Apache spark PYSPARK:读取RDD时出错

我试图从我的RDD中读取，但出现以下错误。 请告知。 该文件存在于HDFS中。我使用hadoop文件系统命令将该文件移动到HDFS中

代码：

baby_names = sc.textFile("/user/rahul/baby_names.csv")

rows = baby_names.map(lambda line:line.split(","))

for row in rows.take(rows.count()):print(row[1])

Py4JJavaError                             Traceback (most recent call last)
<ipython-input-7-b9dcd91a9f1c> in <module>()
----> 1 for row in rows.take(rows.count()):print(row[1])

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in count(self)
   1039         3
   1040         """
-> 1041         return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
   1042 
   1043     def stats(self):

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in sum(self)
   1030         6.0
   1031         """
-> 1032         return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
   1033 
   1034     def count(self):

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in fold(self, zeroValue, op)
    904         # zeroValue provided to each partition is unique from the one provided
    905         # to the final reduce call
--> 906         vals = self.mapPartitions(func).collect()
    907         return reduce(op, vals, zeroValue)
    908 

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in collect(self)
    807         """
    808         with SCCallSiteSync(self.context) as css:
--> 809             port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    810         return list(_load_from_socket(port, self._jrdd_deserializer))
    811 

/home/rahul/Hadoop/spark/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:

/home/rahul/Hadoop/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()

/home/rahul/Hadoop/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    317                 raise Py4JJavaError(
    318                     "An error occurred while calling {0}{1}{2}.\n".
--> 319                     format(target_id, ".", name), value)
    320             else:
    321                 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: file:/user/rahul/baby_names.csv
    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:202)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:53)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
    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: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:745)

错误：

baby_names = sc.textFile("/user/rahul/baby_names.csv")

rows = baby_names.map(lambda line:line.split(","))

for row in rows.take(rows.count()):print(row[1])

Py4JJavaError                             Traceback (most recent call last)
<ipython-input-7-b9dcd91a9f1c> in <module>()
----> 1 for row in rows.take(rows.count()):print(row[1])

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in count(self)
   1039         3
   1040         """
-> 1041         return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
   1042 
   1043     def stats(self):

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in sum(self)
   1030         6.0
   1031         """
-> 1032         return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
   1033 
   1034     def count(self):

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in fold(self, zeroValue, op)
    904         # zeroValue provided to each partition is unique from the one provided
    905         # to the final reduce call
--> 906         vals = self.mapPartitions(func).collect()
    907         return reduce(op, vals, zeroValue)
    908 

/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in collect(self)
    807         """
    808         with SCCallSiteSync(self.context) as css:
--> 809             port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    810         return list(_load_from_socket(port, self._jrdd_deserializer))
    811 

/home/rahul/Hadoop/spark/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:

/home/rahul/Hadoop/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()

/home/rahul/Hadoop/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    317                 raise Py4JJavaError(
    318                     "An error occurred while calling {0}{1}{2}.\n".
--> 319                     format(target_id, ".", name), value)
    320             else:
    321                 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: file:/user/rahul/baby_names.csv
    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:202)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:53)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
    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: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:745)

