MAPIE

Getting Started

Quick Start with MAPIE
The conformalization (“calibration”) set
- 1. Split conformal predictions
  - Split conformal predictions with a pre-trained model
  - Split conformal predictions with an untrained model
- 2. Cross conformal predictions
Choosing the right algorithm
MAPIE v1 release notes

Measure predictions uncertainty

Prediction intervals (regression)
Prediction sets (classification)

Control prediction errors

Getting started with risk control
Precision control for a binary classifier
All risk control examples
- 1. Quickstart examples
  - Precision control for a binary classifier
- 2. Advanced analysis

Calibrate classifiers

Theoretical Description
Calibration examples
- 1. Quickstart examples
- 2. Advanced analysis
  - Evaluating the asymptotic convergence of p-values
Calibration notebooks

Question & Answers

Metrics: how to measure conformal prediction performance?
Mondrian: how to use prior knowledge on groups when measuring uncertainty?
- Tutorial: how to ensure fairness across groups with Mondrian
- Theoretical Description
  - References
How to control LLM risks?

API

MAPIE API

MAPIE

Prediction sets (classification)
All classification examples
1. Quickstart examples
View page source

1. Quickstart examples

The following examples present the main functionalities of MAPIE through basic quickstart classification problems.

Plot prediction sets

Plot prediction sets

Previous Next

© Copyright 2026, Capgemini Invent.

Built with Sphinx using a theme provided by Read the Docs.