You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
scala> import org.apache.spark.sql.{SparkSession, Row}
scala> import org.apache.spark.sql.functions._
scala> import org.apache.spark.sql.types._
scala> val spark = SparkSession.builder.appName("Test").getOrCreate()
scala> import spark.implicits._
scala> val schema = MapType(StringType, IntegerType)
scala> val data = Seq(
| Row(Map("a" -> 1))
| )
scala> val df = spark.createDataFrame(
| spark.sparkContext.parallelize(data),
| StructType(Seq(StructField("value", schema)))
| )
scala> val jsonDF = df.select(to_json(col("value")).alias("json_string"))
scala> jsonDF.show(false)
24/05/28 06:11:14 WARN GpuOverrides:
!Exec <CollectLimitExec> cannot run on GPU because the Exec CollectLimitExec has been disabled, and is disabled by default because Collect Limit replacement can be slower on the GPU, if huge number of rows in a batch it could help by limiting the number of rows transferred from GPU to CPU. Set spark.rapids.sql.exec.CollectLimitExec to true if you wish to enable it
@Partitioning <SinglePartition$> could run on GPU
*Exec <ProjectExec> will run on GPU
*Expression <Alias> to_json(value#31, Some(UTC)) AS json_string#36 will run on GPU
*Expression <StructsToJson> to_json(value#31, Some(UTC)) will run on GPU
! <RDDScanExec> cannot run on GPU because GPU does not currently support the operator class org.apache.spark.sql.execution.RDDScanExec
@Expression <AttributeReference> value#31 could run on GPU
24/05/28 06:11:15 ERROR Executor: Exception in task 6.0 in stage 8.0 (TID 35)
java.lang.ClassCastException: org.apache.spark.sql.types.MapType cannot be cast to org.apache.spark.sql.types.StructType
at org.apache.spark.sql.rapids.GpuStructsToJson.doColumnar(GpuStructsToJson.scala:86)
at com.nvidia.spark.rapids.GpuUnaryExpression.doItColumnar(GpuExpressions.scala:250)
at com.nvidia.spark.rapids.GpuUnaryExpression.$anonfun$columnarEval$1(GpuExpressions.scala:261)
at com.nvidia.spark.rapids.Arm$.withResource(Arm.scala:30)
at com.nvidia.spark.rapids.GpuUnaryExpression.columnarEval(GpuExpressions.scala:260)
at com.nvidia.spark.rapids.RapidsPluginImplicits$ReallyAGpuExpression.columnarEval(implicits.scala:35)
at com.nvidia.spark.rapids.GpuAlias.columnarEval(namedExpressions.scala:110)
at com.nvidia.spark.rapids.RapidsPluginImplicits$ReallyAGpuExpression.columnarEval(implicits.scala:35)
at com.nvidia.spark.rapids.GpuProjectExec$.$anonfun$project$1(basicPhysicalOperators.scala:110)
at com.nvidia.spark.rapids.RapidsPluginImplicits$MapsSafely.$anonfun$safeMap$1(implicits.scala:221)
at com.nvidia.spark.rapids.RapidsPluginImplicits$MapsSafely.$anonfun$safeMap$1$adapted(implicits.scala:218)
at scala.collection.immutable.List.foreach(List.scala:431)
at com.nvidia.spark.rapids.RapidsPluginImplicits$MapsSafely.safeMap(implicits.scala:218)
at com.nvidia.spark.rapids.RapidsPluginImplicits$AutoCloseableProducingSeq.safeMap(implicits.scala:253)
at com.nvidia.spark.rapids.GpuProjectExec$.project(basicPhysicalOperators.scala:110)
at com.nvidia.spark.rapids.GpuTieredProject.$anonfun$project$2(basicPhysicalOperators.scala:619)
at com.nvidia.spark.rapids.Arm$.withResource(Arm.scala:30)
at com.nvidia.spark.rapids.GpuTieredProject.recurse$2(basicPhysicalOperators.scala:618)
at com.nvidia.spark.rapids.GpuTieredProject.project(basicPhysicalOperators.scala:631)
at com.nvidia.spark.rapids.GpuTieredProject.$anonfun$projectWithRetrySingleBatchInternal$5(basicPhysicalOperators.scala:567)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$.withRestoreOnRetry(RmmRapidsRetryIterator.scala:272)
at com.nvidia.spark.rapids.GpuTieredProject.$anonfun$projectWithRetrySingleBatchInternal$4(basicPhysicalOperators.scala:567)
at com.nvidia.spark.rapids.Arm$.withResource(Arm.scala:30)
at com.nvidia.spark.rapids.GpuTieredProject.$anonfun$projectWithRetrySingleBatchInternal$3(basicPhysicalOperators.scala:565)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$NoInputSpliterator.next(RmmRapidsRetryIterator.scala:395)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$RmmRapidsRetryIterator.next(RmmRapidsRetryIterator.scala:613)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$RmmRapidsRetryAutoCloseableIterator.next(RmmRapidsRetryIterator.scala:517)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$.drainSingleWithVerification(RmmRapidsRetryIterator.scala:291)
at com.nvidia.spark.rapids.RmmRapidsRetryIterator$.withRetryNoSplit(RmmRapidsRetryIterator.scala:185)
at com.nvidia.spark.rapids.GpuTieredProject.$anonfun$projectWithRetrySingleBatchInternal$1(basicPhysicalOperators.scala:565)
at com.nvidia.spark.rapids.Arm$.withResource(Arm.scala:39)
at com.nvidia.spark.rapids.GpuTieredProject.projectWithRetrySingleBatchInternal(basicPhysicalOperators.scala:562)
at com.nvidia.spark.rapids.GpuTieredProject.projectAndCloseWithRetrySingleBatch(basicPhysicalOperators.scala:601)
at com.nvidia.spark.rapids.GpuProjectExec.$anonfun$internalDoExecuteColumnar$2(basicPhysica
The text was updated successfully, but these errors were encountered:
Feng-Jiang28
changed the title
SPARK-21513: to_json support map[string, integer] to json
to_json converting map[string, integer] to json, throws an exception
May 28, 2024
to_json converting map[string, integer] to json, throws an exception
Reproduce:
CPU:
GPU:
The text was updated successfully, but these errors were encountered: