I have a venv set up and running 'conda list' in cmd window I can see spacy 2.2.4, en-core-web-sm 2.2.5, pyspark 2.4.5 among other packages.
I want to apply spacy's named entity recognition to a column in a Spark Dataframe called 'tweets' within Jupyter Notebook. I am doing this by passing the NER into a Spark UDF, and passing that UDF into the withColumn operation:
import spacy nlp = spacy.load("en_core_web_sm") def spacy_ner(text_col): entities = [] for parsed in nlp.pipe(text_col): if parsed.ents: inner = '' for ent in parsed.ents: inner += ent.text + '' else: inner = '' entities.append(inner) return entities ner = udf(spacy_ner) ner = sqlContext.udf.register("ner", spacy_ner) tweets = tweets.withColumn('text_ner',ner('text_nosw')) result = tweets.groupBy(tweets.text_ner).count() result.show() However I'm getting "ModuleNotFoundError: No module named 'spacy'":
Py4JJavaError: An error occurred while calling o1006.showString. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 43.0 failed 1 times, most recent failure: Lost task 0.0 in stage 43.0 (TID 289, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 366, in main func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 241, in read_udfs arg_offsets, udf = read_single_udf(pickleSer, infile, eval_type, runner_conf) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 168, in read_single_udf f, return_type = read_command(pickleSer, infile) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 71, in read_command command = serializer.loads(command.value) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads return pickle.loads(obj, encoding=encoding) ModuleNotFoundError: No module named 'spacy' at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64) at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.agg_doAggregateWithKeys_0$(Unknown Source) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:55) at org.apache.spark.scheduler.Task.run(Task.scala:123) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1891) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1878) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1878) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2112) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2061) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2050) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3389) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550) at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3370) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3369) at org.apache.spark.sql.Dataset.head(Dataset.scala:2550) at org.apache.spark.sql.Dataset.take(Dataset.scala:2764) at org.apache.spark.sql.Dataset.getRows(Dataset.scala:254) at org.apache.spark.sql.Dataset.showString(Dataset.scala:291) 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.api.python.PythonException: Traceback (most recent call last): File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 366, in main func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 241, in read_udfs arg_offsets, udf = read_single_udf(pickleSer, infile, eval_type, runner_conf) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 168, in read_single_udf f, return_type = read_command(pickleSer, infile) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 71, in read_command command = serializer.loads(command.value) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads return pickle.loads(obj, encoding=encoding) ModuleNotFoundError: No module named 'spacy' at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64) at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.agg_doAggregateWithKeys_0$(Unknown Source) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:55) at org.apache.spark.scheduler.Task.run(Task.scala:123) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ... 1 more --------------------------------------------------------------------------- Py4JJavaError Traceback (most recent call last) <ipython-input-30-9fbae11f2e36> in <module> 4 tweets = tweets.withColumn('text_ner',ner('text_nosw')) 5 result = tweets.groupBy(tweets.text_ner).count() ----> 6 result.show() ~/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/sql/dataframe.py in show(self, n, truncate, vertical) 378 """ 379 if isinstance(truncate, bool) and truncate: --> 380 print(self._jdf.showString(n, 20, vertical)) 381 else: 382 print(self._jdf.showString(n, int(truncate), vertical)) ~/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args) 1255 answer = self.gateway_client.send_command(command) 1256 return_value = get_return_value( -> 1257 answer, self.gateway_client, self.target_id, self.name) 1258 1259 for temp_arg in temp_args: ~/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw) 61 def deco(*a, **kw): 62 try: ---> 63 return f(*a, **kw) 64 except py4j.protocol.Py4JJavaError as e: 65 s = e.java_exception.toString() ~/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name) 326 raise Py4JJavaError( 327 "An error occurred while calling {0}{1}{2}.\n". --> 328 format(target_id, ".", name), value) 329 else: 330 raise Py4JError( Py4JJavaError: An error occurred while calling o1006.showString. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 43.0 failed 1 times, most recent failure: Lost task 0.0 in stage 43.0 (TID 289, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 366, in main func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 241, in read_udfs arg_offsets, udf = read_single_udf(pickleSer, infile, eval_type, runner_conf) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 168, in read_single_udf f, return_type = read_command(pickleSer, infile) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 71, in read_command command = serializer.loads(command.value) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads return pickle.loads(obj, encoding=encoding) ModuleNotFoundError: No module named 'spacy' at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64) at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.agg_doAggregateWithKeys_0$(Unknown Source) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:55) at org.apache.spark.scheduler.Task.run(Task.scala:123) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) at java.lang.Thread.run(Thread.java:748) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1891) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1879) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1878) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1878) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:927) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:927) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2112) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2061) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2050) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:738) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:365) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3389) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2550) at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3370) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3369) at org.apache.spark.sql.Dataset.head(Dataset.scala:2550) at org.apache.spark.sql.Dataset.take(Dataset.scala:2764) at org.apache.spark.sql.Dataset.getRows(Dataset.scala:254) at org.apache.spark.sql.Dataset.showString(Dataset.scala:291) 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.api.python.PythonException: Traceback (most recent call last): File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 366, in main func, profiler, deserializer, serializer = read_udfs(pickleSer, infile, eval_type) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 241, in read_udfs arg_offsets, udf = read_single_udf(pickleSer, infile, eval_type, runner_conf) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 168, in read_single_udf f, return_type = read_command(pickleSer, infile) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/worker.py", line 71, in read_command command = serializer.loads(command.value) File "/Users/Noah/anaconda3/envs/pyspark_env/lib/python3.7/site-packages/pyspark/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads return pickle.loads(obj, encoding=encoding) ModuleNotFoundError: No module named 'spacy' at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:81) at org.apache.spark.sql.execution.python.PythonUDFRunner$$anon$1.read(PythonUDFRunner.scala:64) at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37) at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.agg_doAggregateWithKeys_0$(Unknown Source) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$13$$anon$1.hasNext(WholeStageCodegenExec.scala:636) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:409) at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:125) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:55) at org.apache.spark.scheduler.Task.run(Task.scala:123) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408) at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) ... 1 more 
