Skip to content

Instantly share code, notes, and snippets.

ParquetOutputFormat.setWriteSupportClass(job,classOf[ProtoWriteSupport[Aggregate]])
ProtoParquetOutputFormat.setProtobufClass(job,classOf[Aggregate])
hourlyAggregates.saveAsNewAPIHadoopFile(outputDir,
classOf[Void],
classOf[Aggregate],
classOf[ParquetOutputFormat[Aggregate]],
job.getConfiguration)
val data = sc.textFile("src/test/resources/*.csv")
val calls = data.map (Call(_)).cache()
val hourlyPairs = calls.map(c => (c.getHourly,c))
val weeklyPairs = calls.map(c => (c.getWeekly,c))
val groupedHourly = hourlyPairs.groupByKey()
val groupedWeekly = weeklyPairs.groupByKey()
@Arnonrgo
Arnonrgo / UsingHBaseTestUtil.scala
Created September 7, 2013 19:42
Setting up an embeded Hbase cluster for testing
val tableName="testTable"
val family = Bytes.toBytes("f")
val qualifier=Bytes.toBytes("q")
val hbaseTestUtil = new HBaseTestingUtility()
val config = hbaseTestUtil.getConfiguration
val tmpDir = File.createTempFile("logdir", "")
tmpDir.delete()
tmpDir.mkdir()
package com.yammer.metrics.jersey.tests.resources;
import com.yammer.metrics.annotation.ExceptionMetered;
import com.yammer.metrics.annotation.Metered;
import com.yammer.metrics.annotation.Timed;
import javax.ws.rs.*;
import javax.ws.rs.core.MediaType;
import java.io.IOException;