Created
November 22, 2012 16:09
-
-
Save AndyCross/4131891 to your computer and use it in GitHub Desktop.
StreamingUnit
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using Elastacloud.Hadoop.StreamingUnitExample.Job.Map; | |
using Elastacloud.Hadoop.StreamingUnitExample.Job.Reduce; | |
using Microsoft.Hadoop.MapReduce; | |
namespace Elastacloud.Hadoop.StreamingUnitExample.Job | |
{ | |
public class HelloWorldJob : HadoopJob<HelloWorldMapper, HelloWorldReducer> | |
{ | |
public override HadoopJobConfiguration Configure(ExecutorContext context) | |
{ | |
return new HadoopJobConfiguration();//here you would normally set up some input ;-) | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using Microsoft.Hadoop.MapReduce; | |
namespace Elastacloud.Hadoop.StreamingUnitExample.Job.Map | |
{ | |
public class HelloWorldMapper : MapperBase | |
{ | |
public override void Map(string inputLine, MapperContext context) | |
{ | |
//example input: Hello, Andy | |
if (!inputLine.StartsWith("Hello, ")) return; | |
var key = inputLine.Substring(7); | |
if (key.EndsWith(".")) key = key.Trim('.'); | |
context.EmitKeyValue(key, "1");//we are going to count instances, the value is irrelevant | |
} | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System.Collections.Generic; | |
using System.Linq; | |
using Microsoft.Hadoop.MapReduce; | |
namespace Elastacloud.Hadoop.StreamingUnitExample.Job.Reduce | |
{ | |
public class HelloWorldReducer : ReducerCombinerBase | |
{ | |
public override void Reduce(string key, IEnumerable<string> values, ReducerCombinerContext context) | |
{ | |
context.EmitKeyValue(key, values.Count().ToString());//count instances of this key | |
} | |
} | |
} |
We can make this file beautiful and searchable if this error is corrected: No commas found in this CSV file in line 0.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Map | |
Andy 1 | |
Andy 1 | |
Andy 1 | |
andy 1 | |
chickenface 1 | |
why doesn't this work! 1 | |
Reduce | |
Andy 3 | |
andy 1 | |
chickenface 1 | |
why doesn't this work! 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System; | |
using Elastacloud.Hadoop.StreamingUnitExample.Job.Map; | |
using Elastacloud.Hadoop.StreamingUnitExample.Job.Reduce; | |
using Microsoft.Hadoop.MapReduce; | |
namespace Elastacloud.Hadoop.StreamingUnitExample | |
{ | |
class Program | |
{ | |
static void Main(string[] args) | |
{ | |
var inputArray = new[] | |
{ | |
"Hello, Andy", | |
"Hello, andy", | |
"Hello, why doesn't this work!", | |
"Hello, Andy", | |
"Hello, chickenface", | |
"Hello, Andy" | |
}; | |
var output = | |
StreamingUnit.Execute<HelloWorldMapper, HelloWorldReducer>(inputArray); | |
Console.WriteLine("Map"); | |
foreach (var mapperResult in output.MapperResult) | |
{ | |
Console.WriteLine(mapperResult); | |
} | |
Console.WriteLine("Reduce"); | |
foreach (var reducerResult in output.ReducerResult) | |
{ | |
Console.WriteLine(reducerResult); | |
} | |
Console.ReadLine(); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment