// :: ERROR Executor: Exception in task 0.0 in stage 0.0 (TID )

java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V

    at Person.<init>(RDD_To_DataFrame.scala:)

    at RDD_To_DataFrame$.$anonfun$main$(RDD_To_DataFrame.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)

    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:)

    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$$$anon$.hasNext(WholeStageCodegenExec.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:)

    at org.apache.spark.rdd.RDD.iterator(RDD.scala:)

    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:)

    at org.apache.spark.scheduler.Task.run(Task.scala:)

    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:)

    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:)

    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:)

    at java.lang.Thread.run(Thread.java:)

// :: ERROR TaskSetManager: Task  in stage 0.0 failed  times; aborting job

Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task  in stage 0.0 failed  times, most recent failure: Lost task 0.0 in stage 0.0 (TID , localhost, executor driver): java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V

    at Person.<init>(RDD_To_DataFrame.scala:)

    at RDD_To_DataFrame$.$anonfun$main$(RDD_To_DataFrame.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)

    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:)

    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$$$anon$.hasNext(WholeStageCodegenExec.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:)

    at org.apache.spark.rdd.RDD.iterator(RDD.scala:)

    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:)

    at org.apache.spark.scheduler.Task.run(Task.scala:)

    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:)

    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:)

    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:)

    at java.lang.Thread.run(Thread.java:)

Driver stacktrace:

    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$.apply(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$.apply(DAGScheduler.scala:)

    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:)

    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:)

    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$.apply(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$.apply(DAGScheduler.scala:)

    at scala.Option.foreach(Option.scala:)

    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:)

    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:)

    at org.apache.spark.util.EventLoop$$anon$.run(EventLoop.scala:)

    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:)

    at org.apache.spark.SparkContext.runJob(SparkContext.scala:)

    at org.apache.spark.SparkContext.runJob(SparkContext.scala:)

    at org.apache.spark.SparkContext.runJob(SparkContext.scala:)

    at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:)

    at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:)

    at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:)

    at org.apache.spark.sql.Dataset$$anonfun$head$.apply(Dataset.scala:)

    at org.apache.spark.sql.Dataset$$anonfun$head$.apply(Dataset.scala:)

    at org.apache.spark.sql.Dataset$$anonfun$.apply(Dataset.scala:)

    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:)

    at org.apache.spark.sql.Dataset.withAction(Dataset.scala:)

    at org.apache.spark.sql.Dataset.head(Dataset.scala:)

    at org.apache.spark.sql.Dataset.take(Dataset.scala:)

    at org.apache.spark.sql.Dataset.showString(Dataset.scala:)

    at org.apache.spark.sql.Dataset.show(Dataset.scala:)

    at org.apache.spark.sql.Dataset.show(Dataset.scala:)

    at org.apache.spark.sql.Dataset.show(Dataset.scala:)

    at RDD_To_DataFrame$.main(RDD_To_DataFrame.scala:)

    at RDD_To_DataFrame.main(RDD_To_DataFrame.scala)

    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)

    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:)

    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:)

    at java.lang.reflect.Method.invoke(Method.java:)

    at com.intellij.rt.execution.application.AppMain.main(AppMain.java:)

Caused by: java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V

    at Person.<init>(RDD_To_DataFrame.scala:)

    at RDD_To_DataFrame$.$anonfun$main$(RDD_To_DataFrame.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at scala.collection.Iterator$$anon$.next(Iterator.scala:)

    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)

    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:)

    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$$$anon$.hasNext(WholeStageCodegenExec.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.sql.execution.SparkPlan$$anonfun$.apply(SparkPlan.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$$$anonfun$apply$.apply(RDD.scala:)

    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:)

    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:)

    at org.apache.spark.rdd.RDD.iterator(RDD.scala:)

    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:)

    at org.apache.spark.scheduler.Task.run(Task.scala:)

    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:)

    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:)

    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:)

    at java.lang.Thread.run(Thread.java:)

Error:(, ) No TypeTag available for (Array[String],)

        val documentDF= spark.createDataFrame(Seq(

val df= spark.createDataFrame(Seq(

         (,Array("soyo","spark","soyo2","soyo","")),

         (,Array("soyo","hadoop","soyo","hadoop","xiaozhou","soyo2","spark","","")),

         (,Array("soyo","spark","soyo2","hadoop","soyo3","")),

         (,Array("soyo","spark","soyo20","hadoop","soyo2","","")),

         (,Array("soyo","","spark","","spark","spark",""))

       )).toDF("id","words")