Documentation Tests License Python
dftio is to assist machine learning communities in transcribing and manipulating DFT output into a format that is easy to read or used by machine learning models.
dftio uses multiprocessing to paralleling the processing, and provide a standard dataset class that reads the processed dataset directly.
The easiest way to install dftio is using the provided installation script:
# CPU version (default) ./install.sh # Or for GPU with CUDA 12.1 ./install.sh cu121
If you prefer manual installation:
# Install UV if you haven't already pip install uv # Install dftio (CPU version) uv sync # Or for GPU version uv sync --find-links https://data.pyg.org/whl/torch-2.5.0+cu121.html
pip install dftio
Note: dftio depends on torch-scatter which requires special handling. The install script automatically manages this for you.
Current:
| Package | Structure | Eigenvalues | Hamiltonian | Density matrix | Overlap matrix | Total energy |
|---|---|---|---|---|---|---|
| ABACUS | √ | √ | √ | √ | √ | √ |
| RESCU | √ | √ | √ | |||
| SIESTA | √ | √ | √ | √ | ||
| Gaussian | √ | √ | √ | √ | ||
| VASP | √ | √ | √ | |||
| PYATB | √ | √ |
Ongoing:
- Charge Density
- Atomic Orbitals
- Wave Function
- Wave Function Coefficients
- Total Energy
To parse the DFT output files into readable data format, user can follows:
usage: dftio parse [-h] [-ll {DEBUG,3,INFO,2,WARNING,1,ERROR,0}] [-lp LOG_PATH] [-m MODE] [-n NUM_WORKERS] [-r ROOT] [-p PREFIX] [-o OUTROOT] [-f FORMAT] [-ham] [-ovp] [-dm] [-eig] [-min BAND_INDEX_MIN]
options:
-h, --help show this help message and exit
-ll {DEBUG,3,INFO,2,WARNING,1,ERROR,0}, --log-level {DEBUG,3,INFO,2,WARNING,1,ERROR,0}
set verbosity level by string or number, 0=ERROR, 1=WARNING, 2=INFO and 3=DEBUG (default: INFO)
-lp LOG_PATH, --log-path LOG_PATH
set log file to log messages to disk, if not specified, the logs will only be output to console (default: None)
-m MODE, --mode MODE The name of the DFT software, currently support abacus/rescu/siesta/gaussian/pyatb (default: abacus)
-n NUM_WORKERS, --num_workers NUM_WORKERS
The number of workers used to parse the dataset. (For n>1, we use the multiprocessing to accelerate io.) (default: 1)
-r ROOT, --root ROOT The root directory of the DFT files. (default: ./)
-p PREFIX, --prefix PREFIX
The prefix of the DFT files under root. (default: frame)
-o OUTROOT, --outroot OUTROOT
The output root directory. (default: ./)
-f FORMAT, --format FORMAT
The output file format, should be dat, ase or lmdb. (default: dat)
-ham, --hamiltonian Whether to parse the Hamiltonian matrix. (default: False)
-ovp, --overlap Whether to parse the Overlap matrix (default: False)
-dm, --density_matrix
Whether to parse the Density matrix (default: False)
-eig, --eigenvalue Whether to parse the kpoints and eigenvalues (default: False)
-min BAND_INDEX_MIN, --band_index_min BAND_INDEX_MIN
The initial band index for eigenvalues to save.(0-band_index_min) bands will be ignored! (default: 0)
-energy, --energy Whether to parse the total energy from DFT output (default: False)dftio is an open-source tool that calls for enthusiastic developers to contribute their talent. One can contribute through raising function requirement issues, or contact the current developer directly.
Qiangqiang Gu, Jijie Zou, Mingkang Liu, Zixi Gan, Zhanghao Zhouyin