[
https://issues.apache.org/jira/browse/SPARK-17890?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15572217#comment-15572217
]
Khalid Reid edited comment on SPARK-17890 at 10/13/16 3:30 PM:
---------------------------------------------------------------
Hi Sean,
I've created a small project [here|https://github.com/khalidr/Spark_17890] to
reproduce the error using spark-submit. I noticed that things work fine when
using an RDD but fails when I use a DataFrame.
{code}
object Main extends App{
val conf = new SparkConf()
conf.setMaster("local")
val session = SparkSession.builder()
.config(conf)
.getOrCreate()
import session.implicits._
val df = session.sparkContext.parallelize(List(1,2,3)).toDF
println("flatmapping ...")
df.flatMap(_ => Seq.empty[Foo])
println("mapping...")
df.map(_ => Seq.empty[Foo]) //spark-submit fails here. Things work if I
remove the toDF call
}
case class Foo(value:String)
{code}
{noformat}
Exception in thread "main" scala.ScalaReflectionException: class Foo not found.
at
scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:123)
at
scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:22)
at Main$$typecreator3$1.apply(Main.scala:21)
at
scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
at
org.apache.spark.sql.SQLImplicits$$typecreator9$1.apply(SQLImplicits.scala:125)
at
scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$.apply(ExpressionEncoder.scala:49)
at
org.apache.spark.sql.SQLImplicits.newProductSeqEncoder(SQLImplicits.scala:125)
at Main$.delayedEndpoint$Main$1(Main.scala:21)
at Main$delayedInit$body.apply(Main.scala:5)
at scala.Function0$class.apply$mcV$sp(Function0.scala:34)
at
scala.runtime.AbstractFunction0.apply$mcV$sp(AbstractFunction0.scala:12)
at scala.App$$anonfun$main$1.apply(App.scala:76)
at scala.App$$anonfun$main$1.apply(App.scala:76)
at scala.collection.immutable.List.foreach(List.scala:381)
at
scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:35)
at scala.App$class.main(App.scala:76)
at Main$.main(Main.scala:5)
at Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:483)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
{noformat}
was (Author: kor):
Hi Sean,
I've created a small project [here|https://github.com/khalidr/Spark_17890] to
reproduce the error using spark-submit. I noticed that things work fine when
using an RDD but fails when I use a DataFrame.
{code}
object Main extends App{
val conf = new SparkConf()
conf.setMaster("local")
val session = SparkSession.builder()
.config(conf)
.getOrCreate()
import session.implicits._
val df = session.sparkContext.parallelize(List(1,2,3)).toDF
println("flatmapping ...")
df.flatMap(_ => Seq.empty[Foo])
println("mapping...")
df.map(_ => Seq.empty[Foo]) //spark-submit fails here
}
case class Foo(value:String)
{code}
{noformat}
Exception in thread "main" scala.ScalaReflectionException: class Foo not found.
at
scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:123)
at
scala.reflect.internal.Mirrors$RootsBase.staticClass(Mirrors.scala:22)
at Main$$typecreator3$1.apply(Main.scala:21)
at
scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
at
org.apache.spark.sql.SQLImplicits$$typecreator9$1.apply(SQLImplicits.scala:125)
at
scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$.apply(ExpressionEncoder.scala:49)
at
org.apache.spark.sql.SQLImplicits.newProductSeqEncoder(SQLImplicits.scala:125)
at Main$.delayedEndpoint$Main$1(Main.scala:21)
at Main$delayedInit$body.apply(Main.scala:5)
at scala.Function0$class.apply$mcV$sp(Function0.scala:34)
at
scala.runtime.AbstractFunction0.apply$mcV$sp(AbstractFunction0.scala:12)
at scala.App$$anonfun$main$1.apply(App.scala:76)
at scala.App$$anonfun$main$1.apply(App.scala:76)
at scala.collection.immutable.List.foreach(List.scala:381)
at
scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:35)
at scala.App$class.main(App.scala:76)
at Main$.main(Main.scala:5)
at Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:483)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
{noformat}
> scala.ScalaReflectionException
> ------------------------------
>
> Key: SPARK-17890
> URL: https://issues.apache.org/jira/browse/SPARK-17890
> Project: Spark
> Issue Type: Bug
> Affects Versions: 2.0.1
> Environment: x86_64 GNU/Linux
> Java(TM) SE Runtime Environment (build 1.8.0_60-b27)
> Reporter: Khalid Reid
> Priority: Minor
> Labels: newbie
>
> Hello,
> I am seeing an error message in spark-shell when I map a DataFrame to a
> Seq\[Foo\]. However, things work fine when I use flatMap.
> {noformat}
> scala> case class Foo(value:String)
> defined class Foo
> scala> val df = sc.parallelize(List(1,2,3)).toDF
> df: org.apache.spark.sql.DataFrame = [value: int]
> scala> df.map{x => Seq.empty[Foo]}
> scala.ScalaReflectionException: object $line14.$read not found.
> at scala.reflect.internal.Mirrors$RootsBase.staticModule(Mirrors.scala:162)
> at scala.reflect.internal.Mirrors$RootsBase.staticModule(Mirrors.scala:22)
> at $typecreator1$1.apply(<console>:29)
> at
> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
> at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
> at
> org.apache.spark.sql.SQLImplicits$$typecreator9$1.apply(SQLImplicits.scala:125)
> at
> scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe$lzycompute(TypeTags.scala:232)
> at scala.reflect.api.TypeTags$WeakTypeTagImpl.tpe(TypeTags.scala:232)
> at
> org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$.apply(ExpressionEncoder.scala:49)
> at
> org.apache.spark.sql.SQLImplicits.newProductSeqEncoder(SQLImplicits.scala:125)
> ... 48 elided
> scala> df.flatMap{_ => Seq.empty[Foo]} //flatMap works
> res2: org.apache.spark.sql.Dataset[Foo] = [value: string]
> {noformat}
> I am seeing the same error reported
> [here|https://issues.apache.org/jira/browse/SPARK-8465?jql=text%20~%20%22scala.ScalaReflectionException%22]
> when I use spark-submit.
> I am new to Spark but I don't expect this to throw an exception.
> Thanks.
--
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
