I am trying to perform some insert column operations in dataframe. Following is the code I used:
> val df = sqlContext.read.json("examples/src/main/resources/people.json") > df.show() { works correctly } > df.withColumn("age", df.col("name") ) { works correctly } > df.withColumn("age", df.col("name") ).show() { gives ERROR } > df.withColumn("arbitrary", df.col("name") ).show() { gives ERROR } This is the ERROR LOG : """ ERROR GenerateMutableProjection: failed to compile: import org.apache.spark.sql.catalyst.InternalRow; public SpecificProjection generate(org.apache.spark.sql.catalyst.expressions.Expression[] expr) { return new SpecificProjection(expr); } class SpecificProjection extends org.apache.spark.sql.catalyst.expressions.codegen.BaseMutableProjection { private org.apache.spark.sql.catalyst.expressions.Expression[] expressions = null; private org.apache.spark.sql.catalyst.expressions.MutableRow mutableRow = null; public SpecificProjection(org.apache.spark.sql.catalyst.expressions.Expression[] expr) { expressions = expr; mutableRow = new org.apache.spark.sql.catalyst.expressions.GenericMutableRow(3); } public org.apache.spark.sql.catalyst.expressions.codegen.BaseMutableProjection target(org.apache.spark.sql.catalyst.expressions.MutableRow row) { mutableRow = row; return this; } /* Provide immutable access to the last projected row. */ public InternalRow currentValue() { return (InternalRow) mutableRow; } public Object apply(Object _i) { InternalRow i = (InternalRow) _i; boolean isNull0 = i.isNullAt(0); long primitive1 = isNull0 ? -1L : (i.getLong(0)); if(isNull0) mutableRow.setNullAt(0); else mutableRow.setLong(0, primitive1); boolean isNull2 = i.isNullAt(1); org.apache.spark.unsafe.types.UTF8String primitive3 = isNull2 ? null : ((org.apache.spark.unsafe.types.UTF8String)i.apply(1)); if(isNull2) mutableRow.setNullAt(1); else mutableRow.update(1, primitive3); boolean isNull4 = i.isNullAt(1); org.apache.spark.unsafe.types.UTF8String primitive5 = isNull4 ? null : ((org.apache.spark.unsafe.types.UTF8String)i.apply(1)); if(isNull4) mutableRow.setNullAt(2); else mutableRow.update(2, primitive5); return mutableRow; } } org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6897) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5331) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5207) at org.codehaus.janino.UnitCompiler.getType2(UnitCompiler.java:5188) at org.codehaus.janino.UnitCompiler.access$12600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$16.visitReferenceType(UnitCompiler.java:5119) at org.codehaus.janino.Java$ReferenceType.accept(Java.java:2880) at org.codehaus.janino.UnitCompiler.getType(UnitCompiler.java:5159) at org.codehaus.janino.UnitCompiler.access$16700(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$31.getParameterTypes2(UnitCompiler.java:8533) at org.codehaus.janino.IClass$IInvocable.getParameterTypes(IClass.java:835) at org.codehaus.janino.IClass$IMethod.getDescriptor2(IClass.java:1063) at org.codehaus.janino.IClass$IInvocable.getDescriptor(IClass.java:849) at org.codehaus.janino.IClass.getIMethods(IClass.java:211) at org.codehaus.janino.IClass.getIMethods(IClass.java:199) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:409) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:658) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:662) at org.codehaus.janino.UnitCompiler.access$600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitMemberClassDeclaration(UnitCompiler.java:350) at org.codehaus.janino.Java$MemberClassDeclaration.accept(Java.java:1035) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileDeclaredMemberTypes(UnitCompiler.java:769) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:532) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:393) at org.codehaus.janino.UnitCompiler.access$400(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitPackageMemberClassDeclaration(UnitCompiler.java:347) at org.codehaus.janino.Java$PackageMemberClassDeclaration.accept(Java.java:1139) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileUnit(UnitCompiler.java:322) at org.codehaus.janino.SimpleCompiler.compileToClassLoader(SimpleCompiler.java:383) at org.codehaus.janino.ClassBodyEvaluator.compileToClass(ClassBodyEvaluator.java:315) at org.codehaus.janino.ClassBodyEvaluator.cook(ClassBodyEvaluator.java:233) at org.codehaus.janino.SimpleCompiler.cook(SimpleCompiler.java:192) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:84) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:77) at org.codehaus.janino.ClassBodyEvaluator.<init>(ClassBodyEvaluator.java:72) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.compile(CodeGenerator.scala:245) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:87) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:29) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:272) at org.spark-project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379) at org.spark-project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342) at org.spark-project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257) at org.spark-project.guava.cache.LocalCache.get(LocalCache.java:4000) at org.spark-project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004) at org.spark-project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:285) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:282) at org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:173) at org.apache.spark.sql.execution.Project.buildProjection$lzycompute(basicOperators.scala:39) at org.apache.spark.sql.execution.Project.buildProjection(basicOperators.scala:39) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:42) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:41) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) 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) Caused by: java.lang.ClassNotFoundException: Object at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:69) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:274) at org.codehaus.janino.ClassLoaderIClassLoader.findIClass(ClassLoaderIClassLoader.java:78) at org.codehaus.janino.IClassLoader.loadIClass(IClassLoader.java:254) at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6893) ... 