Hi all,
I'm trying to use the new LDA in mllib, but when trying to train the model,
I'm getting following error:
java.lang.IllegalAccessError: tried to access class
org.apache.spark.util.collection.Sorter from class
org.apache.spark.graphx.impl.EdgePartitionBuilder
at
org.apache.spark.graphx.impl.EdgePartitionBuilder.toEdgePartition(EdgePartitionBuilder.scala:39)
at org.apache.spark.graphx.EdgeRDD$$anonfun$1.apply(EdgeRDD.scala:109)
Has anyone seen this yet and has an idea what might be the problem?
It happens both with the provided sample data and with my own corpus.
Full code + more stack below.
Thx and Regards,
Jeff
Code:
------------------
object LdaTest {
def main(args: Array[String]) = {
val conf = new SparkConf().setAppName("LDA").setMaster("local[4]")
val sc = new SparkContext(conf)
// val data =
scala.io.Source.fromFile("/home/jeff/nmf_compare/scikit_v.txt").getLines().toList
// val parsedData = data.map(s => Vectors.dense(s.trim().split("
").map(_.toDouble)))
// val corpus = parsedData.zipWithIndex.map( t => (t._2.toLong, t._1) )
//val data = sc.textFile("/home/jeff/nmf_compare/scikit_v.txt")
val data =
sc.textFile("/home/jeff/Downloads/spark-1.3.0-bin-hadoop2.4/data/mllib/sample_lda_data.txt")
val parsedData = data.map(s => Vectors.dense(s.trim().split("
").map(_.toDouble)))
val corpus = parsedData.zipWithIndex.map(_.swap).cache()
// val parCorpus = sc.parallelize(corpus)
// println(parCorpus)
val ldaModel = new LDA().setK(10).run(corpus)
println(ldaModel)
}
}
Stack:
----------------
...
15/03/17 09:48:50 INFO spark.CacheManager: Partition rdd_8_0 not found,
computing it
15/03/17 09:48:50 INFO spark.CacheManager: Partition rdd_8_1 not found,
computing it
15/03/17 09:48:50 INFO spark.CacheManager: Another thread is loading
rdd_8_0, waiting for it to finish...
15/03/17 09:48:50 INFO storage.BlockManager: Found block rdd_4_0 locally
15/03/17 09:48:50 INFO spark.CacheManager: Partition rdd_4_1 not found,
computing it
15/03/17 09:48:50 INFO spark.CacheManager: Another thread is loading
rdd_8_1, waiting for it to finish...
15/03/17 09:48:50 INFO rdd.HadoopRDD: Input split:
file:/home/jeff/Downloads/spark-1.3.0-bin-hadoop2.4/data/mllib/sample_lda_data.txt:132+132
15/03/17 09:48:50 INFO storage.MemoryStore: ensureFreeSpace(1048) called
with curMem=47264, maxMem=1965104824
15/03/17 09:48:50 INFO spark.CacheManager: Finished waiting for rdd_8_0
15/03/17 09:48:50 ERROR executor.Executor: Exception in task 0.0 in stage
3.0 (TID 3)
java.lang.IllegalAccessError: tried to access class
org.apache.spark.util.collection.Sorter from class
org.apache.spark.graphx.impl.EdgePartitionBuilder
at
org.apache.spark.graphx.impl.EdgePartitionBuilder.toEdgePartition(EdgePartitionBuilder.scala:39)
at org.apache.spark.graphx.EdgeRDD$$anonfun$1.apply(EdgeRDD.scala:109)
at org.apache.spark.graphx.EdgeRDD$$anonfun$1.apply(EdgeRDD.scala:104)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:609)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:609)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:61)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:227)
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.graphx.EdgeRDD.compute(EdgeRDD.scala:49)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
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.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
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:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
15/03/17 09:48:50 INFO spark.CacheManager: Whoever was loading rdd_8_0
failed; we'll try it ourselves
15/03/17 09:48:50 INFO storage.MemoryStore: Block rdd_4_1 stored as values
in memory (estimated size 1048.0 B, free 1874.0 MB)
15/03/17 09:48:50 INFO spark.CacheManager: Partition rdd_8_0 not found,
computing it
15/03/17 09:48:50 INFO storage.BlockManagerInfo: Added rdd_4_1 in memory on
10.2.200.66:51465 (size: 1048.0 B, free: 1874.1 MB)
15/03/17 09:48:50 INFO storage.BlockManager: Found block rdd_4_0 locally
15/03/17 09:48:50 INFO storage.BlockManagerMaster: Updated info of block
rdd_4_1
15/03/17 09:48:50 ERROR executor.Executor: Exception in task 0.0 in stage
5.0 (TID 5)
java.lang.IllegalAccessError: org/apache/spark/util/collection/Sorter
at
org.apache.spark.graphx.impl.EdgePartitionBuilder.toEdgePartition(EdgePartitionBuilder.scala:39)
at org.apache.spark.graphx.EdgeRDD$$anonfun$1.apply(EdgeRDD.scala:109)
at org.apache.spark.graphx.EdgeRDD$$anonfun$1.apply(EdgeRDD.scala:104)
...
