ParquetデータをPySpark
にロードしようとしています。ここで、列の名前にはスペースが含まれています。
df = spark.read.parquet('my_parquet_dump')
df.select(df['Foo Bar'].alias('foobar'))
列のエイリアスを作成しましたが、このエラーとエラーがJVM
のPySpark
側から伝播します。以下にスタックトレースを添付しました。
Scalaでデータを前処理せずに、またソースの寄木細工のファイルを変更せずに、この寄木細工のファイルをPySpark
にロードする方法はありますか?
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
/usr/local/python/pyspark/sql/utils.py in deco(*a, **kw)
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
/usr/local/python/lib/py4j-0.10.4-src.Zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
318 "An error occurred while calling {0}{1}{2}.\n".
--> 319 format(target_id, ".", name), value)
320 else:
Py4JJavaError: An error occurred while calling o864.collectToPython.
: org.Apache.spark.sql.AnalysisException: Attribute name "Foo Bar" contains invalid character(s) among " ,;{}()\n\t=". Please use alias to rename it.;
at org.Apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$.checkConversionRequirement(ParquetSchemaConverter.scala:581)
at org.Apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$.checkFieldName(ParquetSchemaConverter.scala:567)
at org.Apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$$anonfun$checkFieldNames$1.apply(ParquetSchemaConverter.scala:575)
at org.Apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$$anonfun$checkFieldNames$1.apply(ParquetSchemaConverter.scala:575)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at org.Apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$.checkFieldNames(ParquetSchemaConverter.scala:575)
at org.Apache.spark.sql.execution.datasources.parquet.ParquetFileFormat.buildReaderWithPartitionValues(ParquetFileFormat.scala:293)
at org.Apache.spark.sql.execution.FileSourceScanExec.inputRDD$lzycompute(DataSourceScanExec.scala:285)
at org.Apache.spark.sql.execution.FileSourceScanExec.inputRDD(DataSourceScanExec.scala:283)
at org.Apache.spark.sql.execution.FileSourceScanExec.inputRDDs(DataSourceScanExec.scala:303)
at org.Apache.spark.sql.execution.ProjectExec.inputRDDs(basicPhysicalOperators.scala:42)
at org.Apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:386)
at org.Apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.Apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:117)
at org.Apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:138)
at org.Apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.Apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:135)
at org.Apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:116)
at org.Apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:228)
at org.Apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:311)
at org.Apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
at org.Apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply$mcI$sp(Dataset.scala:2803)
at org.Apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:2800)
at org.Apache.spark.sql.Dataset$$anonfun$collectToPython$1.apply(Dataset.scala:2800)
at org.Apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.Apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2823)
at org.Apache.spark.sql.Dataset.collectToPython(Dataset.scala:2800)
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:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.Java:132)
at py4j.commands.CallCommand.execute(CallCommand.Java:79)
at py4j.GatewayConnection.run(GatewayConnection.Java:214)
at Java.lang.Thread.run(Thread.Java:748)
During handling of the above exception, another exception occurred:
AnalysisException Traceback (most recent call last)
<ipython-input-37-9d7c55a5465c> in <module>()
----> 1 spark.sql("SELECT `Foo Bar` as hey FROM df limit 10").take(1)
/usr/local/python/pyspark/sql/dataframe.py in take(self, num)
474 [Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
475 """
--> 476 return self.limit(num).collect()
477
478 @since(1.3)
/usr/local/python/pyspark/sql/dataframe.py in collect(self)
436 """
437 with SCCallSiteSync(self._sc) as css:
--> 438 port = self._jdf.collectToPython()
439 return list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
440
/usr/local/python/lib/py4j-0.10.4-src.Zip/py4j/Java_gateway.py in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/usr/local/python/pyspark/sql/utils.py in deco(*a, **kw)
67 e.Java_exception.getStackTrace()))
68 if s.startswith('org.Apache.spark.sql.AnalysisException: '):
---> 69 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
70 if s.startswith('org.Apache.spark.sql.catalyst.analysis'):
71 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
AnalysisException: 'Attribute name "Foo Bar" contains invalid character(s) among " ,;{}()\\n\\t=". Please use alias to rename it.;'
@MaFFからの提案は私に合格したようです
df = spark.read.parquet("my_parquet_dump")
df2 = df.withColumnRenamed("Foo Bar", "foobar")
df2.registerTempTable("temp")
hc.sql("CREATE TABLE persistent STORED AS PARQUET AS SELECT * FROM temp")
どのようなエラーメッセージが表示されますか?
悪い記号を正規表現に置き換えることができます。私の 回答 を確認してください。