uncertainty-toolbox/uncertainty-toolbox

Health v2 · maintenance only

Adoption not part of the score

2012 stars · 152 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library for predictive uncertainty quantification, providing metrics, visualizations, and recalibration procedures for regression models. It also includes a glossary and curated paper list on uncertainty estimation.

Use cases

• evaluate calibration of model uncertainty estimates
• compare predictive uncertainties across models with standard metrics
• visualize confidence intervals and calibration curves
• recalibrate regression predictions to improve uncertainty quality
• compute scoring rules for probabilistic forecasts
• learn about uncertainty quantification terminology and papers

When to choose

• you need standardized metrics for regression uncertainty and calibration
• you want quick recalibration of predicted means and standard deviations
• you need plots and benchmarks for probabilistic predictions

When to avoid

• you need uncertainty quantification for classification tasks (toolbox focuses on regression)
• you want full Bayesian deep learning training methods rather than evaluation
• you need production-scale distributed metric computation

Facets

library · maturity active

data-science machine-learning data-visualization benchmarking machine-learning data-science python cross-platform uncertainty-quantification calibration predictive-uncertainty scoring-rules recalibration bayesian-deep-learning regression algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="uncertainty-toolbox/uncertainty-toolbox")