Developing a Solution with SQL Server Machine Learning Services
If you want to launch a Python or R project with data which lives in SQL Server, SQL Server Machine Learning Services may be right for you. In this talk, we will take a look at SQL Server Machine Learning Services, starting with an overview and installation, but quickly moving into custom development. We will deploy packages with sqlmlutils and investigate some of the nicest features of Machine Learning Services, including native scoring and parallel processing. We will also see how to develop and deploy custom code, generating predictions which any application can read.
As far as tooling goes, for R, I recommend RStudio. If you want to build source or binary packages, you will need the correct version of Rtools. Because I have R 3.5 installed, I grabbed Rtools35.exe. If you've already move to R 4.0, there's a new version of Rtools, but watch out: SQL Server 2019 runs on R 3.5, so there might be some incompatibility issues.