python - 通过 pyspark py4jjavaerror 使用 spark 加载 csv 文件

Question

我正在尝试使用 pyspark 将文件加载到 spark 中，我收到此错误，无法弄清楚，当点击下面的命令时出现问题，尝试加载我本地主目录上的 csv 文件。

我使用的是火花集群模式而不是本地模式。但是这两种模式都会出现问题。

df_Csv = (spark.read.format("csv")
                  .option("header", "true")
                  .option("mode", "DROPMALFORMED")
                  .load("file://"+csv_path_local+"/Resultats_17PCIX.csv"))

Py4JJavaError                             Traceback (most recent call last)
<ipython-input-24-fed66bbb39c2> in <module>()
      3                   .option("header", "true")
      4                   .option("mode", "DROPMALFORMED")
----> 5                   .load("file://"+csv_path_local+"/Resultats_17PCIX.csv"))
      6 
      7 df_Csv.registerTempTable("df_Csv")

/usr/local/spark/python/pyspark/sql/readwriter.py in load(self, path, format, schema, **options)
    164         self.options(**options)
    165         if isinstance(path, basestring):
--> 166             return self._df(self._jreader.load(path))
    167         elif path is not None:
    168             if type(path) != list:

/usr/local/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

/usr/local/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o382.load.
: scala.MatchError: 3.1.0 (of class java.lang.String)
    at org.apache.spark.sql.hive.client.IsolatedClientLoader$.hiveVersion(IsolatedClientLoader.scala:89)
    at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:300)
    at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:287)
    at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
    at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:195)
    at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
    at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:194)
    at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
    at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.externalCatalog(HiveSessionStateBuilder.scala:39)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog$lzycompute(HiveSessionStateBuilder.scala:54)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.catalog(HiveSessionStateBuilder.scala:52)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anon$1.<init>(HiveSessionStateBuilder.scala:69)
    at org.apache.spark.sql.hive.HiveSessionStateBuilder.analyzer(HiveSessionStateBuilder.scala:69)
    at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
    at org.apache.spark.sql.internal.BaseSessionStateBuilder$$anonfun$build$2.apply(BaseSessionStateBuilder.scala:293)
    at org.apache.spark.sql.internal.SessionState.analyzer$lzycompute(SessionState.scala:79)
    at org.apache.spark.sql.internal.SessionState.analyzer(SessionState.scala:79)
    at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
    at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
    at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
    at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:74)
    at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(SparkSession.scala:432)
    at org.apache.spark.sql.execution.datasources.csv.TextInputCSVDataSource$.createBaseDataset(CSVDataSource.scala:183)
    at org.apache.spark.sql.execution.datasources.csv.TextInputCSVDataSource$.infer(CSVDataSource.scala:147)
    at org.apache.spark.sql.execution.datasources.csv.CSVDataSource.inferSchema(CSVDataSource.scala:63)
    at org.apache.spark.sql.execution.datasources.csv.CSVFileFormat.inferSchema(CSVFileFormat.scala:57)
    at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$8.apply(DataSource.scala:203)
    at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$8.apply(DataSource.scala:203)
    at scala.Option.orElse(Option.scala:289)
    at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:202)
    at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:393)
    at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
    at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:174)
    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.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Unknown Source)

我正在使用带有 python 3.6、java 1.8 和 hadoop 3.1.0 的 spark 版本 2.3.2

标签： pythoncsvapache-sparkpyspark