I have recently upgraded spark version but when I try to run save a random
forest model using model save command I am getting nosuchmethoderror. My code
works fine with 1.3x version.
model.save(sc.sc(), "modelsavedir");
ERROR: org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation -
Aborting job.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 22.0 failed 1 times, most recent failure: Lost task 0.0 in stage 22.0
(TID 230, localhost): java.lang.NoSuchMethodError:
parquet.schema.Types$GroupBuilder.addField(Lparquet/schema/Type;)Lparquet/schema/Types$BaseGroupBuilder;
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:517)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:516)
at
scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51)
at
scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60)
at
scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:516)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:312)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at
scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at
scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at
org.apache.spark.sql.types.StructType.foreach(StructType.scala:92)
at
scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at
org.apache.spark.sql.types.StructType.map(StructType.scala:92)
at
org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:305)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58)
at
org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55)
at
parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:287)
at
parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:261)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272)
at
org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:233)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at
org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150)
at
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
