Replication package for: Battling the Skills Gap: Identification of Java Knowledge Units through Machine Learning

Replication package containing: Dataset with all the Java files used for training the binary classifiers Jupyter Notebook for training various ML models using cross-validation Python program that scans git repositories and extracts detected Knowledge Units (KUs) All the trained ML models (trained using the included notebook) Dataset with all the Java files and necessary Python scripts used for evaluating the sliding window technique's performance