adding JDBC example to DataFrame API

This commit is contained in:
skaarthik 2016-01-10 21:15:17 -08:00
Родитель 6d1db2330c
Коммит 50937ea04a
6 изменённых файлов: 173 добавлений и 0 удалений

Просмотреть файл

@ -1,8 +1,12 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 2013
VisualStudioVersion = 12.0.30501.0
MinimumVisualStudioVersion = 10.0.40219.1
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Pi", "Pi\Pi.csproj", "{913E6A56-9839-4379-8B3C-855BA9341663}"
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "JdbcDataFrame", "JdbcDataFrame\JdbcDataFrame.csproj", "{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU
@ -13,6 +17,10 @@ Global
{913E6A56-9839-4379-8B3C-855BA9341663}.Debug|Any CPU.Build.0 = Debug|Any CPU
{913E6A56-9839-4379-8B3C-855BA9341663}.Release|Any CPU.ActiveCfg = Release|Any CPU
{913E6A56-9839-4379-8B3C-855BA9341663}.Release|Any CPU.Build.0 = Release|Any CPU
{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}.Debug|Any CPU.Build.0 = Debug|Any CPU
{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}.Release|Any CPU.ActiveCfg = Release|Any CPU
{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}.Release|Any CPU.Build.0 = Release|Any CPU
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE

Просмотреть файл

@ -0,0 +1,20 @@
<?xml version="1.0" encoding="utf-8"?>
<configuration>
<configSections>
<section name="log4net" type="log4net.Config.Log4NetConfigurationSectionHandler, log4net" />
</configSections>
<log4net>
<root>
<level value="DEBUG" />
<appender-ref ref="ConsoleAppender" />
</root>
<appender name="ConsoleAppender" type="log4net.Appender.ConsoleAppender">
<layout type="log4net.Layout.PatternLayout">
<conversionPattern value="[%date] [%thread] [%-5level] [%logger] - %message%newline" />
</layout>
</appender>
</log4net>
</configuration>

Просмотреть файл

@ -0,0 +1,67 @@
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="12.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
<PropertyGroup>
<Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
<Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
<ProjectGuid>{4DAFC0A4-0619-4D6C-BF8E-9EC84C9DE9FC}</ProjectGuid>
<OutputType>Exe</OutputType>
<AppDesignerFolder>Properties</AppDesignerFolder>
<RootNamespace>JdbcDataFrame</RootNamespace>
<AssemblyName>SparkCLRJdbcDataFrameExample</AssemblyName>
<TargetFrameworkVersion>v4.5</TargetFrameworkVersion>
<FileAlignment>512</FileAlignment>
</PropertyGroup>
<PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
<PlatformTarget>AnyCPU</PlatformTarget>
<DebugSymbols>true</DebugSymbols>
<DebugType>full</DebugType>
<Optimize>false</Optimize>
<OutputPath>bin\Debug\</OutputPath>
<DefineConstants>DEBUG;TRACE</DefineConstants>
<ErrorReport>prompt</ErrorReport>
<WarningLevel>4</WarningLevel>
</PropertyGroup>
<PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
<PlatformTarget>AnyCPU</PlatformTarget>
<DebugType>pdbonly</DebugType>
<Optimize>true</Optimize>
<OutputPath>bin\Release\</OutputPath>
<DefineConstants>TRACE</DefineConstants>
<ErrorReport>prompt</ErrorReport>
<WarningLevel>4</WarningLevel>
</PropertyGroup>
<ItemGroup>
<Reference Include="CSharpWorker, Version=1.5.2.0, Culture=neutral, processorArchitecture=MSIL">
<SpecificVersion>False</SpecificVersion>
<HintPath>..\..\csharp\Worker\Microsoft.Spark.CSharp\bin\Debug\CSharpWorker.exe</HintPath>
</Reference>
<Reference Include="Microsoft.Spark.CSharp.Adapter, Version=1.5.2.0, Culture=neutral, processorArchitecture=MSIL">
<SpecificVersion>False</SpecificVersion>
<HintPath>..\..\csharp\Adapter\Microsoft.Spark.CSharp\bin\Debug\Microsoft.Spark.CSharp.Adapter.dll</HintPath>
</Reference>
<Reference Include="System" />
<Reference Include="System.Core" />
<Reference Include="System.Xml.Linq" />
<Reference Include="System.Data.DataSetExtensions" />
<Reference Include="Microsoft.CSharp" />
<Reference Include="System.Data" />
<Reference Include="System.Xml" />
</ItemGroup>
<ItemGroup>
<Compile Include="Program.cs" />
<Compile Include="Properties\AssemblyInfo.cs" />
</ItemGroup>
<ItemGroup>
<None Include="App.config" />
<None Include="packages.config" />
</ItemGroup>
<Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
<!-- To modify your build process, add your task inside one of the targets below and uncomment it.
Other similar extension points exist, see Microsoft.Common.targets.
<Target Name="BeforeBuild">
</Target>
<Target Name="AfterBuild">
</Target>
-->
</Project>

