AzimUddin

/*1. Create a Visual studio 2012 Project.
2. Add HDInsight SDK NuGet to your project -
In Visual Studio 2012, Click on Tools -> library package manager -> Package Manager Console 
PM> Install-Package Microsoft.WindowsAzure.Management.HDInsight 
3. Use the following code, fill up the relevant info, then build and run -
*/

using System;
using System.Collections.Generic;
using System.Linq;

AzimUddin

# An Example of using passing hadoop configurations for a job in HDInsight, via direct REST API
$MyHDInsightUserName = "YourClusterUserName"
$MyHDInsightPwd = "YourPwd"
$clusterName = "YourClusterName"
$storageAcctname = "YourStorageAcctname"
$containerName = "YourDefaultContainerName"

$HdInsightPwd = ConvertTo-SecureString $MyHDInsightPwd -AsPlainText -Force
$HdInsightCreds = New-Object System.Management.Automation.PSCredential ($MyHDInsightUserName, $HdInsightPwd)

AzimUddin

var mapReduceJob = new MapReduceJobCreateParameters() 
{
      ClassName = "wordcount", // required
      JobName = "MyWordCountJob", //optional
      JarFile = "/example/jars/hadoop-examples.jar",  // Required, alternative syntax: wasb://hdijobs@azimasv2.blob.core.windows.net/example/jar/hadoop-examples.jar
      StatusFolder = "/AzimMRJobs/WordCountJobStatus" //Optional, but good to use to know where logs are uploaded in Azure Storage
};

//WordCount progam needs two arguments
mapReduceJob.Arguments.Add("/example/data/gutenberg/davinci.txt"); //input file

AzimUddin

# mapreduce example with hadoop job configurations
$clusterName = "YourClusterName"
$jobConfig = @{ "mapred.output.compress"="true"; "mapred.output.compression.codec"="org.apache.hadoop.io.compress.GzipCodec" }
$myWordCountJob = New-AzureHDInsightMapReduceJobDefinition -JarFile "/example/jars/hadoop-examples.jar" -ClassName "wordcount" -jobName "WordCountJob" -StatusFolder "/MyMRJobs/WordCountJobStatus" -Defines $jobConfig 
$myWordCountJob.Arguments.Add("/example/data/gutenberg/davinci.txt")
$myWordCountJob.Arguments.Add("MyMRJobs/WordCountOutput")
$MyMRJob = Start-AzureHDInsightJob -Cluster $clusterName -JobDefinition $myWordCountJob

#Hive Job example with hadoop job configurations
$clusterName = "YourClusterName"