68 more Caused by: java.lang.ClassNotFoundException: Object at java.lang.ClassLoader.findClass(ClassLoader.java:531) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30) at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:64) ... 75 more 15/06/19 18:17:03 ERROR Executor: Exception in task 0.0 in stage 15.0 (TID 16) java.util.concurrent.ExecutionException: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306) at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293) at org.spark-project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116) at org.spark-project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135) at org.spark-project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380) at org.spark-project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342) at org.spark-project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257) at org.spark-project.guava.cache.LocalCache.get(LocalCache.java:4000) at org.spark-project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004) at org.spark-project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:285) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:282) at org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:173) at org.apache.spark.sql.execution.Project.buildProjection$lzycompute(basicOperators.scala:39) at org.apache.spark.sql.execution.Project.buildProjection(basicOperators.scala:39) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:42) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:41) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) 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) Caused by: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6897) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5331) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5207) at org.codehaus.janino.UnitCompiler.getType2(UnitCompiler.java:5188) at org.codehaus.janino.UnitCompiler.access$12600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$16.visitReferenceType(UnitCompiler.java:5119) at org.codehaus.janino.Java$ReferenceType.accept(Java.java:2880) at org.codehaus.janino.UnitCompiler.getType(UnitCompiler.java:5159) at org.codehaus.janino.UnitCompiler.access$16700(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$31.getParameterTypes2(UnitCompiler.java:8533) at org.codehaus.janino.IClass$IInvocable.getParameterTypes(IClass.java:835) at org.codehaus.janino.IClass$IMethod.getDescriptor2(IClass.java:1063) at org.codehaus.janino.IClass$IInvocable.getDescriptor(IClass.java:849) at org.codehaus.janino.IClass.getIMethods(IClass.java:211) at org.codehaus.janino.IClass.getIMethods(IClass.java:199) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:409) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:658) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:662) at org.codehaus.janino.UnitCompiler.access$600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitMemberClassDeclaration(UnitCompiler.java:350) at org.codehaus.janino.Java$MemberClassDeclaration.accept(Java.java:1035) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileDeclaredMemberTypes(UnitCompiler.java:769) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:532) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:393) at org.codehaus.janino.UnitCompiler.access$400(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitPackageMemberClassDeclaration(UnitCompiler.java:347) at org.codehaus.janino.Java$PackageMemberClassDeclaration.accept(Java.java:1139) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileUnit(UnitCompiler.java:322) at org.codehaus.janino.SimpleCompiler.compileToClassLoader(SimpleCompiler.java:383) at org.codehaus.janino.ClassBodyEvaluator.compileToClass(ClassBodyEvaluator.java:315) at org.codehaus.janino.ClassBodyEvaluator.cook(ClassBodyEvaluator.java:233) at org.codehaus.janino.SimpleCompiler.cook(SimpleCompiler.java:192) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:84) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:77) at org.codehaus.janino.ClassBodyEvaluator.<init>(ClassBodyEvaluator.java:72) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.compile(CodeGenerator.scala:245) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:87) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:29) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:272) at org.spark-project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379) ... 26 more Caused by: java.lang.ClassNotFoundException: Object at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:69) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:274) at org.codehaus.janino.ClassLoaderIClassLoader.findIClass(ClassLoaderIClassLoader.java:78) at org.codehaus.janino.IClassLoader.loadIClass(IClassLoader.java:254) at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6893) ... 68 more Caused by: java.lang.ClassNotFoundException: Object at java.lang.ClassLoader.findClass(ClassLoader.java:531) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30) at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:64) ... 