Просмотреть файл

@ -0,0 +1,35 @@
// Copyright (c) Microsoft. All rights reserved.
// Licensed under the MIT license. See LICENSE file in the project root for full license information.
using System;
using System.Collections.Generic;
using Microsoft.Spark.CSharp.Core;
using Microsoft.Spark.CSharp.Services;
using Microsoft.Spark.CSharp.Sql;
namespace Microsoft.Spark.CSharp.Examples
{
/// <summary>
/// This example shows how to use JDBC in SparkCLR's C# API for Apache Spark DataFrame to
/// load data from SQL Server. The connection url need to be updated for a different JDBC source.
/// </summary>
class JdbcDataFrameExample
{
static void Main(string[] args)
{
LoggerServiceFactory.SetLoggerService(Log4NetLoggerService.Instance); //this is optional - DefaultLoggerService will be used if not set
var logger = LoggerServiceFactory.GetLogger(typeof(JdbcDataFrameExample));
var sparkConf = new SparkConf();
var sparkContext = new SparkContext(sparkConf);
var sqlContext = new SqlContext(sparkContext);
var df = sqlContext.Read()
.Jdbc("jdbc:sqlserver://localhost:1433;databaseName=Temp;;integratedSecurity=true;", "xyz",
new Dictionary<string, string>());
df.ShowSchema();
var rowCount = df.Count();
logger.LogInfo("Row count is " + rowCount);
}
}
}

Просмотреть файл

@ -0,0 +1,34 @@
// Copyright (c) Microsoft. All rights reserved.
// Licensed under the MIT license. See LICENSE file in the project root for full license information.
using System.Reflection;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
// General Information about an assembly is controlled through the following
// set of attributes. Change these attribute values to modify the information
// associated with an assembly.
[assembly: AssemblyTitle("SparkCLRJdbcDataFrameExample")]
[assembly: AssemblyDescription("JDBC Example for DataFrame API in SparkCLR")]
[assembly: AssemblyConfiguration("")]
[assembly: AssemblyCompany("Microsoft Corporation")]
[assembly: AssemblyProduct("Microsoft SparkCLR")]
[assembly: AssemblyCopyright("Copyright © Microsoft Corporation 2015")]
[assembly: AssemblyTrademark("")]
[assembly: AssemblyCulture("")]
// Setting ComVisible to false makes the types in this assembly not visible
// to COM components. If you need to access a type in this assembly from
// COM, set the ComVisible attribute to true on that type.
[assembly: ComVisible(false)]
// [assembly: CLSCompliant(true)]
// Version information for an assembly consists of the following four values:
//
// Major Version
// Minor Version
// Build Number
// Revision
//
[assembly: AssemblyVersion("1.5.2.0")]
[assembly: AssemblyFileVersion("1.5.2.0")]

Просмотреть файл

@ -0,0 +1,9 @@
<?xml version="1.0" encoding="utf-8"?>
<packages>
<package id="log4net" version="2.0.5" targetFramework="net45" />
<package id="Newtonsoft.Json" version="7.0.1" targetFramework="net45" />
<package id="Razorvine.Pyrolite" version="4.10.0.0" targetFramework="net45" />
<package id="Razorvine.Serpent" version="1.12.0.0" targetFramework="net45" />
<!-- TODO uncomment the following line and remove references from the project for Adapter & Worker -->
<!--package id="Microsoft.SparkCLR" version="1.5.2-SNAPSHOT" targetFramework="net45" /-->
</packages>