我一直在寻找解决方案，但是找不到任何与之相关的东西。
我正在尝试使用Spark中的sc.textFile（）读取csv文件。我使用的是1.5.1版。当我读到它时，我没有收到错误，但当我尝试除.count（）以外的任何函数时，我得到一个错误...例如.take（2）。我可以在文件中读取一个熊猫文件，然后将其更改为Spark DataFrame，一切都正常。这是我尝试做rdd.take（2）
时的代码和错误 import pandas as pd
from pyspark.sql import SQLContext
sqlContext = SQLContext(sc)
data_pd = pandas.read_csv('Data_Cortex_Nuclear.csv')
df = pd.DataFrame(data_pd)
df = sqlContext.createDataFrame(df)
rdd = sc.textFile('Data_Cortex_Nuclear.csv')
rdd.take(2) #Get error
df.take(2) #Get correct code
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-165-8a14f6c71652> in <module>()
8
9 rdd = sc.textFile('Data_Cortex_Nuclear.csv')
---> 10 rdd.take(2)
11 df.take(2)
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-168-8a14f6c71652> in <module>()
8
9 rdd = sc.textFile('Data_Cortex_Nuclear.csv')
---> 10 rdd.take(2)
11 df.take(2)
C:\Users\Anna\Downloads\spark-1.5.1-bin-hadoop2.6\spark-1.5.1-bin-hadoop2.6\python\pyspark\rdd.pyc in take(self, num)
1297
1298 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))
-> 1299 res = self.context.runJob(self, takeUpToNumLeft, p)
1300
1301 items += res
C:\Users\Anna\Downloads\spark-1.5.1-bin-hadoop2.6\spark-1.5.1-bin-hadoop2.6\python\pyspark\context.pyc in runJob(self, rdd, partitionFunc, partitions, allowLocal)
914 # SparkContext#runJob.
915 mappedRDD = rdd.mapPartitions(partitionFunc)
--> 916 port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions)
917 return list(_load_from_socket(port, mappedRDD._jrdd_deserializer))
918
C:\Users\Anna\Downloads\spark-1.5.1-bin-hadoop2.6\spark-1.5.1-bin-hadoop2.6\python\lib\py4j-0.8.2.1-src.zip\py4j\java_gateway.py in __call__(self, *args)
536 answer = self.gateway_client.send_command(command)
537 return_value = get_return_value(answer, self.gateway_client,
--> 538 self.target_id, self.name)
539
540 for temp_arg in temp_args:
C:\Users\Anna\Downloads\spark-1.5.1-bin-hadoop2.6\spark-1.5.1-bin-hadoop2.6\python\pyspark\sql\utils.pyc in deco(*a, **kw)
34 def deco(*a, **kw):
35 try:
---> 36 return f(*a, **kw)
37 except py4j.protocol.Py4JJavaError as e:
38 s = e.java_exception.toString()
C:\Users\Anna\Downloads\spark-1.5.1-bin-hadoop2.6\spark-1.5.1-bin-hadoop2.6\python\lib\py4j-0.8.2.1-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
298 raise Py4JJavaError(
299 'An error occurred while calling {0}{1}{2}.\n'.
--> 300 format(target_id, '.', name), value)
301 else:
302 raise Py4JError(
Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 78.0 failed 1 times, most recent failure: Lost task 0.0 in stage 78.0 (TID 78, localhost): java.net.SocketException: Connection reset by peer: socket write error
at java.net.SocketOutputStream.socketWrite0(Native Method)
at java.net.SocketOutputStream.socketWrite(Unknown Source)
at java.net.SocketOutputStream.write(Unknown Source)
at java.io.BufferedOutputStream.flushBuffer(Unknown Source)
at java.io.BufferedOutputStream.write(Unknown Source)
at java.io.DataOutputStream.write(Unknown Source)
at java.io.FilterOutputStream.write(Unknown Source)
at org.apache.spark.api.python.PythonRDD$.writeUTF(PythonRDD.scala:622)
at org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:442)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:452)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:280)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1699)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:239)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1822)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1835)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.GeneratedMethodAccessor74.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:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Unknown Source)
Caused by: java.net.SocketException: Connection reset by peer: socket write error
at java.net.SocketOutputStream.socketWrite0(Native Method)
at java.net.SocketOutputStream.socketWrite(Unknown Source)
at java.net.SocketOutputStream.write(Unknown Source)
at java.io.BufferedOutputStream.flushBuffer(Unknown Source)
at java.io.BufferedOutputStream.write(Unknown Source)
at java.io.DataOutputStream.write(Unknown Source)
at java.io.FilterOutputStream.write(Unknown Source)
at org.apache.spark.api.python.PythonRDD$.writeUTF(PythonRDD.scala:622)
at org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:442)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:452)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:452)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:280)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1699)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:239)