gpt4 book ai didi

pyspark - 无法将 Spark 数据帧以 Parquet 文件格式写入 PySpark 中的 C 驱动器

转载 作者:行者123 更新时间:2023-12-02 19:46:12 25 4
gpt4 key购买 nike

我正在使用以下命令尝试将 Spark(2.4.4 使用 Ananaconda 3 Jupyter Notebook)数据帧写入 Pyspark 中的 parquet 文件,并收到一条我无法解决的非常奇怪的错误消息。如果有任何见解,我将不胜感激。

df.write.mode("overwrite").parquet("test/")

错误信息如下:

--------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-37-2b4a1d75a5f6> in <module>()
1 # df.write.partitionBy("AB").parquet("C:/test.parquet",mode='overwrite')
----> 2 df.write.mode("overwrite").parquet("test/")
3 # df.write.mode('SaveMode.Overwrite').parquet("C:/test.parquet")

C:\spark-2.4.4-bin-hadoop2.7\python\pyspark\sql\readwriter.py in parquet(self, path, mode, partitionBy, compression)
841 self.partitionBy(partitionBy)
842 self._set_opts(compression=compression)
--> 843 self._jwrite.parquet(path)
844
845 @since(1.6)

C:\spark-2.4.4-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\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:

C:\spark-2.4.4-bin-hadoop2.7\python\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()

C:\spark-2.4.4-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\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 o862.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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80)
at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80)
at org.apache.spark.sql.DataFrameWriter$$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$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229)
at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:566)
at sun.reflect.GeneratedMethodAccessor114.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 52.0 failed 1 times, most recent failure: Lost task 0.0 in stage 52.0 (TID 176, localhost, executor driver): java.io.IOException: (null) entry in command string: null chmod 0644 C:\Users\583621\OneDrive - Booz Allen Hamilton\Personal\Teaching\PySpark Essentials for Data Scientists\PySpark DataFrame Essentials\test\_temporary\0\_temporary\attempt_20191206164455_0052_m_000000_176\part-00000-2cd01dbe-9e3f-44a5-88e1-e904822024c2-c000.snappy.parquet
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:770)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:866)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:849)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:733)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:225)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:307)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:296)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:328)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSOutputSummer.<init>(ChecksumFileSystem.java:398)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:461)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:440)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:911)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:892)
at org.apache.parquet.hadoop.util.HadoopOutputFile.create(HadoopOutputFile.java:74)
at org.apache.parquet.hadoop.ParquetFileWriter.<init>(ParquetFileWriter.java:248)
at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:390)
at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:349)
at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetOutputWriter.scala:37)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anon$1.newInstance(ParquetFileFormat.scala:151)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:236)
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$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:167)
... 32 more
Caused by: java.io.IOException: (null) entry in command string: null chmod 0644 C:\Users\583621\OneDrive - Booz Allen Hamilton\Personal\Teaching\PySpark Essentials for Data Scientists\PySpark DataFrame Essentials\test\_temporary\0\_temporary\attempt_20191206164455_0052_m_000000_176\part-00000-2cd01dbe-9e3f-44a5-88e1-e904822024c2-c000.snappy.parquet
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:770)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:866)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:849)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:733)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:225)
at org.apache.hadoop.fs.RawLocalFileSystem$LocalFSFileOutputStream.<init>(RawLocalFileSystem.java:209)
at org.apache.hadoop.fs.RawLocalFileSystem.createOutputStreamWithMode(RawLocalFileSystem.java:307)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:296)
at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:328)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSOutputSummer.<init>(ChecksumFileSystem.java:398)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:461)
at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:440)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:911)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:892)
at org.apache.parquet.hadoop.util.HadoopOutputFile.create(HadoopOutputFile.java:74)
at org.apache.parquet.hadoop.ParquetFileWriter.<init>(ParquetFileWriter.java:248)
at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:390)
at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:349)
at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetOutputWriter.scala:37)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anon$1.newInstance(ParquetFileFormat.scala:151)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.newOutputWriter(FileFormatDataWriter.scala:120)
at org.apache.spark.sql.execution.datasources.SingleDirectoryDataWriter.<init>(FileFormatDataWriter.scala:108)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:236)
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$TaskRunner.run(Executor.scala:414)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
... 1 more


1
# Now something a bit more complicated: Read in a full parquet
2
parquet

最佳答案

您需要设置 Hadoop 主目录。您可以从 Hadoop 重新分发中获取 WINUTILS.EXE 二进制文件。对于某些 Hadoop 版本,有一个存储库 on github .

然后1) 您可以将环境变量%HADOOP_HOME%设置为指向包含WINUTILS.EXE的BIN目录之上的目录。

2) 或在代码中配置为

import sys
import os

os.environ['HADOOP_HOME'] = "C:/Mine/Spark/hadoop-2.6.0"
sys.path.append("C:/Mine/Spark/hadoop-2.6.0/bin")

希望这有帮助!

关于pyspark - 无法将 Spark 数据帧以 Parquet 文件格式写入 PySpark 中的 C 驱动器,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/59220832/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com