I’m using Spark 1.6.1
Class is case class DistinctValues(statType: Int, dataType: Int, _id: Int,
values: Array[(String, Long)], numOfMembers: Int,category: String)
and
error for newGnsDS.joinWith(newGnsDS, $"dataType”)
Exception in thread "main" org.apache.spark.sql.AnalysisException: cannot
resolve 'dataType' given input columns: [countUnique, median, recentEdid, max,
cdid, dataType, firstQuarter, sigma, replicationRateAvg, thirdQuarter,
accCount, avg, countNotNull, statType, categoryId, category, min, numRows,
numDistinctRows];
error for newGnsDS.as("a").joinWith(newGnsDS.as("b"), $"a.dataType" ===
$"b.datatype”)
Exception in thread "main" org.apache.spark.sql.AnalysisException: cannot
resolve 'a.dataType' given input columns: [countUnique, median, recentEdid,
max, cdid, dataType, firstQuarter, sigma, replicationRateAvg, thirdQuarter,
accCount, avg, countNotNull, statType, categoryId, category, min, numRows,
numDistinctRows];
Common error
at
org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:60)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:57)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:335)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:335)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:334)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:332)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:332)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:281)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:321)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:332)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:108)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:119)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:127)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:127)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:57)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:50)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:121)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:120)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:120)
at scala.collection.immutable.List.foreach(List.scala:318)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:120)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:120)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:120)
at scala.collection.immutable.List.foreach(List.scala:318)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:120)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:50)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:44)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:34)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData$lzycompute(QueryExecution.scala:39)
at
org.apache.spark.sql.execution.QueryExecution.withCachedData(QueryExecution.scala:38)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:43)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:43)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:47)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:45)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:52)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:52)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:704)
at org.apache.spark.sql.Dataset.take(Dataset.scala:725)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:240)
at org.apache.spark.sql.Dataset.show(Dataset.scala:230)
at org.apache.spark.sql.Dataset.show(Dataset.scala:193)
at org.apache.spark.sql.Dataset.show(Dataset.scala:201)
at dblab.lod.sw.Main$.main(Main.scala:1251)
at dblab.lod.sw.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:497)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
