CreateHDICluster.ps1

##################### Begin Edits ####################
#region edits
param
(
    # NOTE: All the storage accounts and containers need to be created on the same data center as the HDInsight cluster and would need to be created prior to running the script
    # They can be created from the Azure Management Portal

    # This is the name of your Azure Subscription that will be used for provisiong Azure HDInsight
    [string]$PrimarySubscriptionName="xxx",
    # This is the primary storage account that needs to be created on the same data center as your HDInsight Cluster
    # This needs to be pre-provisioned prior to running the script
    [string]$PrimaryStorageAccount="myhdi30primary", 
    # This is the name of the container in the primary storage account. This needs to be pre-provisioned prior to running this script.
    [string]$PrimaryStorageContainer="install",
    # This is the additional storage account that is used to storage the external JAR files for customizing the HDInsight Cluster. Needs to be pre-provisioned prior to running the script.
    [string]$HiveLibStorageAccount="myhdi30libs",
    # This is the name of the container in the additional storage account. Again, needs to be created prior to running the script.
    [string]$HiveLibStorageContainer="libs",
    # This is the data center where the HDInsight cluster and storage accounts are provisioned
    [string]$HDInsightClusterLocation="West US",
    #This is the name of the HDInsight cluster
    [string]$HDInsightClusterName="MyHDI30",
    #This is the size of the cluster # of data nodes
    [string]$HDIClusterSize = "1",
    #This is the version of the HDInsight cluster. Default version is 2.1, however you can choose to create 3.0 or 3.1 clusters
    # Please refer to this page for HDInsight/HDP/Hadoop version mapping - http://azure.microsoft.com/en-us/documentation/articles/hdinsight-component-versioning/
    [string]$HDInsightClusterVersion="3.0",
    # HDInsight cluster admin user name and password need to be specified here. This will be used for subsequent admin logins to the cluster for job submissions. 
    [string]$MyHDInsightUserName = "xxx",
    [string]$MyHDInsightPwd = "xxx"
)
#endregion edits
#################### End Edits ####################### 

#region code

# Credentials
Add-AzureAccount
Select-AzureSubscription $PrimarySubscriptionName
 
$HdInsightPwd = ConvertTo-SecureString $MyHDInsightPwd -AsPlainText -Force
$creds= New-Object System.Management.Automation.PSCredential ($MyHDInsightUserName, $HdInsightPwd)
 
$PrimarySubscriptionID = (Get-AzureSubscription $PrimarySubscriptionName).SubscriptionId
$PrimaryStorageAccountKey = Get-AzureStorageKey $PrimaryStorageAccount | %{ $_.Primary }
$HiveLibStorageAccountKey = Get-AzureStorageKey $HiveLibStorageAccount | %{ $_.Primary }
 
#This will be the credential used for the admin account of the HDInsight Cluster
#$creds = Get-Credential -Message "Please enter the admin account credentials for your HDInsight Cluster"
 
# Set Custom Configuration
$configvalues = new-object 'Microsoft.WindowsAzure.Management.HDInsight.Cmdlet.DataObjects.AzureHDInsightHiveConfiguration'
 
$configvalues.Configuration = @{ “hive.exec.compress.output”=”true” } 
$configvalues.AdditionalLibraries = new-object 'Microsoft.WindowsAzure.Management.HDInsight.Cmdlet.DataObjects.AzureHDInsightDefaultStorageAccount'
$configvalues.AdditionalLibraries.StorageAccountName = "$HiveLibStorageAccount.blob.core.windows.net" 
$configvalues.AdditionalLibraries.StorageAccountKey = $HiveLibStorageAccountKey
$configvalues.AdditionalLibraries.StorageContainerName = $HiveLibStorageContainer
 
# Create Azure HDInsight Cluster

New-AzureHDInsightClusterConfig -ClusterSizeInNodes $HDIClusterSize -ClusterType Hadoop `
| Set-AzureHDInsightDefaultStorage -StorageAccountName "$PrimaryStorageAccount.blob.core.windows.net" -StorageAccountKey $PrimaryStorageAccountKey -StorageContainerName $PrimaryStorageContainer  `
| Add-AzureHDInsightConfigValues -Hive $configvalues `
| New-AzureHDInsightCluster -Subscription $PrimarySubscriptionID -Credential $creds -Name $HDInsightClusterName  -Location $HDInsightClusterLocation -Version $HDInsightClusterVersion

#endregion code