SQLBits 2024

Getting started with SparkML in Microsoft Fabric

Microsoft Fabric supports machine learning in their Spark notebooks. See an end-to-end demo of how Fabric data is used to build machine learning models upon, which are then used to make predictions about other Fabric datasets.
SparkML (aka MLlib) is a library for machine learning on the Spark framework. Crucial is the concept of Transformers and Estimators, with which parameterized pipelines can be built.
In this session you will see how to start building machine learning pipelines in Microsoft Fabric notebooks using MLlib, train a machine learning model and see the resulting model being used to make predictions.