VIDA-NYU/pycalibrate
pycalibrate is a Python library to visually analyze model calibration in Jupyter Notebooks
This tool helps data scientists and machine learning engineers understand how well their predictive models are calibrated. You input your model's predictions and the true outcomes, and it generates interactive visualizations that show where your model is overconfident or underconfident. This helps you assess the reliability of your model's probability estimates.
No commits in the last 6 months. Available on PyPI.
Use this if you need to visually analyze the calibration of your machine learning models directly within a Jupyter Notebook to ensure their predictions are trustworthy.
Not ideal if you need a tool for real-time model monitoring in production environments or if you are looking for advanced model interpretability methods beyond calibration analysis.
Stars
17
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 02, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VIDA-NYU/pycalibrate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookincubator/MCGrad
MCGrad is a scalable and easy-to-use tool for multicalibration. It ensures your ML model...
dholzmueller/probmetrics
Post-hoc calibration methods and metrics for classification
gpleiss/temperature_scaling
A simple way to calibrate your neural network.
yfzhang114/Generalization-Causality
关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative...
Affirm/splinator
Splinator: probabilistic calibration with regression splines