A lightweight utility library for deep learning and graph-based research workflows — including configuration management, visualization, file I/O, model saving/loading, and evaluation utilities.
Requirements
- Python ≥ 3.8
- PyTorch ≥ 1.12
Install via pip:
python -m pip install the_utilsFor detailed documentation, see the_utils_docs.
Example:
from the_utils import evaluate_from_embed_file
from the_utils import save_to_csv_files
method_name='orderedgnn'
data_name='texas'
clustering_res, classification_res = evaluate_from_embed_file(
f'{data_name}_{method_name}_embeds.pth',
f'{data_name}_data.pth',
save_path='./save/',
)
insert_info = {'data': data_name, 'method': method_name,}
save_to_csv_files(clustering_res, insert_info, 'clutering.csv')
save_to_csv_files(classification_res, insert_info, 'classification.csv')Dependencies are listed in:
- requirements.txt
- requirements-dev.txt
- pyproject.toml (see
dependencies)
We welcome contributions of any kind — bug fixes, enhancements, or new utilities. Please refer to the CONTRIBUTING.md for setup instructions and guidelines.