Hi All, I am trying to run the spark example JavaDecisionTree code using some external data set. It works for certain dataset only with specific maxBins and maxDepth settings. Even for a working dataset if I add a new data item I get a ArrayIndexOutOfBounds Exception, I get the same exception for the first case as well (changing maxBins and maxDepth). I am not sure what is wrong here, can anyone please explain this.
Exception stacktrace: 14/10/21 13:47:15 ERROR executor.Executor: Exception in task 1.0 in stage 7.0 (TID 13) java.lang.ArrayIndexOutOfBoundsException: 6301 at org.apache.spark.mllib.tree.DecisionTree$.updateBinForOrderedFeature$1(DecisionTree.scala:648) at org.apache.spark.mllib.tree.DecisionTree$.binaryOrNotCategoricalBinSeqOp$1(DecisionTree.scala:706) at org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:798) at org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) at org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28) at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) at org.apache.spark.InterruptibleIterator.foldLeft(InterruptibleIterator.scala:28) at scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) at org.apache.spark.InterruptibleIterator.aggregate(InterruptibleIterator.scala:28) at org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) at org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) at org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) at org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62) at org.apache.spark.scheduler.Task.run(Task.scala:54) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) 14/10/21 13:47:15 WARN scheduler.TaskSetManager: Lost task 1.0 in stage 7.0 (TID 13, localhost): java.lang.ArrayIndexOutOfBoundsException: 6301 org.apache.spark.mllib.tree.DecisionTree$.updateBinForOrderedFeature$1(DecisionTree.scala:648) org.apache.spark.mllib.tree.DecisionTree$.binaryOrNotCategoricalBinSeqOp$1(DecisionTree.scala:706) org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:798) org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.Iterator$class.foreach(Iterator.scala:727) org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28) scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) org.apache.spark.InterruptibleIterator.foldLeft(InterruptibleIterator.scala:28) scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) org.apache.spark.InterruptibleIterator.aggregate(InterruptibleIterator.scala:28) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62) org.apache.spark.scheduler.Task.run(Task.scala:54) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) java.lang.Thread.run(Thread.java:745) 14/10/21 13:47:15 ERROR scheduler.TaskSetManager: Task 1 in stage 7.0 failed 1 times; aborting job 14/10/21 13:47:15 INFO scheduler.TaskSchedulerImpl: Removed TaskSet 7.0, whose tasks have all completed, from pool 14/10/21 13:47:15 INFO scheduler.TaskSchedulerImpl: Cancelling stage 7 14/10/21 13:47:15 INFO scheduler.DAGScheduler: Failed to run reduce at RDDFunctions.scala:111 org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 7.0 failed 1 times, most recent failure: Lost task 1.0 in stage 7.0 (TID 13, localhost): java.lang.ArrayIndexOutOfBoundsException: 6301 org.apache.spark.mllib.tree.DecisionTree$.updateBinForOrderedFeature$1(DecisionTree.scala:648) org.apache.spark.mllib.tree.DecisionTree$.binaryOrNotCategoricalBinSeqOp$1(DecisionTree.scala:706) org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:798) org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) org.apache.spark.mllib.tree.DecisionTree$$anonfun$3.apply(DecisionTree.scala:830) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.Iterator$class.foreach(Iterator.scala:727) org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28) scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) org.apache.spark.InterruptibleIterator.foldLeft(InterruptibleIterator.scala:28) scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) org.apache.spark.InterruptibleIterator.aggregate(InterruptibleIterator.scala:28) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$4.apply(RDDFunctions.scala:99) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) org.apache.spark.mllib.rdd.RDDFunctions$$anonfun$5.apply(RDDFunctions.scala:100) org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596) org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62) org.apache.spark.scheduler.Task.run(Task.scala:54) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:177) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1185) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1174) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1173) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1173) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:688) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:688) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1391) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386) at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/Spark-MLLIB-Decision-Tree-ArrayIndexOutOfBounds-Exception-tp16907.html Sent from the Apache Spark User List mailing list archive at Nabble.com. --------------------------------------------------------------------- To unsubscribe, e-mail: user-unsubscr...@spark.apache.org For additional commands, e-mail: user-h...@spark.apache.org