Understand the project
Practical overview
When it fits
Use UQ360 when a machine-learning workflow needs to quantify prediction uncertainty, compare uncertainty-related model measures or present uncertainty with predictions.
Who it is for
- Data scientists assessing uncertainty or calibration in model predictions.
- Developers adding prediction intervals or uncertainty metrics to machine-learning workflows.
Documented uses
- Add prediction intervals to a regression model.
- Evaluate uncertainty and calibration with available metrics.
- Compare model configurations using an uncertainty metric.
- Communicate uncertainty alongside model predictions.
Before you choose
Requirements & limits
The README describes UQ360 as open source under the Apache-2.0 license and gives PyPI and repository installation routes.
- The README lists Python 3.7 on macOS, Ubuntu and Windows as supported configurations.
- The project is described as still in development.
- The interactive browser experience introduces concepts through an example; the Python package, notebooks and API are the developer-oriented resources.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Source-based practical guide
Install UQ360 from PyPI
Install the toolkit in an existing Python environment.
Before you start
- A Python environment; the README lists Python 3.7 configurations for macOS, Ubuntu and Windows.
Steps
Activate the Python environment where you want the package installed.
Run the command below.
pip install uq360
Expected outcome
The UQ360 package is installed in the selected environment.
Guide limitations
- The README notes that example notebooks may need to be downloaded separately when installing this way.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 8 October 2026
- Original website title
- IBM/UQ360 · Official homepage title · retained in its source language