This desktop application is designed to experiment with source code clustering techniques within the context of Model-Driven Engineering (MDE). The tool aids in identifying high-level concepts from legacy systems' source code, facilitating their modernization and improving maintainability.
- Source code clustering: Implement various clustering techniques to analyze and group similar source code entities.
- Metrics: Calculate internal and external metrics to evaluate clustering effectiveness.
- Preprocessing scenarios: Support for three preprocessing scenarios:
- WoPP: Without Preprocessing.
- PPwS: Preprocessing with Stemming.
- PPWoS: Preprocessing Without Stemming.
- Noisy Dataset Handling: Evaluate clustering effectiveness on both normal and noisy datasets.
The results for the paper "Model-Driven Engineering and Machine Learning for Enhancing Legacy Systems Modernization" can be downloaded from the link below.