Custom Losses and Metrics for XGBoost, LightGBM, CatBoost
Project description
bokbokbok
Overview
bokbokbok is a python package that enables you to use Custom Loss Functions and Evaluation Metrics for XGBoost and LightGBM. Main features:
- Weighted Cross Entropy
- Weighted Focal Loss
- Log Cosh Loss
- Root Mean Squared Percentage Error
- F1 score
- Quadratic Weighted Kappa
Installation
pip install bokbokbok
Documentation
The documentation can be found here.
Contributing
To learn more about making a contribution to bokbokbok, please see CONTRIBUTING.md.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
bokbokbok-0.6.1.tar.gz
(7.4 kB
view hashes)
Built Distribution
bokbokbok-0.6.1-py3-none-any.whl
(10.9 kB
view hashes)
Close
Hashes for bokbokbok-0.6.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 026659db27e0f54afc9f0fa1107c254a06acae736a22260c3abb7bd9a0a4dca4 |
|
| MD5 | 00efad05099a8b9d5cbff48bca1188ee |
|
| BLAKE2b-256 | 9ac41384fdbe82e69836713feb92e230345d11dff31322392d3e03bd493c10a0 |
