Platform for Machine Learning projects on Software Engineering

hacktoberfest machine-learning software-engineering

Перейти к файлу

Marco Castelluccio 67c300263f Split downloading of bugs and retrieval of bugs for training		2018-10-11 19:40:53 +02:00
data	Don't use MongoDB	2018-10-11 15:43:44 +02:00
.gitignore	First commit	2018-03-11 20:12:35 +00:00
.isort.cfg	Enable several flake8 checkers	2018-09-21 16:45:04 +02:00
.travis.yml	Add Travis CI configuration	2018-09-22 02:01:35 +02:00
LICENSE	First commit	2018-03-11 20:12:35 +00:00
README.md	Update number of bugs in the dataset	2018-10-11 17:29:20 +02:00
bug_features.py	Add a ML-based classifier	2018-09-22 02:10:21 +02:00
bugbug.py	Fix flake8 issues in bugbug.py	2018-09-22 02:00:36 +02:00
classes.csv	First commit	2018-03-11 20:12:35 +00:00
classes_more.csv	Add more labelled bugs	2018-10-11 14:04:41 +02:00
get_bugs.py	Split downloading of bugs and retrieval of bugs for training	2018-10-11 19:40:53 +02:00
handwritten_rules_run.py	Split downloading of bugs and retrieval of bugs for training	2018-10-11 19:40:53 +02:00
requirements.txt	Don't use MongoDB	2018-10-11 15:43:44 +02:00
run.py	Split downloading of bugs and retrieval of bugs for training	2018-10-11 19:40:53 +02:00
setup.cfg	Enable several flake8 checkers	2018-09-21 16:45:04 +02:00
test-requirements.txt	Enable several flake8 checkers	2018-09-21 16:45:04 +02:00
utils.py	Add a ML-based classifier	2018-09-22 02:10:21 +02:00

README.md

bugbug - Classify Bugzilla bugs between actual bugs and bugs that aren't bugs

Bugs on Bugzilla aren't always bugs. Sometimes they are feature requests, refactorings, and so on. The aim of this project is to distinguish between bugs that are actually bugs and bugs that aren't.

The dataset currently contains 2110 bugs, the accuracy of the current classifier is ~92% (precision ~97%, recall ~93%).

Setup

Run pip install -r requirements.txt and pip install -r test-requirements.txt
Run cat data/bugs.json.xz.part* | unxz > data/bugs.json

If you update the bugs database, run cat data/bugs.json | xz -v9 - | split -d -b 20MB - data/bugs.json.xz.part.