Skip to main content

Celonis Product Documentation

Machine Learning

The Celonis Platform offers integrated and embedded machine learning capabilities, giving you access to a fully hosted and managed machine learning workbench. This workbench is an integrated Python development environment based on Jupyter Notebook. These integrated tools require no installation, no maintenance, and no server requests.

You can access the machine learning features by clicking Data - Machine Learning:


Machine learning workbench (MLWB) activity types

When using the machine learning workbench, you can create the following activity types:

  • Notebooks and Console

    • Python3 (lpykernel)

    • Julia 1.5.3

    • Python 3.8 (XPython raw)

    • Python 3.8 (XPython)

    • R

  • Other

    • Terminal

    • Text file

    • Markdown file

    • Julia file

    • Python file

    • R file

Celonis Python packages

Celonis also offers two pre-installed Python packages, enabling you to use your Celonis Platform data when creating machine learning notebooks.


PyCelonis is an python based API wrapper for the Celonis Platform. With this package you can interact with Celonis objects as native objects, e.g. copy an analysis, pull and push data, and reload a datamodel, etc.

For more information about PyCelonis, see: PyCelonis Documentation

And for a set of tutorials on how to use PyCelonis, see: PyCelonis tutorials

PyCelonis example repository

This repository contains demo notebooks covering popular functionalities and use cases of PyCelonis. The repository contains several notebooks for both PyCelonis 1.X and 2.X that act as examples on what you can achieve using PyCelonis. The examples are grouped by their PyCelonis version and specific use cases.

To access the repository, see: PyCelonis example repository