Estou lendo um arquivo csv e transformando em parket:
leitura:
empresas2 = spark.read.csv(
r'C:\Users\guilherme.kanai\Desktop\arquivos\any.csv',
sep=';',
inferSchema=True,
header=True)
enviando para parket:
empresas2.write.parquet(
path= r'C:\Users\guilherme.kanai\Desktop\arquivos\parquet\novo.parquet',
#OU - r'C:\Users\guilherme.kanai\Desktop\arquivos\parquet\'
mode='overwrite',
)
Ambos dão o mesmo erro
Py4JJavaError Traceback (most recent call last)
c:\Users\guilherme.kanai\Downloads\aula6_projeto_spark.ipynb Cell 12 in ()
----> 1 empresas2.write.parquet(
2 path= r'C:\Users\guilherme.kanai\Desktop\arquivos\parquet\novo.parquet',
3 mode='overwrite',
4 )
File c:\Users\guilherme.kanai\AppData\Local\Programs\Python\Python39\lib\site-packages\pyspark\sql\readwriter.py:1140, in DataFrameWriter.parquet(self, path, mode, partitionBy, compression)
1138 self.partitionBy(partitionBy)
1139 self._set_opts(compression=compression)
-> 1140 self._jwrite.parquet(path)
File c:\Users\guilherme.kanai\AppData\Local\Programs\Python\Python39\lib\site-packages\py4j\java_gateway.py:1321, in JavaMember.__call__(self, *args)
1315 command = proto.CALL_COMMAND_NAME +\
1316 self.command_header +\
1317 args_command +\
1318 proto.END_COMMAND_PART
1320 answer = self.gateway_client.send_command(command)
-> 1321 return_value = get_return_value(
1322 answer, self.gateway_client, self.target_id, self.name)
1324 for temp_arg in temp_args:
1325 temp_arg._detach()
File c:\Users\guilherme.kanai\AppData\Local\Programs\Python\Python39\lib\site-packages\pyspark\sql\utils.py:190, in capture_sql_exception..deco(*a, **kw)
188 def deco(*a: Any, **kw: Any) -> Any:
189 try:
--> 190 return f(*a, **kw)
191 except Py4JJavaError as e:
192 converted = convert_exception(e.java_exception)
File c:\Users\guilherme.kanai\AppData\Local\Programs\Python\Python39\lib\site-packages\py4j\protocol.py:326, 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)
329 else:
330 raise Py4JError(
331 "An error occurred while calling {0}{1}{2}. Trace:\n{3}\n".
332 format(target_id, ".", name, value))
Py4JJavaError: An error occurred while calling o34.parquet.
: 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:288)
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)