How mcop81/optimise-transport-marchandise-ml works
Project type and purpose
• This is a full-stack web application built with Django (Python) that provides a UI for managing deliveries, trucks, chauffeurs and predicting delivery delays using a pre-trained Random Forest model.
• Key purpose: user registration/authentication, CRUD operations on deliveries/trucks/chauffeurs, map visualizations, and ML-based delay predictions.
File structure
• Top level:
• core/ – Django project configuration (settings.py, urls.py, wsgi.py, asgi.py)
• apps/ – Django “apps”:
– authentication/ (login, registration forms, views, URLs, models)
– home/ (delivery/truck management, map pages, ML integration)
– static/ (CSS/JS/images; Argon Dashboard theme)
– templates/ (layouts, includes, per-app HTML templates)
• media/ – user-uploaded files (if any)
• staticfiles/ – collected static assets
• Dockerfile, docker-compose.yml, nginx/ – containerization and reverse-proxy
• Procfile, runtime.txt, requirements.txt – deployment (Heroku) and dependencies
• core/models/*.pkl – serialized Random Forest ML models
README for additional insights
• Confirms SQLite usage in development, Django migrations, “home” app serves authenticated pages, “authentication” app handles user login/register.