You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hivemall.apache.org by "Makoto Yui (Jira)" <ji...@apache.org> on 2021/05/14 18:13:00 UTC

[jira] [Closed] (HIVEMALL-314) Fix define-all.spark

     [ https://issues.apache.org/jira/browse/HIVEMALL-314?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Makoto Yui closed HIVEMALL-314.
-------------------------------
    Resolution: Fixed

> Fix define-all.spark 
> ---------------------
>
>                 Key: HIVEMALL-314
>                 URL: https://issues.apache.org/jira/browse/HIVEMALL-314
>             Project: Hivemall
>          Issue Type: Bug
>    Affects Versions: 0.6.0
>            Reporter: Makoto Yui
>            Assignee: Makoto Yui
>            Priority: Major
>             Fix For: 0.6.2
>
>
> {code:java}
> org.apache.spark.sql.AnalysisException: Can not load class 'hivemall.knn.lsh.MinHashesUDFWrapper' when registering the function 'minhashes', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.ftvec.AddBiasUDFWrapper' when registering the function 'add_bias', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.ftvec.ExtractFeatureUDFWrapper' when registering the function 'extract_feature', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.ftvec.ExtractWeightUDFWrapper' when registering the function 'extract_weight', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'array_remove'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function array_remove already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'array_intersect'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function array_intersect already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'element_at'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function element_at already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Cannot drop native function 'array_union'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function array_union already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.tools.mapred.RowIdUDFWrapper' when registering the function 'rowid', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Cannot drop native function 'to_json'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 75 elided
> org.apache.spark.sql.AnalysisException: Function to_json already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Cannot drop native function 'from_json'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function from_json already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'raise_error'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function raise_error already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.dataset.LogisticRegressionDataGeneratorUDTFWrapper' when registering the function 'lr_datagen', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'approx_count_distinct'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 75 elided
> org.apache.spark.sql.AnalysisException: Function approx_count_distinct already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Cannot drop native function 'max_by'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 75 elided
> org.apache.spark.sql.AnalysisException: Function max_by already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Cannot drop native function 'min_by'
>   at org.apache.spark.sql.execution.command.DropFunctionCommand.run(functions.scala:182)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> org.apache.spark.sql.AnalysisException: Function min_by already exists
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1407)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elidedorg.apache.spark.sql.AnalysisException: Can not load class 'hivemall.xgboost.XGBoostOnlinePredictUDTFF' when registering the function 'xgboost_predict', please make sure it is on the classpath
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.$anonfun$registerFunction$1(SessionCatalog.scala:1414)
>   at scala.Option.getOrElse(Option.scala:189)
>   at org.apache.spark.sql.catalyst.catalog.SessionCatalog.registerFunction(SessionCatalog.scala:1411)
>   at org.apache.spark.sql.execution.command.CreateFunctionCommand.run(functions.scala:82)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
>   at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79)
>   at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3687)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
>   at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
>   at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
>   at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3685)
>   at org.apache.spark.sql.Dataset.<init>(Dataset.scala:228)
>   at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
>   at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
>   at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
>   at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
>   at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:650)
>   ... 71 elided
> {code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)