Py4JJavaError回溯（最近一次调用）
在（）
---->1表示行中的行。take（rows.count（））：print（行[1]）
/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc计数（self）
1039         3
1040         """
->1041返回self.mapPartitions（lambda i:[sum（1代表i中的u）]）.sum（）
1042
1043 def状态（自身）：
/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc的总和（self）
1030         6.0
1031         """
->1032返回self.mapPartitions（lambda x:[求和（x）]）.fold（0，运算符.add）
1033
1034 def计数（自身）：
/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc（self，zeroValue，op）
904#提供给每个分区的zeroValue与提供的分区是唯一的
905#到最后的reduce通话
-->906 VAL=self.mapPartitions（func.collect（））
907返回减少（op、VAL、零值）
908
/home/rahul/Hadoop/spark/python/pyspark/rdd.pyc in collect（self）
807         """
808使用SCCallSiteSync（self.context）作为css：
-->809 port=self.ctx.\u jvm.PythonRDD.collectAndServe（self.\u jrdd.rdd（））
810返回列表（_从_套接字加载（端口，self._jrdd_反序列化器））
811
/home/rahul/Hadoop/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in u__调用（self，*args）
1131 answer=self.gateway\u client.send\u命令（command）
1132返回值=获取返回值(
->1133应答，self.gateway\u客户端，self.target\u id，self.name）
1134
1135对于临时参数中的临时参数：
/装饰中的home/rahul/Hadoop/spark/python/pyspark/sql/utils.pyc（*a，**kw）
61 def装饰（*a，**千瓦）：
62尝试：
--->63返回f（*a，**kw）
64除py4j.protocol.Py4JJavaError外的其他错误为e:
65 s=e.java_exception.toString（）
/获取返回值中的home/rahul/Hadoop/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py（答案、网关客户端、目标id、名称）
317 raise Py4JJavaError(
318“调用{0}{1}{2}时出错。\n”。
-->319格式（目标id，“.”，名称），值）
320其他：
321升起Py4JError(
Py4JJavaError:调用z:org.apache.spark.api.python.PythonRDD.collectAndServe时出错。
：org.apache.hadoop.mapred.InvalidInputException:输入路径不存在：文件：/user/rahul/baby_names.csv
位于org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus（FileInputFormat.java:287）
位于org.apache.hadoop.mapred.FileInputFormat.listStatus（FileInputFormat.java:229）
位于org.apache.hadoop.mapred.FileInputFormat.getSplits（FileInputFormat.java:315）
位于org.apache.spark.rdd.HadoopRDD.getPartitions（HadoopRDD.scala:202）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:252）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:250）
位于scala.Option.getOrElse（Option.scala:121）
位于org.apache.spark.rdd.rdd.partitions（rdd.scala:250）
位于org.apache.spark.rdd.MapPartitionsRDD.getPartitions（MapPartitionsRDD.scala:35）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:252）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:250）
位于scala.Option.getOrElse（Option.scala:121）
位于org.apache.spark.rdd.rdd.partitions（rdd.scala:250）
位于org.apache.spark.api.python.PythonRDD.getPartitions（PythonRDD.scala:53）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:252）
位于org.apache.spark.rdd.rdd$$anonfun$partitions$2.apply（rdd.scala:250）
位于scala.Option.getOrElse（Option.scala:121）
位于org.apache.spark.rdd.rdd.partitions（rdd.scala:250）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:1958）
位于org.apache.spark.rdd.rdd$$anonfun$collect$1.apply（rdd.scala:935）
位于org.apache.spark.rdd.RDDOperationScope$.withScope（RDDOperationScope.scala:151）
位于org.apache.spark.rdd.RDDOperationScope$.withScope（RDDOperationScope.scala:112）
位于org.apache.spark.rdd.rdd.withScope（rdd.scala:362）
位于org.apache.spark.rdd.rdd.collect（rdd.scala:934）
位于org.apache.spark.api.python.PythonRDD$.collectAndServe（PythonRDD.scala:453）
位于org.apache.spark.api.python.PythonRDD.collectAndServe（PythonRDD.scala）
在sun.reflect.NativeMethodAccessorImpl.invoke0（本机方法）处
位于sun.reflect.NativeMethodAccessorImpl.invoke（NativeMethodAccessorImpl.java:62）
在sun.reflect.DelegatingMethodAccessorImpl.invoke（DelegatingMethodAccessorImpl.java:43）中
位于java.lang.reflect.Method.invoke（Method.java:498）
位于py4j.reflection.MethodInvoker.invoke（MethodInvoker.java:244）
位于py4j.reflection.ReflectionEngine.invoke（ReflectionEngine.java:357）
在py4j.Gateway.invoke处（Gateway.java:280）
位于py4j.commands.AbstractCommand.invokeMethod（AbstractCommand.java:132）
在py4j.commands.CallCommand.execute（CallCommand.java:79）
在py4j.GatewayConnection.run处（GatewayConnection.java:214）
运行（Thread.java:745）

如果有任何有关spark配置更改的链接，请共享。

如果要读取所有行，为什么不使用

collect（）

baby_names = sc.textFile("/user/rahul/baby_names.csv")

rows = baby_names.map(lambda line:line.split(",")) \
                 .filter(lambda line: len(line)>1) \
                 .map(lambda line: (line[0],line[1]))

for row in rows.collect():print(row)

或

---

collect（）-以数组的形式返回数据集的所有元素 驱动程序。这通常是有用的后，过滤器或其他 返回足够小的数据子集的操作。

count（）-返回数据集中的元素数。

take（n）-返回 包含数据集前n个元素的数组

---

org.apache.hadoop.mapred.InvalidInputException:输入路径不存在：文件：/user/rahul/baby_names.csvlooks就像您提供的本地路径一样-您在哪里找到的