https://github.com/sriniiyer/codenn

Summarizing Source Code using a Neural Attention Model - CODENN
https://github.com/sriniiyer/codenn

Last synced: 5 days ago
JSON representation

Summarizing Source Code using a Neural Attention Model - CODENN

• Host: GitHub
• URL: https://github.com/sriniiyer/codenn
• Owner: sriniiyer
• License: mit
• Created: 2016-06-06T22:01:31.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2023-01-23T21:04:53.000Z (almost 3 years ago)
• Last Synced: 2024-04-20T08:34:49.154Z (over 1 year ago)
• Language: Python
• Size: 16.8 MB
• Stars: 235
• Watchers: 11
• Forks: 73
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-machine-learning-on-source-code - 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 (Software)
• awesome-machine-learning-on-source-code - 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 (Software)
• awesome-machine-learning-on-source-code - 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 (Software)

README

          


**Run CODENN**

See details of CODENN in our paper

Summarizing Source Code using a Neural Attention Model (https://github.com/sriniiyer/codenn/blob/master/summarizing_source_code.pdf)

Requirements

* Torch (http://torch.ch/docs/getting-started.html)

* Cutorch

* antlr4 for parsing C# (pip install antlr4-python2-runtime)

Setup environment

`export PYTHONPATH=~/codenn/src/:~/codenn/src/sqlparse`

`export CODENN_DIR=~/codenn/`

`export CODENN_WORK=./workdir`

Build both csharp and sql datasets

Install modified sqlparse

`cd src/sqlparse/`

`sudo python setup.py install`

Build datasets

`cd src/model`

`./buildData.sh`

Train codenn models and predict on test set

`./run.sh {sql|csharp}`