Skip to main content

An Interface between the Runner Neural Network Energy Representation (RuNNer) and the Atomic Simulation Environment (ASE).

Project description

runnerase

pipeline status Documentation

An Interface between the Runner Neural Network Energy Representation (RuNNer) and the Atomic Simulation Environment (ASE).

[!WARNING] DEPRECATED The code in this repo is unmaintained. It works only for RuNNer <= v1.3. For RuNNer >= v2.0, please visit RuNNerASE 2.0.

Key Features

  • readers and writers for all RuNNer file formats.
  • Runner, an ASE calculator class for managing the RuNNer workflow.
  • SymmetryFunction/SymmetryFunctionSet, classes for generating and manipulating atom-centered symmetry functions.
  • A plotting library for generating nice figures from RuNNer data.
  • storage classes for atom-centered symmetry function values, weights and scaling data of the atomic neural networks, the split between training and testing set, and the results of a RuNNer fit.
  • Customizable automatic training of a full potential from a dataset.
  • Active learning module.
  • Connection to LAMMPS for large-scale simulations.
  • Ability to submit and retrieve jobs to the SLURM queueing system.

Installation

The package can be easily installed via pip. If they are not available, the dependencies ASE, numpy and scipy will be automatically installed. The use of the optional dependency tqdm (progressbar) is highly recommended for following the calculation progress.

$ pip install runnerase[progressbar]

Please check out our documentation for further information!

Questions, Contributions, Suggestions

Everyone is warmly invited to open issues and merge requests here on Gitlab or contact the developer.

Credits

This software is an extension of the Atomic Simulation Environment (ASE).

The code is written and maintained by Alexander Knoll - @aknoll - alexknoll@mailbox.org.

License

This software is distributed under the GPLv3. For details, see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

runnerase-1.1.0.tar.gz (104.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

runnerase-1.1.0-py3-none-any.whl (115.3 kB view details)

Uploaded Python 3

File details

Details for the file runnerase-1.1.0.tar.gz.

File metadata

  • Download URL: runnerase-1.1.0.tar.gz
  • Upload date:
  • Size: 104.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.19

File hashes

Hashes for runnerase-1.1.0.tar.gz
Algorithm Hash digest
SHA256 ff95b9f19874adf28b24e6e2d086d78027888ece86d84e1dc5e67af8dcbe8cbc
MD5 d49700fdb1977bb3ce2a56ffea456c2a
BLAKE2b-256 2f233cdaf05d632acc15657bbd134afff14b021f3156cedde5d97f36f4ab6fcd

See more details on using hashes here.

File details

Details for the file runnerase-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: runnerase-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 115.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.19

File hashes

Hashes for runnerase-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d505439bbc16e1ad1853961fc89ac3b0065005d10f7395c8a8d895774fb8d29f
MD5 ed65a9954004fe16736b700a7fd1c841
BLAKE2b-256 a8f535e6d82d5492bb776edfcd403b53b87e21f74b1dfc95e56fb69b2afd82df

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page