Python Model Coexecution

Coexecute Python^® scikit-learn^® and custom Python machine learning models for prediction in Simulink^® using blocks in Statistics and Machine Learning Toolbox™. Load a saved Python model into a Scikit-learn Model Predict block or a Custom Python Model Predict block and configure incoming data types. Each block executes the model in Python and returns the Python output to Simulink. You can optionally load a Python function into the Scikit-learn Model Predict block to preprocess the predictor data Simulink passes to the Python model, and a function to postprocess the predicted responses from the model.

MATLAB supports the reference implementation of Python, often called CPython. If you are on a Mac or Linux^® platform, you already have Python installed. If you use Windows^®, you need to install a distribution, such as those found at https://www.python.org/downloads/. For more information, see Configure Your System to Use Python. Both blocks have been tested using Python version 3.10. To use the Scikit-learn Model Predict block, your MATLAB Python environment must have the scikit-learn module installed.