A Library for Representing Python Programs as Graphs for Machine Learning

TL;DR

This paper introduces an open source Python library that constructs various graph representations of Python programs, facilitating machine learning research on code by combining control-flow, data-flow, and syntactic information.

Contribution

The paper presents a novel library, python_graphs, that enables static analysis and graph construction of Python programs for machine learning applications.

Findings

Successfully applied to millions of programming submissions

Supports multiple graph types including control-flow and data-flow

Demonstrates utility in machine learning research on code

Abstract

Graph representations of programs are commonly a central element of machine learning for code research. We introduce an open source Python library python_graphs that applies static analysis to construct graph representations of Python programs suitable for training machine learning models. Our library admits the construction of control-flow graphs, data-flow graphs, and composite ``program graphs'' that combine control-flow, data-flow, syntactic, and lexical information about a program. We present the capabilities and limitations of the library, perform a case study applying the library to millions of competitive programming submissions, and showcase the library's utility for machine learning research.