[
https://issues.apache.org/jira/browse/SPARK-4130?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Joseph E. Gonzalez updated SPARK-4130:
--------------------------------------
Description:
When testing MLlib on the splice site data
(http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#splice-site)
the loadSVM. To reproduce in spark shell:
```
import org.apache.spark.mllib.util.MLUtils
val data = MLUtils.loadLibSVMFile(sc,
"hdfs://ec2-54-200-69-227.us-west-2.compute.amazonaws.com:9000/splice_site.t")
```
generates the error:
```
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:73
failed 4 times, most recent failure: Exception failure in TID 335 on host
ip-172-31-31-54.us-west-2.compute.internal: java.lang.NumberFormatException:
For input string: ""
java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
java.lang.Integer.parseInt(Integer.java:504)
java.lang.Integer.parseInt(Integer.java:527)
scala.collection.immutable.StringLike$class.toInt(StringLike.scala:229)
scala.collection.immutable.StringOps.toInt(StringOps.scala:31)
org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:81)
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$$anon$11.next(Iterator.scala:328)
scala.collection.Iterator$class.foreach(Iterator.scala:727)
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:107)
org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
org.apache.spark.rdd.MappedRDD.compute(MappedRDD.scala:31)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111)
org.apache.spark.scheduler.Task.run(Task.scala:51)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
```
was:
When testing MLlib on the splice site data
(http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#splice-site)
the loadSVM. To reproduce in spark shell:
import org.apache.spark.mllib.util.MLUtils
val data = MLUtils.loadLibSVMFile(sc,
"hdfs://ec2-54-200-69-227.us-west-2.compute.amazonaws.com:9000/splice_site.t")
generates the error:
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:73
failed 4 times, most recent failure: Exception failure in TID 335 on host
ip-172-31-31-54.us-west-2.compute.internal: java.lang.NumberFormatException:
For input string: ""
java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
java.lang.Integer.parseInt(Integer.java:504)
java.lang.Integer.parseInt(Integer.java:527)
scala.collection.immutable.StringLike$class.toInt(StringLike.scala:229)
scala.collection.immutable.StringOps.toInt(StringOps.scala:31)
org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:81)
org.apache.spark.mllib.util.MLUtils$$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$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
> loadLibSVMFile does not handle extra whitespace
> -----------------------------------------------
>
> Key: SPARK-4130
> URL: https://issues.apache.org/jira/browse/SPARK-4130
> Project: Spark
> Issue Type: Bug
> Components: MLlib
> Reporter: Joseph E. Gonzalez
>
> When testing MLlib on the splice site data
> (http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#splice-site)
> the loadSVM. To reproduce in spark shell:
> ```
> import org.apache.spark.mllib.util.MLUtils
> val data = MLUtils.loadLibSVMFile(sc,
> "hdfs://ec2-54-200-69-227.us-west-2.compute.amazonaws.com:9000/splice_site.t")
> ```
> generates the error:
> ```
> org.apache.spark.SparkException: Job aborted due to stage failure: Task
> 0.0:73 failed 4 times, most recent failure: Exception failure in TID 335 on
> host ip-172-31-31-54.us-west-2.compute.internal:
> java.lang.NumberFormatException: For input string: ""
>
> java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
> java.lang.Integer.parseInt(Integer.java:504)
> java.lang.Integer.parseInt(Integer.java:527)
>
> scala.collection.immutable.StringLike$class.toInt(StringLike.scala:229)
> scala.collection.immutable.StringOps.toInt(StringOps.scala:31)
>
> org.apache.spark.mllib.util.MLUtils$$anonfun$4$$anonfun$5.apply(MLUtils.scala:81)
>
> 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:745)
> ```
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
