我有代码可以在聚类后计算平方误差的集合和内,而我主要从Spark mllib源代码中获取代码。

当我使用spark API运行类似代码时,它将在许多不同的(分布式)作业中运行并成功运行。当我运行它的代码(应该与Spark代码做同样的事情)时,我得到了堆栈溢出错误。有什么想法吗?

这是代码:

import java.util.Arrays
        import org.apache.spark.mllib.linalg.{Vectors, Vector}
        import org.apache.spark.mllib.linalg._
        import org.apache.spark.mllib.linalg.distributed.RowMatrix
        import org.apache.spark.rdd.RDD
        import org.apache.spark.api.java.JavaRDD
        import breeze.linalg.{axpy => brzAxpy, inv, svd => brzSvd, DenseMatrix => BDM, DenseVector => BDV,
          MatrixSingularException, SparseVector => BSV, CSCMatrix => BSM, Matrix => BM}

        val EPSILON = {
            var eps = 1.0
            while ((1.0 + (eps / 2.0)) != 1.0) {
              eps /= 2.0
            }
            eps
          }

        def dot(x: Vector, y: Vector): Double = {
            require(x.size == y.size,
              "BLAS.dot(x: Vector, y:Vector) was given Vectors with non-matching sizes:" +
              " x.size = " + x.size + ", y.size = " + y.size)
            (x, y) match {
              case (dx: DenseVector, dy: DenseVector) =>
                dot(dx, dy)
              case (sx: SparseVector, dy: DenseVector) =>
                dot(sx, dy)
              case (dx: DenseVector, sy: SparseVector) =>
                dot(sy, dx)
              case (sx: SparseVector, sy: SparseVector) =>
                dot(sx, sy)
              case _ =>
                throw new IllegalArgumentException(s"dot doesn't support (${x.getClass}, ${y.getClass}).")
            }
         }

         def fastSquaredDistance(
              v1: Vector,
              norm1: Double,
              v2: Vector,
              norm2: Double,
              precision: Double = 1e-6): Double = {
            val n = v1.size
            require(v2.size == n)
            require(norm1 >= 0.0 && norm2 >= 0.0)
            val sumSquaredNorm = norm1 * norm1 + norm2 * norm2
            val normDiff = norm1 - norm2
            var sqDist = 0.0
            /*
             * The relative error is
             * <pre>
             * EPSILON * ( \|a\|_2^2 + \|b\\_2^2 + 2 |a^T b|) / ( \|a - b\|_2^2 ),
             * </pre>
             * which is bounded by
             * <pre>
             * 2.0 * EPSILON * ( \|a\|_2^2 + \|b\|_2^2 ) / ( (\|a\|_2 - \|b\|_2)^2 ).
             * </pre>
             * The bound doesn't need the inner product, so we can use it as a sufficient condition to
             * check quickly whether the inner product approach is accurate.
             */
            val precisionBound1 = 2.0 * EPSILON * sumSquaredNorm / (normDiff * normDiff + EPSILON)
            if (precisionBound1 < precision) {
              sqDist = sumSquaredNorm - 2.0 * dot(v1, v2)
            } else if (v1.isInstanceOf[SparseVector] || v2.isInstanceOf[SparseVector]) {
              val dotValue = dot(v1, v2)
              sqDist = math.max(sumSquaredNorm - 2.0 * dotValue, 0.0)
              val precisionBound2 = EPSILON * (sumSquaredNorm + 2.0 * math.abs(dotValue)) /
                (sqDist + EPSILON)
              if (precisionBound2 > precision) {
                sqDist = Vectors.sqdist(v1, v2)
              }
            } else {
              sqDist = Vectors.sqdist(v1, v2)
            }
            sqDist
        }

        def findClosest(
              centers: TraversableOnce[Vector],
              point: Vector): (Int, Double) = {
            var bestDistance = Double.PositiveInfinity
            var bestIndex = 0
            var i = 0
            centers.foreach { center =>
              // Since `\|a - b\| \geq |\|a\| - \|b\||`, we can use this lower bound to avoid unnecessary
              // distance computation.
              var lowerBoundOfSqDist = Vectors.norm(center, 2.0) - Vectors.norm(point, 2.0)
              lowerBoundOfSqDist = lowerBoundOfSqDist * lowerBoundOfSqDist
              if (lowerBoundOfSqDist < bestDistance) {
                val distance: Double = fastSquaredDistance(center, Vectors.norm(center, 2.0), point, Vectors.norm(point, 2.0))
                if (distance < bestDistance) {
                  bestDistance = distance
                  bestIndex = i
                }
              }
              i += 1
            }
            (bestIndex, bestDistance)
        }

         def pointCost(
              centers: TraversableOnce[Vector],
              point: Vector): Double =
            findClosest(centers, point)._2



        def clusterCentersIter: Iterable[Vector] =
            clusterCenters.map(p => p)


        def computeCostZep(indata: RDD[Vector]): Double = {
            val bcCenters = indata.context.broadcast(clusterCenters)
            indata.map(p => pointCost(bcCenters.value, p)).sum()
          }

        computeCostZep(projectedData)


我相信我正在使用所有相同的并行化作业作为spark,但是对我来说不起作用。关于分发/帮助我的代码的任何建议,看看为什么我的代码中会发生内存溢出,这将非常有帮助

这是一个非常类似spark的源代码链接:
KMeansModelKMeans

这是运行良好的代码:

val clusters = KMeans.train(projectedData, numClusters, numIterations)

val clusterCenters = clusters.clusterCenters




// Evaluate clustering by computing Within Set Sum of Squared Errors
val WSSSE = clusters.computeCost(projectedData)
println("Within Set Sum of Squared Errors = " + WSSSE)


