Skip to content

Latest commit

 

History

History
90 lines (57 loc) · 4.75 KB

File metadata and controls

90 lines (57 loc) · 4.75 KB
title In-Database Python Analytics for SQL Developers | Microsoft Docs
ms.custom
ms.date 04/28/2017
ms.prod sql-server-2017
ms.reviewer
ms.suite
ms.technology
r-services
ms.tgt_pltfrm
ms.topic article
applies_to
SQL Server 2017
dev_langs
Python
TSQL
ms.assetid
caps.latest.revision 1
author jeannt
ms.author jeannt
manager jhubbard

In-Database Python Analytics for SQL Developers

The goal of this walkthrough is to provide SQL programmers with hands-on experience building a machine learning solution in SQL Server. In this walkthrough, you'll learn how to incorporate Python into an application or BI solution by wrapping R code in stored procedures.

Note

The same solution is available in R, in either SQL Server 2016 or SQL Server 2017. See LINK.

Overview

The process of building an end to end solution typically consists of obtaining and cleaning data, data exploration and feature engineering, model training and tuning, and finally deployment of the model in production. Development and testing of the actual code is best performed using a dedicated development environment.For Python, that might mean PyCharm, a command-line tool, or Python Extensions for Visual Studio.

However, after the solution has been created, you can easily deploy it to [!INCLUDEssNoVersion] using [!INCLUDEtsql] stored procedures in the familiar environment of [!INCLUDEssManStudio].

In this walkthrough, we'll assume that you have been given all the Python code needed for the solution, and you'll focus on building and deploying the solution using SQL Server.

After the model has been saved to the database, call the model for prediction from [!INCLUDEtsql] by using stored procedures.

Note

We recommend that you do not use [!INCLUDEssManStudioFull] to write or test Python code. If the code that you embed in a stored procedure has any problems, the information that is returned from the stored procedure is usually inadequate to understand the cause of the error.

Scenario

This walkthrough uses the well-known NYC Taxi data set. To make this walkthrough easy and quick, we've provided a representative 1% sampling of the data. You'll use this data to build a binary classification model that predicts whether a particular trip is likely to get a tip or not, based on columns such as the time of day, distance, and pick-up location.

Requirements

This walkthrough is intended for users who are already familiar with fundamental database operations, such as creating databases and tables, importing data into tables, and creating SQL queries.

All Python code is provided. An experienced SQL programmer should be able to complete this walkthrough by using [!INCLUDEtsql] in [!INCLUDEssManStudioFull] or by running the provided PowerShell scripts.

Before starting the walkthrough, you must complete these preparations:

  • Install an instance of SQL Server 2017 with Machine Learning Services and Python enabled (requires CTP 2.0 or later), or get permission to connect to an instance.
  • The login that you use for this walkthrough must have permissions to create databases and other objects, to upload data, select data, and run stored procedures.

Next Step

Step 1: Download the Sample Data

See Also

Machine Learning Services with Python