Graph Sets
Hand-curated graph datasets for fast experimentation with graph neural networks. Loaders return PyTorch-ready tensors so you can focus on modeling instead of wrangling benchmark data.
Installation
pip install graphsets
Usage
from graphsets import load_cora
# directory containing cora.content and cora.cites from the standard Cora release
data_dir = "/path/to/cora"
features, adj, labels, idx_train, idx_val, idx_test = load_cora(data_dir)
What you get
- Features: float tensor of node attributes (row-normalized).
- Adjacency: symmetric 0/1 tensor built from
cora.cites. - Labels: integer class ids matching the original paper labels.
- Splits: simple train/val/test indices (140/300/1000 nodes) for quick baselines.
Datasets
cora— citation network commonly used for GCN/GAT benchmarks.
1 maintainer
Metadata
1 maintainer
Release files for graphsets 0.0.12
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 |
|---|---|---|---|---|
| graphsets-0.0.12.tar.gz | 5.6 kB | Without provenance | Details for graphsets-0.0.12.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| graphsets-0.0.12-py3-none-any.whl | Python 3 | none | any | Details for graphsets-0.0.12-py3-none-any.whl |
Total release size: 10.3 kB
Release files / graphsets-0.0.12.tar.gz
| Download URL | graphsets-0.0.12.tar.gz |
|---|---|
| Size | 5.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
152c8bca2a6f05731db34ffb70c0204dd451663cca0f7d0f1ef998de8f2e0ae9
|
|
BLAKE2b-256 checksum How to use checksums |
ea58b14c4100cef426fd0c3845fb7f194571f4de6160c3c94428206272ef6508
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|
Release files / graphsets-0.0.12-py3-none-any.whl
| Download URL | graphsets-0.0.12-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
416720db26a7bf992c036cd41fbd622032e50e7ee33cea04f95ddc6815c2db1a
|
|
BLAKE2b-256 checksum How to use checksums |
ecd4c98f09380d7d4b4aeace298400ee7498e9433bb3f2a3e05c996f9f45ef44
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|
Security for graphsets 0.0.12
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.
