我是 pyspark 的新手。我在本地机器上运行pyspark。我试图从pyspark的数据框中写到CSV文件。所以我写了下面的代码
dataframe.write.mode('append').csv(outputPath)
但是我得到了一个错误信息
Traceback (most recent call last):
File "D:\PycharmProjects\pythonProject\org\spark\weblog\SparkWebLogsAnalysis.py", line 71, in <module>
weblog_sessionIds.write.mode('append').csv(outputPath)
File "C:\spark-3.1.2-bin-hadoop3.2\python\pyspark\sql\readwriter.py", line 1372, in csv
self._jwrite.csv(path)
File "C:\spark-3.1.2-bin-hadoop3.2\python\lib\py4j-0.10.9-src.zip\py4j\java_gateway.py", line 1304, in __call__
File "C:\spark-3.1.2-bin-hadoop3.2\python\pyspark\sql\utils.py", line 111, in deco
return f(*a, **kw)
File "C:\spark-3.1.2-bin-hadoop3.2\python\lib\py4j-0.10.9-src.zip\py4j\protocol.py", line 326, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o49.csv.
: java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.createDirectoryWithMode0(Ljava/lang/String;I)V
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createDirectoryWithMode0(Native Method)
at org.apache.hadoop.io.nativeio.NativeIO$Windows.createDirectoryWithMode(NativeIO.java:560)
at org.apache.hadoop.fs.RawLocalFileSystem.mkOneDirWithMode(RawLocalFileSystem.java:534)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:587)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:559)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:586)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:559)
at org.apache.hadoop.fs.ChecksumFileSystem.mkdirs(ChecksumFileSystem.java:705)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.setupJob(FileOutputCommitter.java:354)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.setupJob(HadoopMapReduceCommitProtocol.scala:178)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:173)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:188)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:108)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:106)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:131)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:180)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:218)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:215)