同时又毁了这一切
spark_df.write.option("header",True).partitionBy("variant").mode("overwrite") .csv("/tmp/covid")
它把我的错误
Py4JJavaError Traceback (most recent call last)
C:\Users\NISHAN~1.ARY\AppData\Local\Temp/ipykernel_68352/2305704997.py in <module>
----> 1 spark_df.write.option("header",True).partitionBy("variant").mode("overwrite") .csv("/tmp/covid")
~\AppData\Local\Programs\Python\Python310\lib\site-packages\pyspark\sql\readwriter.py in csv(self, path, mode, compression, sep, quote, escape, header, nullValue, escapeQuotes, quoteAll, dateFormat, timestampFormat, ignoreLeadingWhiteSpace, ignoreTrailingWhiteSpace, charToEscapeQuoteEscaping, encoding, emptyValue, lineSep)
953 charToEscapeQuoteEscaping=charToEscapeQuoteEscaping,
954 encoding=encoding, emptyValue=emptyValue, lineSep=lineSep)
--> 955 self._jwrite.csv(path)
956
957 def orc(self, path, mode=None, partitionBy=None, compression=None):
~\AppData\Local\Programs\Python\Python310\lib\site-packages\py4j\java_gateway.py in __call__(self, *args)
1307
1308 answer = self.gateway_client.send_command(command)
-> 1309 return_value = get_return_value(
1310 answer, self.gateway_client, self.target_id, self.name)
1311
~\AppData\Local\Programs\Python\Python310\lib\site-packages\pyspark\sql\utils.py in deco(*a, **kw)
109 def deco(*a, **kw):
110 try:
--> 111 return f(*a, **kw)
112 except py4j.protocol.Py4JJavaError as e:
113 converted = convert_exception(e.java_exception)
~\AppData\Local\Programs\Python\Python310\lib\site-packages\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
324 value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
325 if answer[1] == REFERENCE_TYPE:
--> 326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
328 format(target_id, ".", name), value)
Py4JJavaError: An error occurred while calling o66.csv.
: java.lang.RuntimeException: java.io.FileNotFoundException: java.io.FileNotFoundException: HADOOP_HOME and hadoop.home.dir are unset. -see https://wiki.apache.org/hadoop/WindowsProblems
at org.apache.hadoop.util.Shell.getWinUtilsPath(Shell.java:736)
at org.apache.hadoop.util.Shell.getSetPermissionCommand(Shell.java:271)
at org.apache.hadoop.util.Shell.getSetPermissionCommand(Shell.java:287)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:978)
at org.apache.hadoop.fs.RawLocalFileSystem.mkOneDirWithMode(RawLocalFileSystem.java:660)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:700)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:672)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:699)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:672)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirsWithOptionalPermission(RawLocalFileSystem.java:699)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:672)
at org.apache.hadoop.fs.ChecksumFileSystem.mkdirs(ChecksumFileSystem.java:788)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.setupJob(FileOutputCommitter.java:356)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.setupJob(HadoopMapReduceCommitProtocol.scala:178)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:182)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:186)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:113)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:111)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:125)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:110)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:110)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:106)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:481)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:82)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:481)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:457)
at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:106)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:93)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:91)
at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:128)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:848)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:382)
at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:355)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:839)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Unknown Source)
Caused by: java.io.FileNotFoundException: java.io.FileNotFoundException: HADOOP_HOME and hadoop.home.dir are unset. -see https://wiki.apache.org/hadoop/WindowsProblems
at org.apache.hadoop.util.Shell.fileNotFoundException(Shell.java:548)
at org.apache.hadoop.util.Shell.getHadoopHomeDir(Shell.java:569)
at org.apache.hadoop.util.Shell.getQualifiedBin(Shell.java:592)
at org.apache.hadoop.util.Shell.<clinit>(Shell.java:689)
at org.apache.hadoop.util.StringUtils.<clinit>(StringUtils.java:79)
at org.apache.hadoop.conf.Configuration.getTimeDurationHelper(Configuration.java:1886)
at org.apache.hadoop.conf.Configuration.getTimeDuration(Configuration.java:1846)
at org.apache.hadoop.conf.Configuration.getTimeDuration(Configuration.java:1819)
at org.apache.hadoop.util.ShutdownHookManager.getShutdownTimeout(ShutdownHookManager.java:183)
at org.apache.hadoop.util.ShutdownHookManager$HookEntry.<init>(ShutdownHookManager.java:207)
at org.apache.hadoop.util.ShutdownHookManager.addShutdownHook(ShutdownHookManager.java:304)
at org.apache.spark.util.SparkShutdownHookManager.install(ShutdownHookManager.scala:181)
at org.apache.spark.util.ShutdownHookManager$.shutdownHooks$lzycompute(ShutdownHookManager.scala:50)
at org.apache.spark.util.ShutdownHookManager$.shutdownHooks(ShutdownHookManager.scala:48)
at org.apache.spark.util.ShutdownHookManager$.addShutdownHook(ShutdownHookManager.scala:153)
at org.apache.spark.util.ShutdownHookManager$.<init>(ShutdownHookManager.scala:58)
at org.apache.spark.util.ShutdownHookManager$.<clinit>(ShutdownHookManager.scala)
at org.apache.spark.util.Utils$.createTempDir(Utils.scala:335)
at org.apache.spark.deploy.SparkSubmit.prepareSubmitEnvironment(SparkSubmit.scala:344)
at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:898)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1043)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1052)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.io.FileNotFoundException: HADOOP_HOME and hadoop.home.dir are unset.
at org.apache.hadoop.util.Shell.checkHadoopHomeInner(Shell.java:468)
at org.apache.hadoop.util.Shell.checkHadoopHome(Shell.java:439)
at org.apache.hadoop.util.Shell.<clinit>(Shell.java:516)
... 22 more
我是否需要HDFS来运行partionBy()功能
1条答案
按热度按时间juzqafwq1#
一个变通的方法是使用google colab。你只需要先在那里安装pyspark
你不需要担心那里的hdfs。