initial commit

2025-12-08 14:58:54 +00:00 · 2017-05-23 20:47:01 +02:00
parent 72558a1e16
commit e519f7230e
1 changed files with 88 additions and 0 deletions
@@ -0,0 +1,88 @@
+# Build a predictive model with RevoScalePy using SQL Server 2017 Machine Learning Services
+
+This sample shows how to create a predictive model using RevoScalePy in conjunction with Python machine learning stack.
+
+The dataset  used in this tutorial is based on Vélib which is a large scale public service of rent bike in Paris, the service offers today about around 14500 bicycles and 1230 stations http://en.velib.paris.fr/.
+
+The dataset is a one month long  sample, on a 15 minutes frequency of the 8th district of Paris.
+
+
+### Contents
+
+[About this sample](#about-this-sample)
+
+[Before you begin](#before-you-begin)
+
+[Sample details](#sample-details)
+
+
+
+
+## About this sample
+
+
+This sample consist of a  binary classifier that predict if a bike station is empty or not.
+
+
+
+
+- **Applies to:** SQL Server 2017 CTP2.0 or higher
+- **Key features:** SQL Server Machine Learning Services 
+- **Workload:** SQL Server Machine Learning Services
+- **Programming Language:** Python, TSQL
+- **Author:** Yassine Khelifi
+- **Update history:** Build a predictive model with RevoScalePy library using SQL Server 2017 Machine Learning Services - Python 
+
+
+
+## Before you begin
+
+To run this sample, you need the following prerequisites: 
+1. [Download this DB backup file](https://sq14samples.blob.core.windows.net/data/velibDB.bak) and restore it using Setup.sql. 
+
+**Software prerequisites:**
+
+
+1. [SQL Server 2017 CTP2.0](https://www.microsoft.com/en-us/sql-server/sql-server-2017) (or higher) with Machine Learning Services (Python) installed
+2. [SQL Server Management Studio](https://docs.microsoft.com/en-us/sql/ssms/download-sql-server-management-studio-ssms)
+3. [Python Tools for Visual Studio](https://www.visualstudio.com/vs/python/) or another Python IDE
+
+## Run this sample
+1. From SQL Server Management Studio, or SQL Server Data Tools, connect to your SQL Server 2017 database and execute setup.sql to restore the sample DB you have downloaded 
+2. From Python Tools for Visual Studio, open the solution  
+3. In Python tools for  Visual Studio, remember to add the Machine Learning Services Python environment to the corresponding paths https://docs.microsoft.com/en-us/visualstudio/python/python-environments
+
+   * "C:\Program Files\Microsoft SQL Server\MSSQL14.MSSQLSERVER\PYTHON_SERVICES" if you run in-db Python Server
+   * "C:\Program Files\Microsoft SQL Server\140\PYTHON_SERVER" if you have the standalone Machine Learning Server installed .
+
+
+
+
+## Sample details
+
+#### datasource.py
+This Python script defines the class that pull data from Sql database and provides access to SQL Server Compute Context.
+
+####  pipeline.sql
+This python file defines the machine learning pipeline that performs features engineering and the classifier that fits the RevoScalePy binary logistic regression.
+
+####  runner.sql
+This python file defines the startup code and main method from which to excecute the solution.
+
+####  setup.sql
+Restores the sample DB (Make sure to update the path to the .bak file)
+
+
+
+
+
+## Disclaimers
+
+The sample is only intenteded to show how  RevoScalePy library can be used in conjunction with python machine leanring stack.
+
+The dataset used in this sample is obtained from JCdecaux data set https://developer.jcdecaux.com/#/opendata/vls?page=dynamic 
+
+[![Etalab open license](https://sq14samples.blob.core.windows.net/images/open_licence.png)](https://developer.jcdecaux.com/#/opendata/license)
+
+
+