错误输出如下:

org.apache.spark.SparkException:由于阶段失败而导致作业中止:94.0阶段中的任务1失败了4次,最近一次失败:94.0阶段中的任务1.3丢失(TID 37663,ip-172-31-13-209.ec2。内部):java.lang.StackOverflowError at $ iwC $$ iwC $$ iwC $$ iwC $ iwC $$ iwC $$ iwC $$ iwC $$ iwC $$ iwC $ iwC $$$$$$ c57ec8bf9b0d5f6161b97741d596ff0 $$ $$ wC $$ iwC $ iwC $$ iwC $ iwC $$ iwC $$ iwC $ iwC $ iwC $$ iwC $$ iwC $$ iwC $ iwC $$ iwC $$ iwC $$ iwC $$ iwC.dot(:226)at $ iwC $$ iwC $ iwC $$ iwC $$ iwC $ iwC $ iwC $$ iwC $$ iwC $ iwC $$ iwC $$$$$ c57ec8bf9b0d5f6161b97741d596ff0 $$$ $ wC $$ iwC $ iwC $ iwC $$ iwC $ iwC $$ iwC $ iwC $ iwC $ iwC $$ iwC $ iwC $ iwC $ iwC $$ iwC $ iwC $ iwC $ .dot(:226)
...

然后下来:

驱动程序堆栈跟踪:org.apache.spark.scheduler.DAGScheduler $$ anonfun $ abortStage $ 1在org.apache.spark.scheduler.DAGScheduler.org $ apache $ spark $ scheduler $ DAGScheduler $$ failJobAndIndependentStages(DAGScheduler.scala:1431)处。在org.apache.spark.scheduler.DAGScheduler $$ anonfun $ abortStage $ 1.apply(DAGScheduler.scala:1418)处应用(DAGScheduler.scala:1419)在scala.collection.mutable.ResizableArray $ class.foreach(ResizableArray.scala: 59)在org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)的scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)在org.apache.spark.scheduler.DAGScheduler $$ org.apache.spark.scheduler.DAGScheduler $$ anonfun $ handleTaskSetFailed $ 1.apply(DAGScheduler.scala:799)上的anonfun $ handleTaskSetFailed $ 1.apply(DAGScheduler.scala:799)在scala.Option.foreach(Option.scala:236) ),位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.org)上的org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)。 scala:1640)位于org.apache.spark.org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599),org.org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)位于org.apache.spark。 org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)上的.EventLoop $$ anon $ 1.run(EventLoop.scala:48)在org.apache.spark.SparkContext.runJob(SparkContext.scala:1832) )的org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)的org.apache.spark.rdd.RDD $$ anonfun $ fold $ 1.apply(RDD.scala:1088)的org.apache.spark。 org.apache.spark.rdd.RDDOperationScope $ .withScope(RDDOperationScope.scala:111)的rdd.RDDOperationScope $ .withScope(RDDOperationScope.scala:150)在org.apache.spark.rdd.RDD.withScope(RDD.scala): 316),位于org.apache.spark.rdd.RDD.fold(RDD.scala:1082),位于org.apache.spark.rdd.DoubleRDDFunctions $$ anonfun $ sum $ 1.apply $ mcD $ sp(DoubleRDDFunctions.scala:34)在org.apache.spark.rdd.DoubleRDDFunctions $$ anonfun $ sum $ 1.apply(DoubleRDDFunctions.scala:34)在o rg.apache.spark.rdd.DoubleRDDFunctions $$ anonfun $ sum $ 1.apply(DoubleRDDFunctions.scala:34)在org.apache.spark.rdd.RDDOperationScope $ .withScope(RDDOperationScope.scala:150)在org.apache.spark位于org.apache.spark.rdd.RDD.RDD.withScope(RDD.scala:316)的.rdd.RDDOperationScope $ .withScope(RDDOperationScope.scala:111),位于org.apache.spark.rdd.DoubleRDDFunctions.sum(DoubleRDDFunctions.scala: 33)

最佳答案

似乎很简单:正在发生什么:您在这里递归调用dot方法:

def dot(x: Vector, y: Vector): Double = {
        require(x.size == y.size,
          "BLAS.dot(x: Vector, y:Vector) was given Vectors with non-matching sizes:" +
          " x.size = " + x.size + ", y.size = " + y.size)
        (x, y) match {
          case (dx: DenseVector, dy: DenseVector) =>
            dot(dx, dy)
          case (sx: SparseVector, dy: DenseVector) =>
            dot(sx, dy)
          case (dx: DenseVector, sy: SparseVector) =>
            dot(sy, dx)
          case (sx: SparseVector, sy: SparseVector) =>
            dot(sx, sy)
          case _ =>
            throw new IllegalArgumentException(s"dot doesn't support (${x.getClass}, ${y.getClass}).")
        }
     }


后续对dot的递归调用与前者具有相同的参数-因此,递归永远不会得出结论。

stacktrace也会告诉您-注意位置在点方法中:

$ iwC $$ iwC $$ iwC $$ iwC $$ iwC $ iwC $$ iwC $$ iwC $$ iwC $ iwC $$ iwC $$$$$ c57ec8bf9b0d5f6161b97741d596ff0 $$ w $$ iwC $$ iwC $ iwC $ iwC $ iwC $$ iwC $ iwC $ iwC $ iwC $ iwC $$ iwC $ iwC $ iwC $ iwC $ iwC $$ iwC.dot (:226)在

08-24 22:19