https://github.com/ringer-softwares/kolmov
A Framework to make the cross validation studies and pos tuning analysis for NeuralRinger developments
https://github.com/ringer-softwares/kolmov
correction cross-validation rak
Last synced: 5 months ago
JSON representation
A Framework to make the cross validation studies and pos tuning analysis for NeuralRinger developments
- Host: GitHub
- URL: https://github.com/ringer-softwares/kolmov
- Owner: ringer-softwares
- License: gpl-3.0
- Created: 2020-12-22T12:43:30.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2023-03-06T12:58:26.000Z (about 3 years ago)
- Last Synced: 2023-03-08T19:50:39.520Z (about 3 years ago)
- Topics: correction, cross-validation, rak
- Language: Python
- Homepage:
- Size: 27.7 MB
- Stars: 3
- Watchers: 3
- Forks: 16
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# KoLMoV
[](https://pypi.org/project/kolmov/)
[](https://github.com/jodafons/kolmov)
We should include some description here.
## What does mean?
KoLMoV (**K**it **o**f **L**earning **M**odels **V**alidation) is a repository that contains somes helpers to calculate the cross validation or pileup linear fit for ringer tuning derived from [saphyra](https://github.com/ringer-atlas/saphyra) package.
**NOTE** This repository is part of the ringer analysis kit.
## Installation:
Install stable version from pip:
```bash
pip install kolmov
```
or install latest version from git:
```bash
pip install git+https://github.com/ringer-atlas/kolmov.git@master
```
or install from source:
```bash
git clone https://github.com/ringer-atlas/kolmov.git
cd kolmov
source scripts/setup.sh
```
## Notes about ringer project:
In 2017 the ATLAS experiment implemented an ensemble of neural networks (NeuralRinger algorithm) dedicated to improving the performance of filtering events containing electrons in the high-input rate online environment of the Large Hadron Collider at CERN, Geneva. The ensemble employs a concept of calorimetry rings. The training procedure and final structure of the ensemble are used to minimize fluctuations from detector response, according to the particle energy and position of incidence.