Embedding Java Classes with code2vec - Java Datasets

This is a collection of Java class classification datasets (i.e., classify a class into one of a set of categories), collected for the research work 'Embedding Java Classes with code2vec: Improvements from Variable Obfuscation'. These are shared for further research in static code analysis tasks (malware classification, author attribution, etc). Obfuscation & Pipeline Code: Download code2vec Models: Download