Cooldata - A Large-Scale Electronics Cooling 3D Flow Field Dataset
Cooldata is a large-scale electronics cooling dataset, containing over 60k stationary 3D flow fields for a diverse set of geometries, simulated with the commercial solver Simcenter STAR-CCM+. This library can be used to acccess the dataset and streamline its application in machine learning tasks.
Find the documentation at cooldata.readthedocs.io.
Features
- Data Storage: Organized in folders containing
.cgnsfiles for compatibility with computational fluid dynamics tools. - PyVista Integration: Access to dataset samples as PyVista objects for easy 3D visualization and manipulation.
- Graph Neural Network Support:
- DGL Support:
- Surface and volume data in mesh format.
- 3D visualization of samples and predictions.
- L2 loss computation and aggregate force evaluation for model training.
- PyG Support: Implementing functionalities similar to DGL.
- DGL Support:
- Hugging Face Integration: Direct dataset loading from Hugging Face.
- Voxelized Flow Field Support: Facilitates image processing-based ML approaches.
- Comprehensive Metadata Accessibility: All metadata is accessible through the library.
Installation
Run
pip install cooldata
If you want to use the DGL support, you also need to install the DGL library, as documented here.
Example Usage
See the examples folder for a detailed example of how to use the library.
Roadmap
- Re-meshing with Random Point Sampling
- Inference of Surface Quantities from Volumetric Predictions
1 maintainer
Metadata
1 maintainer
Release files for cooldata 1.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| cooldata-1.0.2.tar.gz | 20.5 kB | Without provenance | Details for cooldata-1.0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| cooldata-1.0.2-py3-none-any.whl | Python 3 | none | any | Details for cooldata-1.0.2-py3-none-any.whl |
Total release size: 44.8 kB
Release files / cooldata-1.0.2.tar.gz
| Download URL | cooldata-1.0.2.tar.gz |
|---|---|
| Size | 20.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3d12f353b0eb89bc31646f884c09a8fe5b8fdd19bd08dc34b6798fb3f7435c58
|
|
BLAKE2b-256 checksum How to use checksums |
b486a4f7046b6c0b90d4f949a3ee07dd936f17bc9e6b9f9c880282adc10d9a6c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Release files / cooldata-1.0.2-py3-none-any.whl
| Download URL | cooldata-1.0.2-py3-none-any.whl |
|---|---|
| Size | 24.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
35900dd33e671239212356e988663ddd7a186dfdc1edc74915b04fc097eb3951
|
|
BLAKE2b-256 checksum How to use checksums |
19c8dd9397184251e0a7a78788a5c2f0208c15387615db09e75652b74b3e327e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.4
|
Security for cooldata 1.0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
