Hosur Narahari created SPARK-20093:
--------------------------------------
Summary: Exception when Joining dataframe with another dataframe
generated by applying groupBy transformation on original one
Key: SPARK-20093
URL: https://issues.apache.org/jira/browse/SPARK-20093
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.1.0, 2.0.2, 2.0.1, 2.0.0, 2.2.0
Reporter: Hosur Narahari
When we generate a dataframe by doing grouping, and perform join on original
dataframe with aggregate column, we get AnalysisException. Below I've attached
a piece of code and resulting exception to reproduce.
Code:
import org.apache.spark.sql.SparkSession
object App {
lazy val spark =
SparkSession.builder.appName("Test").master("local").getOrCreate
def main(args: Array[String]): Unit = {
test1
}
private def test1 {
import org.apache.spark.sql.functions._
val df = spark.createDataFrame(Seq(("M",172,60), ("M", 170, 60), ("F", 155,
56), ("M", 160, 55), ("F", 150, 53))).toDF("gender", "height", "weight")
val groupDF = df.groupBy("gender").agg(min("height").as("height"))
groupDF.show()
val out = groupDF.join(df, groupDF("height") <=>
df("height")).select(df("gender"), df("height"), df("weight"))
out.show
}
}
When I ran above code, I got below exception:
Exception in thread "main" org.apache.spark.sql.AnalysisException: resolved
attribute(s) height#8 missing from
height#19,height#30,gender#29,weight#31,gender#7 in operator !Join Inner,
(height#19 <=> height#8);;
!Join Inner, (height#19 <=> height#8)
:- Aggregate [gender#7], [gender#7, min(height#8) AS height#19]
: +- Project [_1#0 AS gender#7, _2#1 AS height#8, _3#2 AS weight#9]
: +- LocalRelation [_1#0, _2#1, _3#2]
+- Project [_1#0 AS gender#29, _2#1 AS height#30, _3#2 AS weight#31]
+- LocalRelation [_1#0, _2#1, _3#2]
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:39)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:90)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:342)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:78)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:127)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:78)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:90)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:53)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:67)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2831)
at org.apache.spark.sql.Dataset.join(Dataset.scala:843)
at org.apache.spark.sql.Dataset.join(Dataset.scala:807)
at App$.test1(App.scala:17)
at App$.main(App.scala:9)
at App.main(App.scala)
Please someone look into it.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
