import os, sys
# Set the path for spark installation
# this is the path where you have built spark
os.environ['SPARK_HOME']="C:\spark\spark-1.5.1-bin-hadoop2.6"
# Append to PYTHONPATH so that pyspark could be found
sys.path.append("C:\spark\spark-1.5.1-bin-hadoop2.6\python")
sys.path.append("C:\spark\spark-1.5.1-bin-hadoop2.6\python\lib")
# Now we are ready to import Spark Modules
try:
from pyspark import SparkContext
from pyspark import SparkConf
except ImportError as e:
print ("Error importing Spark Modules", e)
sys.exit(1)
conf = SparkConf().setMaster('local').setAppName('MyApp')
sc = SparkContext(conf=conf)
People=["1,Maj,123","2,Pvt,333","3,Col,999"]
rrd1=sc.parallelize(People)
rrd1.count()
缺货[22]： 3
rrd1.first()
Py4JJavaError Traceback (most recent call last)
<ipython-input-25-7022a79b5145> in <module>()
----> 1 rrd1.first()
C:\spark\spark-1.5.1-bin-hadoop2.6\python\pyspark\rdd.py in first(self)
1315 ValueError: RDD is empty
1316 """
-> 1317 rs = self.take(1)
1318 if rs:
1319 return rs[0]
C:\spark\spark-1.5.1-bin-hadoop2.6\python\pyspark\rdd.py 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:\spark\spark-1.5.1-bin-hadoop2.6\python\pyspark\context.py 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:\Anaconda\lib\site-packages\py4j-0.9-py2.7.egg\py4j\java_gateway.pyc in __call__(self, *args)
811 answer = self.gateway_client.send_command(command)
812 return_value = get_return_value(
--> 813 answer, self.gateway_client, self.target_id, self.name)
814
815 for temp_arg in temp_args:
C:\Anaconda\lib\site-packages\py4j-0.9-py2.7.egg\py4j\protocol.pyc in get_return_value(answer, gateway_client, target_id, name)
306 raise Py4JJavaError(
307 "An error occurred while calling {0}{1}{2}.\n".
--> 308 format(target_id, ".", name), value)
309 else:
310 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 13.0 failed 1 times, most recent failure: Lost task 0.0 in stage 13.0 (TID 19, localhost): java.net.SocketException: Connection reset
at java.net.SocketInputStream.read(Unknown Source)
at java.net.SocketInputStream.read(Unknown Source)
at java.io.BufferedInputStream.fill(Unknown Source)
at java.io.BufferedInputStream.read(Unknown Source)
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:139)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$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.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: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
at java.net.SocketInputStream.read(Unknown Source)
at java.net.SocketInputStream.read(Unknown Source)
at java.io.BufferedInputStream.fill(Unknown Source)
at java.io.BufferedInputStream.read(Unknown Source)
at java.io.DataInputStream.readInt(Unknown Source)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:139)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
... 1 more