以下是我使用Scala在spark.streaming
中获取Flume事件和进程的代码。
尝试使用reduceBykey
函数时,出现以下编译错误:
value reduceByKey is not a member of org.apache.spark.streaming.dstream.DStream[(String, Int)]
为什么?
我们是否需要以除此之外的任何特定方式处理Flume流?
我不认为这是一个依赖性问题,我有其他简单的应用程序在使用reduceBykey
的同一个Eclipse IDE中工作。
package com.deloitte.spark.learning
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import org.apache.spark.streaming.flume._
object Wordcount {
def main(args: Array[String]) {
if (args.length < 2) {
System.err.println("Usage: NetworkWordCount <hostname> <port>")
System.exit(1)
}
val sparkConf = new Sparkconf().setMaster("local[2]").setAppName("aa")
val ssc = new StreamingContext(sparkConf, Seconds(200))
val stream = FlumeUtils.createStream(ssc, args(0), args(1).toInt)
stream.count().map(cnt => "Received " + cnt + " flume events." ).print()
val lines = stream.map {
e => new String(e.event.getBody().array(), "UTF-8")
}
val words = lines.flatMap(_.split(" "))
val wordCounts = words.map(x => (x, 1))
ssc.start()
ssc.awaitTermination(1000)
}
}
答案 0 :(得分:1)
要在reduceByKey
上获取函数DStream[(String, Int)]
,您需要导入以下包:
import org.apache.spark.streaming.StreamingContext._