Replication Package for the Master's Thesis: Integrating Structural and Semantic Analysis for Code Smell Refactoring Prediction

Abstract

This repository contains the official replication package, automation scripts, and machine learning pipelines developed for the Master's Thesis: "Integrating Structural and Semantic Analysis for Code Smell Refactoring Prediction" (Università degli Studi di Milano-Bicocca, 2026). The project bridges traditional static code analysis with advanced embedding representation learning to predict refactoring interventions on code-smelly methods. The predictive framework models a supervised binary classification task across 10 distinct target refactoring operations. Dataset & Feature Space OverviewThe underlying dataset is made of open-source Java systems. Full list included in dataset.md - Tabular Metrics: Implementation smells mined via DesigniteJava alongside a comprehensive suite of 54 object-oriented metrics computed by the CK Analysis Tool.- Control Flow Topologies (Option A): Granular Control Flow Graphs (CFGs) parsed via Joern and translated into 64-dimensional dense vectors using the LINE graph embedding algorithm.- Joint Syntactic-Semantic Bytecode (Option B): Normalized token streams and Program Dependence Graphs (PDGs) extracted directly from the compiler intermediate representation layer (Jimple bytecode) via GraphCode2Vec. Replication Artifacts IncludedThe package is organized to ensure complete scientific reproducibility and includes: - src/core/: Core execution modules for chronological commit mining (RefactoringMiner alignment), smell resolution detection, and target label processing.- src/runners/: Batch automation wrappers and full Linux/WSL execution pipelines (Joern parsing, edge list generation, and node embedding training).- src/utils/: Feature engineering helpers, mean-pooling scripts for graph node aggregation, and multi-source CSV mergers.- src/models_pipeline/: Machine learning workflows implementing dataset balancing/scaling, Bayesian hyperparameter tuning, model training (Logistic Regression, SVM, XGBoost, Deep Neural Networks), and Late Fusion stacking ensembles, along with ablation and explainability outputs (ROC, Calibration, UMAP, SHAP). For detailed environment setup, dependency configurations (such as Joern, GraphCode2Vec, RefactoringMiner, CK, and Designite), and step-by-step reproduction instructions, please refer to the included README.md file. Release Notes / Changelog (v2): - removed venv folder from code.zip