martysai / source-code-summarization

Transformer-based approaches for an efficient docstrings generation on a piece of Python's code.

Source Code Summarization

Currently observed approaches:

Method	Source	Paper
Neural Code Sum	repo	arxiv
Tree Transformer	repo	openreview
TransCoder	repo	arxiv

Environment setup:

conda create -n scs python=3.7
conda activate scs
pip install -r requirements.txt

Install linter with:

pip install flake8

To run formatter execute from the source folder:

bash scripts/yapf.sh