py4j.protocol.Py4JJavaError: An error occurred while calling o89.pyWriteDynamicFrame.
: org.apache.spark.SparkException: Job aborted.
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:231)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:195)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131)
    at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185)
    at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220)
    at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181)
    at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134)
    at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133)
    at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
    at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
    at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
    at org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
    at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
    at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
    at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
    at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
    at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
    at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438)
    at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301)
    at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3(DataSink.scala:595)
    at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3$adapted(DataSink.scala:582)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.$anonfun$executeWithQualifiedScheme$1(FileSchemeWrapper.scala:77)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWith(FileSchemeWrapper.scala:70)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWithQualifiedScheme(FileSchemeWrapper.scala:77)
    at com.amazonaws.services.glue.SparkSQLDataSink.writeDynamicFrame(DataSink.scala:582)
    at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:64)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (172.31.12.229 executor 1): org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059)
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068)
    at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334)
    at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
    at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225)
    at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    at java.lang.Thread.run(Thread.java:748)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2465)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2414)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2413)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2413)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1124)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1124)
    at scala.Option.foreach(Option.scala:407)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1124)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2679)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2621)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2610)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:914)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2238)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:200)
    ... 45 more
Caused by: org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059)
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068)
    at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334)
    at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
    at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225)
    at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    ... 1 more

2021-09-13 09:52:47,872 ERROR [main] glue.ProcessLauncher (Logging.scala:logError(73)): Error from Python:Traceback (most recent call last): File "/tmp/Test - books_api_db_to_s3", line 116, in <module> main() File "/tmp/Test - books_api_db_to_s3", line 111, in main write_to_s3(table_list, database) File "/tmp/Test - books_api_db_to_s3", line 102, in write_to_s3 format=FILE_FORMAT, File "/opt/amazon/lib/python3.6/site-packages/awsglue/dynamicframe.py", line 640, in from_options format_options, transformation_ctx) File "/opt/amazon/lib/python3.6/site-packages/awsglue/context.py", line 277, in write_dynamic_frame_from_options format, format_options, transformation_ctx) File "/opt/amazon/lib/python3.6/site-packages/awsglue/context.py", line 300, in write_from_options return sink.write(frame_or_dfc) File "/opt/amazon/lib/python3.6/site-packages/awsglue/data_sink.py", line 35, in write return self.writeFrame(dynamic_frame_or_dfc, info) File "/opt/amazon/lib/python3.6/site-packages/awsglue/data_sink.py", line 31, in writeFrame return DynamicFrame(self._jsink.pyWriteDynamicFrame(dynamic_frame._jdf, callsite(), info), dynamic_frame.glue_ctx, dynamic_frame.name + "_errors") File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py", line 1305, in __call__ answer, self.gateway_client, self.target_id, self.name) File "/opt/amazon/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 111, in deco return f(*a, **kw) File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line 328, in get_return_value format(target_id, ".", name), value) py4j.protocol.Py4JJavaError: An error occurred while calling o89.pyWriteDynamicFrame. : org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:231) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:195) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106) at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131) at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185) at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133) at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107) at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232) at org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107) at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438) at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301) at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3(DataSink.scala:595) at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3$adapted(DataSink.scala:582) at com.amazonaws.services.glue.util.FileSchemeWrapper.$anonfun$executeWithQualifiedScheme$1(FileSchemeWrapper.scala:77) at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWith(FileSchemeWrapper.scala:70) at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWithQualifiedScheme(FileSchemeWrapper.scala:77) at com.amazonaws.services.glue.SparkSQLDataSink.writeDynamicFrame(DataSink.scala:582) at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:64) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:748) Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (172.31.12.229 executor 1): org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059) at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068) at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334) at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755) at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225) at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52) at org.apache.spark.scheduler.Task.run(Task.scala:131) at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2465) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2414) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2413) at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62) at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2413) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1124) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1124) at scala.Option.foreach(Option.scala:407) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1124) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2679) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2621) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2610) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:914) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2238) at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:200) ... 45 more Caused by: org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059) at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068) at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334) at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755) at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225) at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52) at org.apache.spark.scheduler.Task.run(Task.scala:131) at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ... 1 more

py4j.protocol.Py4JJavaError: An error occurred while calling o89.pyWriteDynamicFrame.
: org.apache.spark.SparkException: Job aborted.
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:231)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:195)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131)
    at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185)
    at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220)
    at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181)
    at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134)
    at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133)
    at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
    at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
    at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
    at org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
    at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
    at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
    at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
    at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
    at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
    at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
    at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438)
    at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301)
    at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3(DataSink.scala:595)
    at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3$adapted(DataSink.scala:582)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.$anonfun$executeWithQualifiedScheme$1(FileSchemeWrapper.scala:77)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWith(FileSchemeWrapper.scala:70)
    at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWithQualifiedScheme(FileSchemeWrapper.scala:77)
    at com.amazonaws.services.glue.SparkSQLDataSink.writeDynamicFrame(DataSink.scala:582)
    at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:64)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (172.31.12.229 executor 1): org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059)
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068)
    at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334)
    at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
    at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225)
    at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    at java.lang.Thread.run(Thread.java:748)

