Operationalize your machine learning project using SQL Server 2016 SSIS and R Services

With the release of CTP3 SQL Server 2016 and its native In-database support for the open source R language (SQL Server R Services), users can now call both R and RevoScaleR functions and scripts directly from within a SQL query and benefit from multi-threaded and multi-core in-DB computations. The R integration brings the utility of data science to your applications without the need to'export' the data to your R environment. Today, I will use the Adventure Works samples for SQL Server 2016 CTP3 to showcase how we can use SSIS to operationalize a R prediction from doing data preparation, to using the training data to build and save the "trained" model and running prediction using the trained model. In this specific example, we will use the IRIS flower dataset from Ronald Fisher that is built-in dataset from R as our data source and we will load this dataset into a SQL Server table called IRIS_RX_DATA. This will be our training data.