User guides

This page contains guides and links to resources that show how OpenSTEF can be used.

Pipelines - high level functionality

OpenSTEF is designed around Pipelines (see concepts for definition). Pipelines offer an easy way to train models, generate forecasts, and evaluate forecasting performance.

The following pipelines are available:

A great way to get started and become familiar with OpenSTEF pipelines is to have a look at this GitHub repository that contains an assortment of Jupyter notebook examples. The repository even includes example data.

You can run each example notebook locally without any setup required, apart from the installation of the OpenSTEF package.

We encourage you to check out all the examples, but here is a list to get you started:

For more in-depth information on how to use and implement the pipelines in an operational setting, including code examples, see the Pipelines user guide section of this documentation.

Deploy as a full Forecasting application

If you would like to setup a full forecasting application that is ready to be used in an operational setting with a backend datastore and graphical user interface frontent, this GitHub repository contains a reference implementation you can use as a starting point. This example implementation includes databases, a user interface, and example data.

More information on what the architecture of such an application could look like can be found here.

Screenshot of the operational dashboard showing the key functionality of OpenSTEF.

Screenshot of the operational dashboard showing the key functionality of OpenSTEF. Dashboard documentation can be found here.

Example Jupyter notebooks

Jupyter Notebooks demonstrating some of OpenSTEF’s main functionality can be found at: OpenSTEF/openstef-offline-example.