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2465)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2414)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2413)
    at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
    at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2413)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1124)
    at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1124)
    at scala.Option.foreach(Option.scala:407)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1124)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2679)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2621)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2610)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:914)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2238)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:200)
    ... 45 more
Caused by: org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059)
    at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068)
    at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438)
    at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352)
    at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334)
    at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
    at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
    at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31)
    at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
    at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
    at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
    at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225)
    at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
    at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
    at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
    at org.apache.spark.scheduler.Task.run(Task.scala:131)
    at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    ... 1 more

2021-09-13 09:52:47,872 ERROR [main] glue.ProcessLauncher "/opt/amazon/lib/python3.6/site-packages/awsglue/context.py", line 277, in write_dynamic_frame_from_options format, format_options, transformation_ctx) File "/opt/amazon/lib/python3.6/site-packages/awsglue/context.py", line 300, in write_from_options return sink.write(frame_or_dfc) File "/opt/amazon/lib/python3.6/site-packages/awsglue/data_sink.py", line 35, in write return self.writeFrame(dynamic_frame_or_dfc, info) File "/opt/amazon/lib/python3.6/site-packages/awsglue/data_sink.py", line 31, in writeFrame return DynamicFrame(self._jsink.pyWriteDynamicFrame(dynamic_frame._jdf, callsite(), info), dynamic_frame.glue_ctx, dynamic_frame.name + "_errors") File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py", line 1305, in __call__ answer, self.gateway_client, self.target_id, self.name) File "/opt/amazon/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 111, in deco return f(*a, **kw) File "/opt/amazon/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line 328, in get_return_value format(target_id, ".", name), value) py4j.protocol.Py4JJavaError: An error occurred while calling o89.pyWriteDynamicFrame. : org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:231) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:195) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106) at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131) at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185) at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133) at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107) at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232) at org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107) at org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438) at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301) at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3(DataSink.scala:595) at com.amazonaws.services.glue.SparkSQLDataSink.$anonfun$writeDynamicFrame$3$adapted(DataSink.scala:582) at com.amazonaws.services.glue.util.FileSchemeWrapper.$anonfun$executeWithQualifiedScheme$1(FileSchemeWrapper.scala:77) at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWith(FileSchemeWrapper.scala:70) at com.amazonaws.services.glue.util.FileSchemeWrapper.executeWithQualifiedScheme(FileSchemeWrapper.scala:77) at com.amazonaws.services.glue.SparkSQLDataSink.writeDynamicFrame(DataSink.scala:582) at com.amazonaws.services.glue.DataSink.pyWriteDynamicFrame(DataSink.scala:64) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:748) Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (172.31.12.229 executor 1): org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059) at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068) at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334) at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755) at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225) at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52) at org.apache.spark.scheduler.Task.run(Task.scala:131) at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2465) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2414) at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2413) at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62) at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2413) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1124) at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1124) at scala.Option.foreach(Option.scala:407) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1124) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2679) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2621) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2610) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:914) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2238) at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:200) ... 45 more Caused by: org.postgresql.util.PSQLException: Bad value for type BigDecimal : NaN at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3059) at org.postgresql.jdbc.PgResultSet.toBigDecimal(PgResultSet.java:3068) at org.postgresql.jdbc.PgResultSet.getNumeric(PgResultSet.java:2486) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:2438) at org.postgresql.jdbc.PgResultSet.getBigDecimal(PgResultSet.java:406) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3(JdbcUtils.scala:403) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.$anonfun$makeGetter$3$adapted(JdbcUtils.scala:401) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:352) at org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anon$1.getNext(JdbcUtils.scala:334) at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:31) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755) at org.apache.spark.sql.execution.UnsafeExternalRowSorter.sort(UnsafeExternalRowSorter.java:225) at org.apache.spark.sql.execution.exchange.ShuffleExchangeExec$.$anonfun$prepareShuffleDependency$10(ShuffleExchangeExec.scala:379) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898) at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373) at org.apache.spark.rdd.RDD.iterator(RDD.scala:337) at org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52) at org.apache.spark.scheduler.Task.run(Task.scala:131) at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ... 1 more