75 more 15/06/19 18:17:03 WARN TaskSetManager: Lost task 0.0 in stage 15.0 (TID 16, localhost): java.util.concurrent.ExecutionException: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306) at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293) at org.spark-project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116) at org.spark-project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135) at org.spark-project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380) at org.spark-project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342) at org.spark-project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257) at org.spark-project.guava.cache.LocalCache.get(LocalCache.java:4000) at org.spark-project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004) at org.spark-project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:285) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:282) at org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:173) at org.apache.spark.sql.execution.Project.buildProjection$lzycompute(basicOperators.scala:39) at org.apache.spark.sql.execution.Project.buildProjection(basicOperators.scala:39) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:42) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:41) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) 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) Caused by: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6897) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5331) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5207) at org.codehaus.janino.UnitCompiler.getType2(UnitCompiler.java:5188) at org.codehaus.janino.UnitCompiler.access$12600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$16.visitReferenceType(UnitCompiler.java:5119) at org.codehaus.janino.Java$ReferenceType.accept(Java.java:2880) at org.codehaus.janino.UnitCompiler.getType(UnitCompiler.java:5159) at org.codehaus.janino.UnitCompiler.access$16700(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$31.getParameterTypes2(UnitCompiler.java:8533) at org.codehaus.janino.IClass$IInvocable.getParameterTypes(IClass.java:835) at org.codehaus.janino.IClass$IMethod.getDescriptor2(IClass.java:1063) at org.codehaus.janino.IClass$IInvocable.getDescriptor(IClass.java:849) at org.codehaus.janino.IClass.getIMethods(IClass.java:211) at org.codehaus.janino.IClass.getIMethods(IClass.java:199) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:409) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:658) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:662) at org.codehaus.janino.UnitCompiler.access$600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitMemberClassDeclaration(UnitCompiler.java:350) at org.codehaus.janino.Java$MemberClassDeclaration.accept(Java.java:1035) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileDeclaredMemberTypes(UnitCompiler.java:769) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:532) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:393) at org.codehaus.janino.UnitCompiler.access$400(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitPackageMemberClassDeclaration(UnitCompiler.java:347) at org.codehaus.janino.Java$PackageMemberClassDeclaration.accept(Java.java:1139) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileUnit(UnitCompiler.java:322) at org.codehaus.janino.SimpleCompiler.compileToClassLoader(SimpleCompiler.java:383) at org.codehaus.janino.ClassBodyEvaluator.compileToClass(ClassBodyEvaluator.java:315) at org.codehaus.janino.ClassBodyEvaluator.cook(ClassBodyEvaluator.java:233) at org.codehaus.janino.SimpleCompiler.cook(SimpleCompiler.java:192) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:84) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:77) at org.codehaus.janino.ClassBodyEvaluator.<init>(ClassBodyEvaluator.java:72) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.compile(CodeGenerator.scala:245) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:87) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:29) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:272) at org.spark-project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379) ... 26 more Caused by: java.lang.ClassNotFoundException: Object at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:69) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:274) at org.codehaus.janino.ClassLoaderIClassLoader.findIClass(ClassLoaderIClassLoader.java:78) at org.codehaus.janino.IClassLoader.loadIClass(IClassLoader.java:254) at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6893) ... 68 more Caused by: java.lang.ClassNotFoundException: Object at java.lang.ClassLoader.findClass(ClassLoader.java:531) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30) at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:64) ... 75 more 15/06/19 18:17:03 ERROR TaskSetManager: Task 0 in stage 15.0 failed 1 times; aborting job org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 15.0 failed 1 times, most recent failure: Lost task 0.0 in stage 15.0 (TID 16, localhost): java.util.concurrent.ExecutionException: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306) at org.spark-project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293) at org.spark-project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116) at org.spark-project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135) at org.spark-project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380) at org.spark-project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342) at org.spark-project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257) at org.spark-project.guava.cache.LocalCache.get(LocalCache.java:4000) at org.spark-project.guava.cache.LocalCache.getOrLoad(LocalCache.java:4004) at org.spark-project.guava.