| title | Tutorial for in-database analytics using R |
|---|---|
| description | Learn how to embed R programming language code in SQL Server stored procedures and T-SQL functions. |
| ms.prod | sql |
| ms.technology | machine-learning |
| ms.date | 06/13/2019 |
| ms.topic | tutorial |
| author | dphansen |
| ms.author | davidph |
| monikerRange | >=sql-server-2016||>=sql-server-linux-ver15||=sqlallproducts-allversions |
[!INCLUDEappliesto-ss-xxxx-xxxx-xxx-md]
In this tutorial for SQL programmers, learn about R integration by building and deploying an R-based machine learning solution using a NYCTaxi_sample database on SQL Server. You'll use T-SQL, SQL Server Management Studio, and a database engine instance with [Machine Learning Services](Machine Learning Services and the R language support
This tutorial introduces you to R functions used in a data modeling workflow. Steps include data exploration, building and training a binary classification model, and model deployment. The model you will build predicts whether a trip is likely to result in a tip based on the time of day, distance traveled, and pick-up location.
All of the R code used in this tutorial is wrapped in stored procedures that you create and run in Management Studio.
The process of building a machine learning solution is a complex one that can involve multiple tools, and the coordination of subject matter experts across several phases:
- obtaining and cleaning data
- exploring the data and building features useful for modeling
- training and tuning the model
- deployment to production
Development and testing of the actual code is best performed using a dedicated R development environment. However, after the script is fully tested, you can easily deploy it to [!INCLUDEssNoVersion] using [!INCLUDEtsql] stored procedures in the familiar environment of [!INCLUDEssManStudio].
The purpose of this multi-part tutorial is an introduction to a typical workflow for migrating "finished R code" to SQL Server.
-
Lesson 3: Train and save an R model using functions and stored procedures
-
Lesson 4: Predict potential outcomes using an R model in a stored procedure
After the model has been saved to the database, call the model for predictions from [!INCLUDEtsql] by using stored procedures.
All tasks can be done using [!INCLUDEtsql] stored procedures in [!INCLUDEssManStudio].
This tutorial assumes familiarity with basic database operations such as creating databases and tables, importing data, and writing SQL queries. It does not assume you know R. As such, all R code is provided.
[!div class="nextstepaction"] Explore and visualize data using R functions in stored procedures