Apache Spark is an open-source parallel processing framework that supports in-memory processing to boost the performance of big-data analytic applications. Spark processing engine is built for speed, ease of use, and sophisticated analytics. Spark's in-memory computation capabilities make it a good choice for iterative algorithms in machine learning and graph computations. Spark is also compatible with Azure Blob storage (WASB) so your existing data stored in Azure can easily be processed via Spark. When you create a Spark cluster in HDInsight, you create Azure compute resources with Spark installed and configured.
This topic describes how to load machine learning (ML) models that have been built using Spark MLlib and stored in Azure Blob Storage (WASB), and how to score them with datasets that have also been stored in WASB. It shows how to pre-process the input data, transform features using the indexing and encoding functions in the MLlib toolkit, and how to create a labeled point data object that can be used as input for scoring with the ML models. The models used for scoring include Linear Regression, Logistic Regression, Random Forest Models, and Gradient Boosting Tree Models. You need an Azure account and an HDInsight Spark cluster to begin this walkthrough. See the Overview of Data Science using Spark on Azure HDInsight for these requirements, for a description of the NYC 2013 Taxi data used here, and for instructions on how execute code from a Jupyter notebook on the Spark cluster.