Optional) Create a virtual environment
3. Install aiida-mlip with dependencies:

git clone https://github.com/stfc/aiida-mlip
cd aiida-mlip
pip install --upgrade pip
poetry install --with pre-commit,dev,docs  # install extra dependencies
pre-commit install  # install pre-commit hooks
pytest -v  # discover and run all tests

See the developer guide for more information.

License

BSD 3-Clause License

Funding

Contributors to this project were funded by