Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/7454#issuecomment-123165239
I think there's a bug. I tried running the LDAExample as follows, and it
failed with the following exception:
I ran:
```
bin/run-example mllib.LDAExample docs/*.md --maxIterations 2 --algorithm
online --vocabSize 10 --k 3
```
and got the exception:
```
6 had an illegal value 6 had an illegal value
15/07/20 22:20:57 WARN TaskSetManager: Lost task 8.0 in stage 12.0 (TID
395, localhost): java.lang.Error
at org.j_paine.formatter.FormatParser.<init>(FormatParser.java:353)
at org.j_paine.formatter.FormatParser.<init>(FormatParser.java:346)
at org.j_paine.formatter.Parsers.<init>(Formatter.java:1748)
at org.j_paine.formatter.Parsers.theParsers(Formatter.java:1739)
at org.j_paine.formatter.Format.<init>(Formatter.java:177)
at org.j_paine.formatter.Formatter.<init>(Formatter.java:30)
at org.netlib.util.Util.f77write(Util.java:429)
at org.netlib.err.Xerbla.xerbla(err.f)
at org.netlib.blas.Dgemv.dgemv(blas.f)
at com.github.fommil.netlib.F2jBLAS.dgemv(F2jBLAS.java:106)
at
breeze.linalg.operators.DenseMatrixMultiplyStuff$implOpMulMatrix_DMD_DVD_eq_DVD$.apply(DenseMatrixOps.scala:80)
at
breeze.linalg.operators.DenseMatrixMultiplyStuff$implOpMulMatrix_DMD_DVD_eq_DVD$.apply(DenseMatrixOps.scala:72)
at breeze.linalg.ImmutableNumericOps$class.$times(NumericOps.scala:135)
at breeze.linalg.De ** On entry to
nseMatrix.$times(DenseMatrix.scala:53)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8$$anonfun$apply$4.apply(LDAOptimizer.scala:395)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8$$anonfun$apply$4.apply(LDAOptimizer.scala:380)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at
org.apache.spark.util.random.GapSamplingReplacementIterator.foreach(RandomSampler.scala:271)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8.apply(LDAOptimizer.scala:380)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8.apply(LDAOptimizer.scala:378)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDDGEMV parameter number 6 had
an illegal value
D.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
** On entry to DGEMV parameter number 6 had an illegal value
15/07/20 22:20:57 ERROR TaskSetManager: Task 8 in stage 12.0 failed 1
times; aborting job
Exception in thread "main" org.apache.spark.SparkException: Job aborted due
to stage failure: Task 8 in stage 12.0 failed 1 times, most recent failure:
Lost task 8.0 in stage 12.0 (TID 395, localhost): java.lang.Error
at org.j_paine.formatter.FormatParser.<init>(FormatParser.java:353)
at org.j_paine.formatter.FormatParser.<init>(FormatParser.java:346)
at org.j_paine.formatter.Parsers.<init>(Formatter.java:1748)
at org.j_paine.formatter.Parsers.theParsers(Formatter.java:1739)
at org.j_paine.formatter.Format.<init>(Formatter.java:177)
at org.j_paine.formatter.Formatter.<init>(Formatter.java:30)
at org.netlib.util.Util.f77write(Util.java:429)
at org.netlib.err.Xerbla.xerbla(err.f)
at org.netlib.blas.Dgemv.dgemv(blas.f)
at com.github.fommil.netlib.F2jBLAS.dgemv(F2jBLAS.java:106)
at
breeze.linalg.operators.DenseMatrixMultiplyStuff$implOpMulMatrix_DMD_DVD_eq_DVD$.apply(DenseMatrixOps.scala:80)
at
breeze.linalg.operators.DenseMatrixMultiplyStuff$implOpMulMatrix_DMD_DVD_eq_DVD$.apply(DenseMatrixOps.scala:72)
at breeze.linalg.ImmutableNumericOps$class.$times(NumericOps.scala:135)
at breeze.linalg.DenseMatrix.$times(DenseMatrix.scala:53)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8$$anonfun$apply$4.apply(LDAOptimizer.scala:395)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8$$anonfun$apply$4.apply(LDAOptimizer.scala:380)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at
org.apache.spark.util.random.GapSamplingReplacementIterator.foreach(RandomSampler.scala:271)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8.apply(LDAOptimizer.scala:380)
at
org.apache.spark.mllib.clustering.OnlineLDAOptimizer$$anonfun$8.apply(LDAOptimizer.scala:378)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1295)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1286)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1285)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1285)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:752)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:752)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:752)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1506)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1467)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1456)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
