Thanks to visit codestin.com
Credit goes to github.com

Skip to content

kaareendrup/RPP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Reconstruction Performance Plotting Library (RPP)

Library for studying the performance of data reconstruction models developed for (but not limited to) machine learning reconstruction of events from particle physics experiments.

Simple example

from RPP.plotters.classification_plotter import ClassificationPlotter

# Initialize plotter
FlavourPlotter = ClassificationPlotter('/my/plot/dir', 'target_label')

# Add model predictions
FlavourPlotter.add_results('my_predictions.csv', 'my_data.db', 'ModelName')

# Plot model score histogram and performance (ROC) curve
FlavourPlotter.plot_score_hist()
FlavourPlotter.plot_performance_curve()

The current data structure is based on the approach of the GraphNeT framework with model predictions as .csv-files and metadata as sqlite-databases.

Code style: black Code quality Build Maintainability Test Coverage

About

Plotting library for machine learning reconstruction in high energy physics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages