RDD映射中的Spark Scala序列化错误

Question

我有一个RDD格式为RDD[((Long，Long)，(Long，Long))]，我需要隐藏或转换为RDD[(Long，Long)，(Long，Long，Long，Long))]，其中第二个RDD元组基于第一个RDD的函数。

我正在尝试实现这个基于地图的功能，但是，我认为在这里做了一些错误的事情。请帮我解决这个问题。

package com.ranker.correlation.listitem
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd._
import scala.collection.Map

class ListItemCorrelation(sc: SparkContext) extends Serializable {

  def up_down(dirX: Long, dirY: Long): (Long, Long, Long, Long) = {
    if (dirX.equals(1)) {
      if (dirY.equals(1)) {
        return (1, 0, 0, 0)
      } else {
        return (0, 1, 0, 0)
      }
    } else {
      if (dirY.equals(1)) {
        return (0, 0, 1, 0)
      } else {
        return (0, 0, 0, 1)
      }
    }
  }

  def run(votes: String):  RDD[((Long, Long), (Long, Long, Long, Long))]   = {
    val userVotes = sc.textFile(votes)
    val userVotesPairs = userVotes.map { t =>
      val p = t.split(",")
      (p(0).toLong, (p(1).toLong, p(2).toLong))
    }
    val jn = userVotesPairs.join(userVotesPairs).values.filter(t => t._1._1.<(t._2._1))
    val first = jn.map(t => ((t._1._1, t._2._1), (t._1._2, t._2._2)))
    var second = first.map(t => ((t._1._1, t._2._1), up_down(t._1._2, t._2._2)))
    //More functionality
    return result
  }

}
object ListItemCorrelation extends Serializable {
  def main(args: Array[String]) {
    val votes = args(0)
    val conf = new SparkConf().setAppName("SparkJoins").setMaster("local")
    val context = new SparkContext(conf)
    val job = new ListItemCorrelation(context)
    val results = job.run(votes)
    val output = args(1)
    results.saveAsTextFile(output)
    context.stop()
  }
}

Answer 1

将up_down方法放在伴生对象上。当在RDD闭包中访问任何类变量时，类（以及其中的所有内容，如SparkContext）都会被序列化。方法参数在这里算作类变量。使用静态对象可以解决以下问题：

package com.ranker.correlation.listitem
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd._
import scala.collection.Map

object ListItemCorrelation {
  def up_down(dirX: Long, dirY: Long): (Long, Long, Long, Long) = {
    if (dirX.equals(1)) {
      if (dirY.equals(1)) {
        return (1, 0, 0, 0)
      } else {
        return (0, 1, 0, 0)
      }
    } else {
      if (dirY.equals(1)) {
        return (0, 0, 1, 0)
      } else {
        return (0, 0, 0, 1)
      }
    }
  }
}


class ListItemCorrelation(sc: SparkContext) extends Serializable {

  def run(votes: String):  RDD[((Long, Long), (Long, Long, Long, Long))]   = {
    val userVotes = sc.textFile(votes)
    val userVotesPairs = userVotes.map { t =>
      val p = t.split(",")
      (p(0).toLong, (p(1).toLong, p(2).toLong))
    }
    val jn = userVotesPairs.join(userVotesPairs).values.filter(t => t._1._1.<(t._2._1))
    val first = jn.map(t => ((t._1._1, t._2._1), (t._1._2, t._2._2)))
    var second = first.map(t => ((t._1._1, t._2._1), ListItemCorrelation.up_down(t._1._2, t._2._2)))
    //More functionality
    return result
  }

}
object ListItemCorrelation extends Serializable {
  def main(args: Array[String]) {
    val votes = args(0)
    val conf = new SparkConf().setAppName("SparkJoins").setMaster("local")
    val context = new SparkContext(conf)
    val job = new ListItemCorrelation(context)
    val results = job.run(votes)
    val output = args(1)
    results.saveAsTextFile(output)
    context.stop()
  }
}