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:285) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:282) at org.apache.spark.sql.execution.SparkPlan.newMutableProjection(SparkPlan.scala:173) at org.apache.spark.sql.execution.Project.buildProjection$lzycompute(basicOperators.scala:39) at org.apache.spark.sql.execution.Project.buildProjection(basicOperators.scala:39) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:42) at org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:41) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:686) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277) at org.apache.spark.rdd.RDD.iterator(RDD.scala:244) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) 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) Caused by: org.codehaus.commons.compiler.CompileException: Line 28, Column 35: Object at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6897) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5331) at org.codehaus.janino.UnitCompiler.getReferenceType(UnitCompiler.java:5207) at org.codehaus.janino.UnitCompiler.getType2(UnitCompiler.java:5188) at org.codehaus.janino.UnitCompiler.access$12600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$16.visitReferenceType(UnitCompiler.java:5119) at org.codehaus.janino.Java$ReferenceType.accept(Java.java:2880) at org.codehaus.janino.UnitCompiler.getType(UnitCompiler.java:5159) at org.codehaus.janino.UnitCompiler.access$16700(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$31.getParameterTypes2(UnitCompiler.java:8533) at org.codehaus.janino.IClass$IInvocable.getParameterTypes(IClass.java:835) at org.codehaus.janino.IClass$IMethod.getDescriptor2(IClass.java:1063) at org.codehaus.janino.IClass$IInvocable.getDescriptor(IClass.java:849) at org.codehaus.janino.IClass.getIMethods(IClass.java:211) at org.codehaus.janino.IClass.getIMethods(IClass.java:199) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:409) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:658) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:662) at org.codehaus.janino.UnitCompiler.access$600(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitMemberClassDeclaration(UnitCompiler.java:350) at org.codehaus.janino.Java$MemberClassDeclaration.accept(Java.java:1035) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileDeclaredMemberTypes(UnitCompiler.java:769) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:532) at org.codehaus.janino.UnitCompiler.compile2(UnitCompiler.java:393) at org.codehaus.janino.UnitCompiler.access$400(UnitCompiler.java:185) at org.codehaus.janino.UnitCompiler$2.visitPackageMemberClassDeclaration(UnitCompiler.java:347) at org.codehaus.janino.Java$PackageMemberClassDeclaration.accept(Java.java:1139) at org.codehaus.janino.UnitCompiler.compile(UnitCompiler.java:354) at org.codehaus.janino.UnitCompiler.compileUnit(UnitCompiler.java:322) at org.codehaus.janino.SimpleCompiler.compileToClassLoader(SimpleCompiler.java:383) at org.codehaus.janino.ClassBodyEvaluator.compileToClass(ClassBodyEvaluator.java:315) at org.codehaus.janino.ClassBodyEvaluator.cook(ClassBodyEvaluator.java:233) at org.codehaus.janino.SimpleCompiler.cook(SimpleCompiler.java:192) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:84) at org.codehaus.commons.compiler.Cookable.cook(Cookable.java:77) at org.codehaus.janino.ClassBodyEvaluator.<init>(ClassBodyEvaluator.java:72) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.compile(CodeGenerator.scala:245) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:87) at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:29) at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$$anon$1.load(CodeGenerator.scala:272) at org.spark-project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599) at org.spark-project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379) ... 26 more Caused by: java.lang.ClassNotFoundException: Object at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:69) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:274) at org.codehaus.janino.ClassLoaderIClassLoader.findIClass(ClassLoaderIClassLoader.java:78) at org.codehaus.janino.IClassLoader.loadIClass(IClassLoader.java:254) at org.codehaus.janino.UnitCompiler.findTypeByName(UnitCompiler.java:6893) ... 68 more Caused by: java.lang.ClassNotFoundException: Object at java.lang.ClassLoader.findClass(ClassLoader.java:531) at org.apache.spark.util.ParentClassLoader.findClass(ParentClassLoader.scala:26) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:34) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at org.apache.spark.util.ParentClassLoader.loadClass(ParentClassLoader.scala:30) at org.apache.spark.repl.ExecutorClassLoader.findClass(ExecutorClassLoader.scala:64) ... 75 more Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org $apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1285) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1276) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1275) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1275) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:749) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:749) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:749) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1484) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1445) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) """ What am I doing wrong ? P.S. I am working on spark master branch. The same code works fine on pyspark. Sincerely, Animesh