我正在RDD中使用Spark打印Ipython，当我这样做时，我收到此错误：
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-4-77015cd18335> in <module>()
---> 24 print inputData.collect()
25
26
/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/pyspark/rdd.pyc in collect(self)
771 """
772 with SCCallSiteSync(self.context) as css:
--> 773 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
774 return list(_load_from_socket(port, self._jrdd_deserializer))
775
/home/vagrant/spark-1.5.0-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:
/home/vagrant/spark-1.5.0-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()
/home/vagrant/spark-1.5.0-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.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 7.0 failed 1 times, most recent failure: Lost task 0.0 in stage 7.0 (TID 56, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 98, in main
command = pickleSer._read_with_length(infile)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
return self.loads(obj)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 421, in loads
return pickle.loads(obj)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 25, in <module>
ImportError: No module named numpy
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:138)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:179)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1910)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.RDD.collect(RDD.scala:904)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:373)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 98, in main
command = pickleSer._read_with_length(infile)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
return self.loads(obj)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 421, in loads
return pickle.loads(obj)
File "/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 25, in <module>
ImportError: No module named numpy
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:138)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:179)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
... 1 more
我目前的代码是：
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.tree import DecisionTree, DecisionTreeModel
from pyspark.mllib.util import MLUtils
import os.path
import numpy as np
print np.version.version
def extract(line):
return (line[1])
inputPath = os.path.join('file1.csv')
fileName = os.path.join(inputPath)
Data = sc.textFile(fileName).zipWithIndex().filter(lambda (line,rownum): rownum>0).map(lambda (line, rownum): line)
inputData = (Data
.map(lambda line: line.split(";"))
.filter(lambda line: len(line) >1 )
.map(extract)) # Map to tuples
# error comes a this line
print inputData.collect()
我已安装numpy（sudo apt-get install python-numpy），可以使用numpy version
numpy.version.version
为什么会出现此错误以及如何解决？
注1：我当前的bash_profile：
# Set the Spark Home as an environment variable.
export SPARK_HOME="$HOME/spark-1.5.0-bin-hadoop2.6"
# Define your Spark arguments for when running Spark.
export PYSPARK_SUBMIT_ARGS="--master local[2]"
# IPython alias for the use with SPARK.
alias IPYSPARK='PYSPARK_DRIVER_PYTHON=ipython PYSPARK_DRIVER_PYTHON_OPTS="notebook --profile=pyspark --ip=0.0.0.0" $SPARK_HOME/bin/pyspark'
我还在spark-env.sh.template文件中添加了以下内容：
#!/usr/bin/env bash
# This file is sourced when running various Spark programs.
export PYSPARK_PYTHON=/usr/bin/python2.7
export PYSPARK_DRIVER_PYTHON=/usr/bin/ipython
注意2：我正在虚拟环境中启动Ipython笔记本。
注3： I have Spark 1.5.0和numpy 1.8.2
更新： sc.parallelize([],1).mapPartitions(lambda _: [(sys.executable, sys.path)]).first()
('/home/vagrant/pyEnv/bin/python2.7', ['', u'/tmp/spark-dbbcfd0b-413e-4406-8bd5-37de29d3fcc5/userFiles-6296ba2d-4ec5-4956-9904-828bda0c6424', '/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/pyspark.zip', '/home/vagrant/spark-1.5.0-bin-hadoop2.6/python/lib/py4j-0.8.2.1-src.zip', '/home/vagrant/spark-1.5.0-bin-hadoop2.6/lib/spark-assembly-1.5.0-hadoop2.6.0.jar', '/home/vagrant/spark-1.5.0-bin-hadoop2.6/python', '/home/vagrant', '/home/vagrant/pyEnv/lib/python2.7', '/home/vagrant/pyEnv/lib/python2.7/plat-x86_64-linux-gnu', '/home/vagrant/pyEnv/lib/python2.7/lib-tk', '/home/vagrant/pyEnv/lib/python2.7/lib-old', '/home/vagrant/pyEnv/lib/python2.7/lib-dynload', '/usr/lib/python2.7', '/usr/lib/python2.7/plat-x86_64-linux-gnu', '/usr/lib/python2.7/lib-tk', '/home/vagrant/pyEnv/local/lib/python2.7/site-packages', '/home/vagrant/pyEnv/lib/python2.7/site-packages'])