/awesome-machine-learning-on-source-code

Interesting links & research papers related to Machine Learning applied to source code

Awesome Machine Learning On Source Code

A curated list of awesome machine learning frameworks and algorithms that work on top of source code. Inspired by Awesome Machine Learning.

If you want to contribute to this list (please do), send a pull request or contact source{d} @srcd_.

Also, a listed repository should be deprecated if:

  • Repository's owner explicitly say that "this library is not maintained".
  • Not committed for long time (2~3 years).

Table of Contents

Digests

Learning from "Big Code" A Survey of Machine Learning for Big Code and Naturalness

Articles

Machine learning articles about processing source code

Frameworks

Machine Learning frameworks/libraries

  • Differentiable Neural Computer (DNC) - A TensorFlow implementation of the Differentiable Neural Computer.
  • sourced.ml - Abstracts feature extraction from source code syntax trees and working with models
  • vecino - Discovering similar Git repositories
  • enry - Insanely fast file based programming language detector.
  • Naturalize - Naturalize is a language agnostic framework for learning coding conventions from a codebase and then expoiting this information for suggesting better identifier names and formatting changes in the code.
  • Extreme Source Code Summarization - A convolutional attention neural network that learns to summarize source code into a short method name-like summary by just looking at the source code tokens.
  • Summarizing Source Code using a Neural Attention Model - CODE-NN , uses LSTM networks with attention to produce sentences that describe C# code snippets and SQL queries from StackOverflow. Torch over C#/SQL
  • Probabilistic API Miner - PAM is a near parameter-free probabilistic algorithm for mining the most interesting API patterns from a list of API call sequences.
  • Interesting Sequence Miner - ISM is a novel algorithm that mines the most interesting sequences under a probabilistic model. It is able to efficiently infer interesting sequences directly from the database.
  • TASSAL - TASSAL is a tool for the automatic summarization of source code using autofolding. Autofolding automatically creates a summary of a source code file by folding non-essential code and comment blocks.
  • JNice2Predict - Efficient and scalable open-source framework for structured prediction, enabling one to build new statistical engines more quickly.

Frameworks for preprocessing source code, etc.

  • go-git - A highly extensible Git implementation in pure Go.
  • bblfsh - A self-hosted server for source code parsing
  • engine - source{d}, a scalable and distributed data retrieval pipeline for source code
  • minhashcuda - source{d}, to efficiently remove duplicates of repositories on nBOW model
  • kmcuda - source{d}, to cluster and to search for nearest neighbors in dense space
  • wmd-relax - source{d}, to find nearest neighbors at Word Mover's Distance - to find nearest repositories
  • swivel-spark-prep - Distributed equivalent of prep.py and fastprep from Swivel using Apache Spark.
  • hercules - Calculates the lines burnout stats in a Git repository

Source code datasets

Credits

  • A lot of references and articles were taken from mast-group