GSoC'23 - Week 4

[Baole Fang]

---
title: "Week 4"
date: 2023-06-22
---

### Model training

Two models are trained with the full dataset:
- [testfailure](
https://github.com/baolef/libreoffice-ci/blob/main/models/testfailure.py)
predicts whether a commit will fail any unit test. It only considers commit
features.
- [testselect](
https://github.com/baolef/libreoffice-ci/blob/main/models/testselect.py)
predicts which unit tests the commit will fail. It only considers unit
tests features.

These two models are based on [bugbug](https://github.com/mozilla/bugbug),
but they have one main limitation. Commit and unit test features are
considered independently. The better way to solve this problem is to
consider these two kinds of features together to predict whether a
`(commit, test)` pair will pass or fail.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/libreoffice/attachments/20230702/f47da062/attachment.htm>