Getting error while writing the spark dataframe as CSV file - pyspark

Question

23/01/10 14:51:56 ERROR FileFormatWriter: Aborting job 18d74180-1f1e-44ea-80dc-caa5a2fe0525.
java.io.IOException: Failed to rename DeprecatedRawLocalFileStatus{path=file:/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/test/\_temporary/0/task_2023011020
21531054031999327673221_0005_m_000000/part-00000-250cb7ce-e146-4cfd-b9f1-f810af4630f2-c000.csv; isDirectory=false; length=13520; replication=1; blocksize=33554432; modification_time=16
73362315593; access_time=1673362315593; owner=; group=; permission=rw-rw-rw-; isSymlink=false; hasAcl=false; isEncrypted=false; isErasureCoded=false} to file:/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/test/part-00000-250cb7ce-e146-4cfd-b9f1-f810af4630f2-c000.csv
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.mergePaths(FileOutputCommitter.java:477)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.mergePaths(FileOutputCommitter.java:490)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJobInternal(FileOutputCommitter.java:405)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJob(FileOutputCommitter.java:377)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.commitJob(HadoopMapReduceCommitProtocol.scala:192)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$25(FileFormatWriter.scala:267)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.util.Utils$.timeTakenMs(Utils.scala:642)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:267)
at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:186)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$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$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:98)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:109)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:169)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:95)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:94)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:584)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:176)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:584)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:560)
at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:94)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:81)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:79)
at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:116)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:860)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:390)
at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:363)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:851)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
23/01/10 14:51:56 WARN FileUtil: Failed to delete file or dir \[/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/test/\_temporary/0/task_202301102021531054031999327673221_0005_m_000000/.part-00000-250cb7ce-e146-4cfd-b9f1-f810af4630f2-c000.csv.crc\]: it still exists.
23/01/10 14:51:56 WARN FileUtil: Failed to delete file or dir \[/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/test/\_temporary/0/task_202301102021531054031999327673221_0005_m_000000/part-00000-250cb7ce-e146-4cfd-b9f1-f810af4630f2-c000.csv\]: it still exists.
Traceback (most recent call last):
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/manage.py", line 21, in \<module\>
main()
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/manage.py", line 17, in main
execute_from_command_line(sys.argv)
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/django/core/management/__init__.py", line 419, in execute_from_command_line
utility.execute()
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/django/core/management/__init__.py", line 413, in execute
self.fetch_command(subcommand).run_from_argv(self.argv)
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/django/core/management/base.py", line 354, in run_from_argv
self.execute(\*args, \*\*cmd_options)
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/django/core/management/base.py", line 398, in execute
output = self.handle(\*args, \*\*options)
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/core/management/commands/prepare_ncoa_sp.py", line 26, in handle
step.start()
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/core/management/commands/prepare_ncoa_sp.py", line 45, in start
self.prepare_agent_address_updates()
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/core/management/commands/prepare_ncoa_sp.py", line 141, in prepare_agent_address_updates
self.\_load_and_normalize(file_glob, {
File "/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/core/management/commands/prepare_ncoa_sp.py", line 127, in \_load_and_normalize
df.write.option("header", True).csv('test')
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/pyspark/sql/readwriter.py", line 1240, in csv
self.\_jwrite.csv(path)
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/py4j/java_gateway.py", line 1321, in __call__
return_value = get_return_value(
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/pyspark/sql/utils.py", line 190, in deco
return f(\*a, \*\*kw)
File "/home/admin123/.virtualenvs/fcd/lib/python3.10/site-packages/py4j/protocol.py", line 326, in get_return_value
raise Py4JJavaError(
py4j.protocol.Py4JJavaError: An error occurred while calling o298.csv.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.errors.QueryExecutionErrors$.jobAbortedError(QueryExecutionErrors.scala:651)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:278)
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$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:98)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:109)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:169)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:95)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:98)
at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:94)
at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:584)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:176)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:584)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:560)
at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:94)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:81)
at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:79)
at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:116)
at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:860)
at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:390)
at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:363)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
at org.apache.spark.sql.DataFrameWriter.csv(DataFrameWriter.scala:851)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
Caused by: java.io.IOException: Failed to rename DeprecatedRawLocalFileStatus{path=file:/d/myproject/FCD/Sparck_updated_code/first-class-data-backend/first_class/test/\_temporary/0/task
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.mergePaths(FileOutputCommitter.java:490)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJobInternal(FileOutputCommitter.java:405)
at org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter.commitJob(FileOutputCommitter.java:377)
at org.apache.spark.internal.io.HadoopMapReduceCommitProtocol.commitJob(HadoopMapReduceCommitProtocol.scala:192)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$25(FileFormatWriter.scala:267)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.util.Utils$.timeTakenMs(Utils.scala:642)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:267)
... 42 more
As you can see above error occurred while try to write the spark dataframe as csv file
sparkContext = SparkContext("spark://DESKTOP-1L1BM8L.localdomain:7077", "fcd_spark_session")
spark_configuration = sparkContext._conf.setAll(
[("spark.shuffle.service.enabled", "false"), ("spark.dynamicAllocation.enabled", "false"),
("spark.executor.memory", "2g"), ("spark.executor.instances", 2)])
sparkContext.stop()
self.spark_session = SparkSession.builder.appName("fcd_spark_session").config(
conf=spark_configuration) \
.master('spark://DESKTOP-1L1BM8L.localdomain:7077').getOrCreate()
def _load_and_normalize(self, glob_paths, renames=None, columns=[], processed_columns=[],
remove_duplicates=[], ):
renames = renames or {}
files = sorted(glob.glob(glob_paths))
for filepath in files:
file_name = basename(filepath)
logger.info(f'adding {basename(filepath)}')
file_write_path = self.csv_fullpath(self.cleaned_folder, "NCOA_address", file_name)
print(file_write_path)
if not os.path.exists(file_write_path):
df = self.read_csv(filepath)
df = df[columns].copy()
df = df[:100]
df = df.fillna('').astype('str')
df = df.apply(tuple, axis=1).tolist()
df = self.spark_session.createDataFrame(df, columns)
df = self.add_procuredate(df, file_name)
df = self.uppercase_and_trim_all_columns(df)
for rename_columns in renames:
df = df.withColumnRenamed(rename_columns, renames[rename_columns])
all_cols_except_procure = [col for col in df.schema.names if col != 'procure_date']
df = df.dropDuplicates(all_cols_except_procure)
df = self.get_normalized_address(df)
df = self.get_normalized_address(df, col_name='orig_normalized_address',
full_address_col='orig_address', city_col='orig_city',
state_col='orig_state',
zip_col='orig_zip')
df = df.where((df.full_address != '') & (df.normalized_address != ''))
df = df.select(processed_columns)
df = df.dropDuplicates(remove_duplicates)
df.write.option("header", True).format("csv").csv('test')
gc.collect()
else:
logger.info(f'{basename(filepath)} file is already available in cleaned folder')
Any suggestions and please comment if you need any additional info regarding the code and config