Comment-based codebase refining framework
Project description
Code for "Unsupervised and Supervised Co-learning for Codebase Mining and its Application in Code Search"
This repo contains the source code introduced in our paper.
Comment-based Codebase Refining (COCORF)
COCORF is a Python3 library for filtering query-appropriate text to build high-quality code search datasets.
It consists of two filters: a rule-based filer and a model-based filter (Pytorch required).
Currently, COCORF should be used with GPU-enabled Pytorch.
Installation
We have uploaded COCORF to Python Package Index (PyPi) and you can install it by the following command:
pip install cocorf
You can also clone this repo and install directly with the following command:
pip install -r requirements.txt
python setup.py install
Besides, COCORF should be used with GPU-enabled Pytorch. You can refer to https://pytorch.org/get-started/locally/ to install Pytorch. Pytorch 1.3 is required (Pytorch 1.3 does not support Python 3.8+).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file cocorf-0.1.tar.gz.
File metadata
- Download URL: cocorf-0.1.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.8.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d354438aae0d999a3135cce35a92a49d7c7364f4741eeb8df775a6cd6e1cd89f
|
|
| MD5 |
8080f9dc9ac9a4567c83bba4dc065826
|
|
| BLAKE2b-256 |
96c0bb5d9db5a6dc6824b34063b806df3e17446cef85c63060de3170046dc594
|