GSoC'23 -- Week 9

[Baole Fang]

---
title: "Week 9"
date: 2023-07-27
---

### Model improvement

To improve model performance, the model based on grouped unit tests is
implemented. Originally, the model is trained to predict on the level of
around 700 unit tests, which is too much. To reduce the number of
predictions, unit tests are grouped into 80 groups based on their folder
parents and functions in [mapping.py](
https://github.com/baolef/libreoffice-ci/blob/group/dataset/mapping.py).
The performance has improved to:

|               | Fail (Predicted) | Pass (Predicted) |
|---------------|------------------|------------------|
| Fail (Actual) | 3860             | 203              |
| Pass (Actual) | 191593           | 1109768          |

[testselect](
https://github.com/baolef/libreoffice-ci/blob/main/models/testselect.py) is
now able to recognize 95% (94% previously) of all failures, while reducing
computation by 85% (84% previously).
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/libreoffice/attachments/20230804/06d2b9b9/attachment.htm>