欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

Py4JJavaError

程序员文章站 2022-05-27 23:16:02
...
textFile=sc.textFile("hdfs://master:9000/user/hduser/wordcount/input/LICENCE.txt")
textFile.count()
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-8-86c1629ebf32> in <module>()
      1 testFile=sc.textFile("hdfs://master:9000/user/hduser/wordcount/input/LICENCE.TXT")
----> 2 testFile.count()

/usr/local/spark/python/pyspark/rdd.pyc in count(self)
   1054         3
   1055         """
-> 1056         return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
   1057 
   1058     def stats(self):

/usr/local/spark/python/pyspark/rdd.pyc in sum(self)
   1045         6.0
   1046         """
-> 1047         return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
   1048 
   1049     def count(self):

/usr/local/spark/python/pyspark/rdd.pyc in fold(self, zeroValue, op)
    919         # zeroValue provided to each partition is unique from the one provided
    920         # to the final reduce call
--> 921         vals = self.mapPartitions(func).collect()
    922         return reduce(op, vals, zeroValue)
    923 

/usr/local/spark/python/pyspark/rdd.pyc in collect(self)
    822         """
    823         with SCCallSiteSync(self.context) as css:
--> 824             port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    825         return list(_load_from_socket(port, self._jrdd_deserializer))
    826 

/usr/local/spark/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1158         answer = self.gateway_client.send_command(command)
   1159         return_value = get_return_value(
-> 1160             answer, self.gateway_client, self.target_id, self.name)
   1161 
   1162         for temp_arg in temp_args:

/usr/local/spark/python/pyspark/sql/utils.pyc 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-0.10.6-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    318                 raise Py4JJavaError(
    319                     "An error occurred while calling {0}{1}{2}.\n".
--> 320                     format(target_id, ".", name), value)
    321             else:
    322                 raise Py4JError(

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: hdfs://master:9000/user/hduser/wordcount/input/LICENCE.TXT
    at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)
    at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
    at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
    at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:200)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
    at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:53)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2092)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:939)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:938)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:153)
    at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
    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.GatewayConnection.run(GatewayConnection.java:214)
    at java.lang.Thread.run(Thread.java:748)


原因:路径没写对
仅供各位参考
修改:

textFile=sc.textFile("hdfs://master:9000/user/hduser/wordcount/input/LICENSE.txt")
textFile.count()
相关标签: ipython

推荐阅读