Fokko edited a comment on pull request #28554: URL: https://github.com/apache/spark/pull/28554#issuecomment-640173630
I finally have some to pick this up. Looks like there is some funky behavior. Doing an average on a string just return `null`, and doing this on a Date, returns an exception: ``` MacBook-Pro-van-Fokko:spark fokkodriesprong$ spark-shell 20/06/07 09:51:57 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties Setting default log level to "WARN". To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel). Spark context Web UI available at http://192.168.1.113:4040 Spark context available as 'sc' (master = local[*], app id = local-1591516331348). Spark session available as 'spark'. Welcome to ____ __ / __/__ ___ _____/ /__ _\ \/ _ \/ _ `/ __/ '_/ /___/ .__/\_,_/_/ /_/\_\ version 2.4.5 /_/ Using Scala version 2.11.12 (Java HotSpot(TM) 64-Bit Server VM, Java 1.8.0_172) Type in expressions to have them evaluated. Type :help for more information. scala> import java.sql.Date import java.sql.Date scala> import org.apache.spark.sql.DataFrame import org.apache.spark.sql.DataFrame scala> val person2: DataFrame = Seq( | ("Bob", 16, 176, new Date(2020, 1, 1)), | ("Alice", 32, 164, new Date(2020, 1, 5)), | ("David", 60, 192, new Date(2020, 1, 19)), | ("Amy", 24, 180, new Date(2020, 1, 25))).toDF("name", "age", "height", "birthday") warning: there were four deprecation warnings; re-run with -deprecation for details person2: org.apache.spark.sql.DataFrame = [name: string, age: int ... 2 more fields] scala> person2.select("name").agg(avg('name)).show() +---------+ |avg(name)| +---------+ | null| +---------+ scala> person2.select("name").agg(avg('birthday)).show() org.apache.spark.sql.AnalysisException: cannot resolve '`birthday`' given input columns: [name];; 'Aggregate [avg('birthday) AS avg(birthday)#38] +- Project [name#9] +- Project [_1#4 AS name#9, _2#5 AS age#10, _3#6 AS height#11, _4#7 AS birthday#12] +- LocalRelation [_1#4, _2#5, _3#6, _4#7] 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$3.applyOrElse(CheckAnalysis.scala:111) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$3.applyOrElse(CheckAnalysis.scala:108) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:280) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:280) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:279) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:328) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:186) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:326) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:328) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:186) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:326) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:277) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:328) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:186) at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:326) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:277) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$transformExpressionsUp$1.apply(QueryPlan.scala:93) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$transformExpressionsUp$1.apply(QueryPlan.scala:93) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:105) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:105) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpression$1(QueryPlan.scala:104) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:116) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$2.apply(QueryPlan.scala:121) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.immutable.List.foreach(List.scala:392) at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) at scala.collection.immutable.List.map(List.scala:296) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:121) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:126) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:186) at org.apache.spark.sql.catalyst.plans.QueryPlan.mapExpressions(QueryPlan.scala:126) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:93) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:108) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:86) at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:126) at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:86) at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:95) at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:108) at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201) at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105) at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:58) at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:56) at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:48) at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78) at org.apache.spark.sql.RelationalGroupedDataset.toDF(RelationalGroupedDataset.scala:65) at org.apache.spark.sql.RelationalGroupedDataset.agg(RelationalGroupedDataset.scala:224) at org.apache.spark.sql.Dataset.agg(Dataset.scala:1804) ... 49 elided ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
