Hi Sameer, This seems to be a file format issue. Can you make sure that your data satisfies the format?
Each line of libsvm format is as follows: <label> <index1>:<value1> <index2>:<value2> ... Thanks, Liquan On Wed, Sep 24, 2014 at 3:02 PM, Sameer Tilak <ssti...@live.com> wrote: > Hi All, > > > When I try to load dataset using MLUtils.loadLibSVMFile, I have the > following problem. Any help will be greatly appreciated! > > > > Code snippet: > > > import org.apache.spark.mllib.regression.LabeledPoint > > import org.apache.spark.mllib.util.MLUtils > > import org.apache.spark.rdd.RDD > > import org.apache.spark.mllib.regression.LinearRegressionWithSGD > > > val examples: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc > ,"structured/results/data.txt") > > > stacktrace: > > > 14/09/24 15:00:49 ERROR Executor: Exception in task ID 0 > java.lang.ArrayIndexOutOfBoundsException: 1 > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:82) > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:79) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:79) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:76) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$class.foreach(Iterator.scala:727) > at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) > at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) > at > scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) > at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:227) > at org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) > at org.apache.spark.scheduler.Task.run(Task.scala:51) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:744) > 14/09/24 15:00:49 ERROR Executor: Exception in task ID 1 > java.lang.ArrayIndexOutOfBoundsException: 1 > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:82) > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:79) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:79) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:76) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$class.foreach(Iterator.scala:727) > at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) > at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) > at > scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) > at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:227) > at org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) > at org.apache.spark.scheduler.Task.run(Task.scala:51) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:744) > 14/09/24 15:00:49 WARN TaskSetManager: Lost TID 0 (task 0.0:0) > 14/09/24 15:00:49 WARN TaskSetManager: Loss was due to > java.lang.ArrayIndexOutOfBoundsException > java.lang.ArrayIndexOutOfBoundsException: 1 > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:82) > at > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:79) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:79) > at org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:76) > at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > at scala.collection.Iterator$class.foreach(Iterator.scala:727) > at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) > at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) > at > scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) > at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:227) > at org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31) > at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) > at org.apache.spark.rdd.RDD.iterator(RDD.scala:229) > at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) > at org.apache.spark.scheduler.Task.run(Task.scala:51) > at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:744) > 14/09/24 15:00:49 ERROR TaskSetManager: Task 0.0:0 failed 1 times; > aborting job > 14/09/24 15:00:49 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks > have all completed, from pool > 14/09/24 15:00:49 INFO DAGScheduler: Failed to run reduce at > MLUtils.scala:95 > 14/09/24 15:00:49 INFO TaskSchedulerImpl: Cancelling stage 0 > 14/09/24 15:00:49 INFO TaskSetManager: Loss was due to > java.lang.ArrayIndexOutOfBoundsException: 1 [duplicate 1] > 14/09/24 15:00:49 INFO TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks > have all completed, from pool > org.apache.spark.SparkException: Job aborted due to stage failure: Task > 0.0:0 failed 1 times, most recent failure: Exception failure in TID 0 on > host localhost: java.lang.ArrayIndexOutOfBoundsException: 1 > > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:82) > > org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:79) > > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > > scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108) > > org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:79) > > org.apache.spark.mllib.util.MLUtils$$anonfun$4.apply(MLUtils.scala:76) > scala.collection.Iterator$$anon$11.next(Iterator.scala:328) > scala.collection.Iterator$class.foreach(Iterator.scala:727) > scala.collection.AbstractIterator.foreach(Iterator.scala:1157) > > scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) > > scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) > org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107) > org.apache.spark.rdd.RDD.iterator(RDD.scala:227) > org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31) > org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) > org.apache.spark.rdd.RDD.iterator(RDD.scala:229) > org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) > org.apache.spark.scheduler.Task.run(Task.scala:51) > > org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) > > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > java.lang.Thread.run(Thread.java:744) > Driver stacktrace: > at org.apache.spark.scheduler.DAGScheduler.org > $apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) > at > org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) > at > org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) > at scala.Option.foreach(Option.scala:236) > at > org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633) > at > org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207) > at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) > at akka.actor.ActorCell.invoke(ActorCell.scala:456) > at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) > at akka.dispatch.Mailbox.run(Mailbox.scala:219) > at > akka.dispatch.ForkJoinExecutorConfigurator$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) > -- Liquan Pei Department of Physics University of Massachusetts Amherst
