i noticed some things stopped working on datasets in spark 2.0.0-SNAPSHOT, and with a confusing error message (cannot resolved some column with input columns []).
for example in 1.6.0-SNAPSHOT: scala> val ds = sc.parallelize(1 to 10).toDS ds: org.apache.spark.sql.Dataset[Int] = [value: int] scala> ds.map(x => Option(x)) res0: org.apache.spark.sql.Dataset[Option[Int]] = [value: int] and same commands in 2.0.0-SNAPSHOT: scala> val ds = sc.parallelize(1 to 10).toDS ds: org.apache.spark.sql.Dataset[Int] = [value: int] scala> ds.map(x => Option(x)) org.apache.spark.sql.AnalysisException: cannot resolve 'value' given input columns: []; 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$$anonfun$transformUp$1.apply(TreeNode.scala:284) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:284) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:283) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:162) at org.apache.spark.sql.catalyst.plans.QueryPlan.org $apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:172) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:176) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) at scala.collection.immutable.List.foreach(List.scala:381) at scala.collection.TraversableLike$class.map(TraversableLike.scala:245) at scala.collection.immutable.List.map(List.scala:285) at org.apache.spark.sql.catalyst.plans.QueryPlan.org $apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:176) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:181) at scala.collection.Iterator$$anon$11.next(Iterator.scala:370) at scala.collection.Iterator$class.foreach(Iterator.scala:742) at scala.collection.AbstractIterator.foreach(Iterator.scala:1194) at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48) at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:308) at scala.collection.AbstractIterator.to(Iterator.scala:1194) at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:300) at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1194) at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:287) at scala.collection.AbstractIterator.toArray(Iterator.scala:1194) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:181) 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:122) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:121) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreachUp$1.apply(TreeNode.scala:121) at scala.collection.immutable.List.foreach(List.scala:381) at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:121) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:50) at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:46) at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.resolve(ExpressionEncoder.scala:322) at org.apache.spark.sql.Dataset.<init>(Dataset.scala:81) at org.apache.spark.sql.Dataset.<init>(Dataset.scala:92) at org.apache.spark.sql.Dataset.mapPartitions(Dataset.scala:339) at org.apache.spark.sql.Dataset.map(Dataset.scala:323) ... 43 elided i observed similar issues with user defined types (org.apache.spark.sql.types.UserDefinedType) in Dataset. trying to insert a UserDefinedType in Dataset[Row] fails with input columns [].
