Poraquê
Poraquê is a research code for electronic structure and machine learning on 3D scalar fields (external potential, charge density, kinetic energy density).
Status
| Area | State |
|---|---|
poraque.fields |
3D scalar fields (EXTCAR/CHGCAR/TAUCAR) on one shared grid |
poraque.fields.io |
Pluggable ingestion — VASP working; Quantum ESPRESSO and GPAW scaffolded |
poraque.ml |
Fourier Neural Operator pipeline, handles per-material grid shapes |
| Everything else | Legacy; being reorganized |
Scripts
# Validate the external-potential model against reference VASP EXTCAR files
python scripts/validate_vasp_data.py --fit-sigma --form-factor
# Train the two neural operators (EXTCAR -> CHGCAR, CHGCAR -> TAUCAR)
python scripts/train_fno.py --resolution 32 --epochs 200
Notes
plan/pi_fno.md— roadmap for the physics-informed operator (PI-FNO).plan/fno_physics.md— how KS-DFT and OF-DFT relate to what the two models learn.
Installation
git clone https://github.com/seixas-research/poraque.git
cd poraque
pip install -e .
License
Open source under the MIT License.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
poraque-26.8.7.tar.gz
(2.7 MB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
poraque-26.8.7-py3-none-any.whl
(181.0 kB
view details)
File details
Details for the file poraque-26.8.7.tar.gz.
File metadata
- Download URL: poraque-26.8.7.tar.gz
- Upload date:
- Size: 2.7 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
02b55b16513eb78fd56aa2740ba35b86b587cea2f8a7f75a78d91ab8230790c5
|
|
| MD5 |
bfdadf854fda00e052971aafea0f0fe0
|
|
| BLAKE2b-256 |
a5e251d3b8592ac8cac593f797d1ced7c4960aabcc3f7cc083c6d5cb556c992e
|
File details
Details for the file poraque-26.8.7-py3-none-any.whl.
File metadata
- Download URL: poraque-26.8.7-py3-none-any.whl
- Upload date:
- Size: 181.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
18159c146cdf273e8898c4d3cb85840ad3d54002d68e9a3f0d0c30801d9fafc2
|
|
| MD5 |
b824c136bc4728c046add5b93ca15d20
|
|
| BLAKE2b-256 |
75aac8519ce7843ff925568eb0fd6e702ff4022fef05c9631eeabf08c995eb25
|