OpenQDC - Open Quantum Data Commons
OpenQDC is an open-source hub of ML-ready quantum datasets. It contains 40+ quantum mechanics (QM) datasets, covering 1.5 billion geometrics across 70 atom species and 250+ QM methods that are curated and consolidated into a single, accessible hub. All of the datasets are available for download through just one line of code.
Use mamba:
mamba install -c conda-forge openqdcTips: You can replace mamba by conda.
Note: We highly recommend using a Conda Python distribution to install OpenQDC. The package is also pip installable:
pip install openqdcgit clone https://github.com/valence-labs/openQDC.git
cd openQDC
# use mamba/conda
mamba env create -n openqdc -f env.yml
pip install -e .You can run tests locally with:
pytestYou can build the documentation locally with:
mkdocs serveA command line interface is available to download datasets or see which dataset is available, for more information please run openqdc --help.
# Display the available datasets
openqdc datasets
# Display the help message for the download command
openqdc download --help
# Download the Spice and QMugs dataset
openqdc download Spice QMugsThe CI runs tests and performs code quality checks for the following combinations:
- The three major platforms: Windows, OSX and Linux.
- The four latest Python versions.
main |
|
|---|---|
| Lib build & Testing |  |
| Code Sanity (linting and type analysis) |  |
| Documentation Build |  |
| Pre-Commit |  |
All data presented in the OpenQDC are already published in scientific journals, full reference to the respective paper is attached to each dataset class. When citing data obtained from OpenQDC, you should cite both the original paper(s) the data come from and our paper on OpenQDC itself.
Stay tuned for the release of the paper