veridevops/arqan.dataset

Code and datasets of thesis "Classification of Cyber-Security Requirements based on open datasets and GitHub harvesting"

github-security-issues

Code and datasets of thesis "Classification of Cyber-Security Requirements based on open datasets and GitHub harvesting"

Structure

• Models Training and Testing.ipynb - notebook with models
• language_detection.py - script that detect language of text using CLD2
• github_scraper.py - script that harvest issues and repositories from GitHub
• data:
• • security_terms.csv - list of security terms
• • repositories.csv - table with GitHub repositories and links that we used for harvesting
• • datasets - folder with 4 datasets for models training