在 Amazon EMR 上运行 Python UDF

Question

I'm trying to get a UDF running on EMR and am having trouble.

My script currently looks like:

from pyspark.sql import SparkSession
from pyspark.sql.functions import pandas_udf
from pyspark.sql.functions import PandasUDFType
from pyspark.sql.types import *
from pyspark import SparkContext
import pandas
import sys


schema = StructType([
    StructField("id", DoubleType()),
    StructField("v_2", DoubleType())
])

def create_spark_session():
    """Create spark session.
Returns:
        spark (SparkSession) - spark session connected to AWS EMR
            cluster
    """
    spark = SparkSession \
        .builder \
        .config("spark.jars.packages",
                "org.apache.hadoop:hadoop-aws:2.8.5") \
        .getOrCreate()
    return spark

@pandas_udf(schema, functionType=PandasUDFType.GROUPED_MAP)
def g(df):
    df['v_2'] = df['v'] * 2
    df2 = df[['id','v_2']].copy()
    return pandas.DataFrame(df2)

def process_customer_data(spark, input_path, output_path):
    df = spark.createDataFrame([(1, 1.0), (1, 2.0), (2, 3.0), (2, 5.0), (2, 10.0)],("id", "v"))
    calced_value = df.groupby("id").apply(g)
    calced_value.write.mode("overwrite").parquet(output_path)

def main():
    spark = create_spark_session()
    input_path = 's3://myinput/input/TestDF.csv'
    output_path = 's3://myoutput/output/'
    process_customer_data(spark, input_path, output_path)

if __name__ == '__main__':
    main()

The error message that I'm getting in log/container/.../stdout.gz:

Traceback (most recent call last):
  File "pyspark_job.py", line 46, in <module>
    main()
  File "pyspark_job.py", line 43, in main
    process_customer_data(spark, input_path, output_path)
  File "pyspark_job.py", line 37, in process_customer_data
    calced_value.write.mode("overwrite").parquet(output_path)
  File "/mnt1/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000001/pyspark.zip/pyspark/sql/readwriter.py", line 843, in parquet
  File "/mnt1/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000001/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
  File "/mnt1/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000001/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
  File "/mnt1/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000001/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o103.parquet.
: org.apache.spark.SparkException: Job aborted.
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198)
    at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
    at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
    at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:156)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
    at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
    at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
    at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
    at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
    at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676)
    at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
    at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
    at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
    at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
    at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
    at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:566)
    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 69 in stage 1.0 failed 4 times, most recent failure: Lost task 69.3 in stage 1.0 (TID 13, ip-10-18-21-147.ec2.internal, executor 1): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 377, in main
    process()
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 372, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 248, in <lambda>
    func = lambda _, it: map(mapper, it)
  File "<string>", line 1, in <lambda>
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 129, in wrapped
    return [(result[field.name], to_arrow_type(field.dataType)) for field in return_type]
  File "/usr/local/lib64/python2.7/site-packages/pandas/core/frame.py", line 2927, in __getitem__
    indexer = self.columns.get_loc(key)
  File "/usr/local/lib64/python2.7/site-packages/pandas/core/indexes/base.py", line 2659, in get_loc
    return self._engine.get_loc(self._maybe_cast_indexer(key))
  File "pandas/_libs/index.pyx", line 108, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/index.pyx", line 132, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/hashtable_class_helper.pxi", line 1601, in pandas._libs.hashtable.PyObjectHashTable.get_item
  File "pandas/_libs/hashtable_class_helper.pxi", line 1608, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'v'

    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456)
    at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:172)
    at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
    at org.apache.spark.api.python.BasePythonRunner$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$11.hasNext(Iterator.scala:409)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:232)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:170)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:123)
    at org.apache.spark.executor.Executor$TaskRunner$$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$$failJobAndIndependentStages(DAGScheduler.scala:2041)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2029)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:2028)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2028)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:966)
    at scala.Option.foreach(Option.scala:257)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:966)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2262)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2211)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2200)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:777)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
    ... 33 more
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 377, in main
    process()
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 372, in process
    serializer.dump_stream(func(split_index, iterator), outfile)
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 248, in <lambda>
    func = lambda _, it: map(mapper, it)
  File "<string>", line 1, in <lambda>
  File "/mnt/yarn/usercache/hadoop/appcache/application_1576264052209_0001/container_1576264052209_0001_01_000002/pyspark.zip/pyspark/worker.py", line 129, in wrapped
    return [(result[field.name], to_arrow_type(field.dataType)) for field in return_type]
  File "/usr/local/lib64/python2.7/site-packages/pandas/core/frame.py", line 2927, in __getitem__
    indexer = self.columns.get_loc(key)
  File "/usr/local/lib64/python2.7/site-packages/pandas/core/indexes/base.py", line 2659, in get_loc
    return self._engine.get_loc(self._maybe_cast_indexer(key))
  File "pandas/_libs/index.pyx", line 108, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/index.pyx", line 132, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/hashtable_class_helper.pxi", line 1601, in pandas._libs.hashtable.PyObjectHashTable.get_item
  File "pandas/_libs/hashtable_class_helper.pxi", line 1608, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: 'v'

    at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456)
    at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:172)
    at org.apache.spark.sql.execution.python.ArrowPythonRunner$$anon$1.read(ArrowPythonRunner.scala:122)
    at org.apache.spark.api.python.BasePythonRunner$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$11.hasNext(Iterator.scala:409)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:232)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:170)
    at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:169)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:123)
    at org.apache.spark.executor.Executor$TaskRunner$$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

I've tried every configuration change I can come up with but keep getting this same error. Any ideas on resolving this error would be appreciated.

Answer 1

I found two problems in your code.

1. You have write df['v_2'] = df['v'] * 2 . What is df['v'] that column not mentioned in your schema.

2. In your def process_customer_data(spark, input_path, output_path): function you didn't use input_path parameter But in your main you passed value for the input_path parameter.