GitHub / VIGINUM-FR / D3lta
A Python implementation of the D3lta algorithm for duplicated textual content detection
JSON API: https://repos.data.code.gouv.fr/api/v1/hosts/GitHub/repositories/VIGINUM-FR%2FD3lta
Stars: 49
Forks: 7
Open issues: 2
License: mit
Language: Jupyter Notebook
Size: 20.8 MB
Dependencies parsed at:
13
Created at: 8 months ago
Updated at: 20 days ago
Pushed at: 20 days ago
Last synced at: about 17 hours ago
Topics: coordination-detection, embeddings, python, semantic-similarity, social-network-analysis, text-analysis
pyproject.toml
pypi
- demoji 1.1.0
- faiss-cpu 1.9.0.post1
- fasttext 0.9.3
- gensim 4.3.3
- networkx 2.8.8
- pandas 2.2.3
- polyleven 0.8
- python ^3.10
- scipy 1.12.0
- tensorflow 2.18.0
- tensorflow-hub 0.16.1
- tensorflow-text 2.18.1
- tqdm 4.67.1
setup.py
pypi