API tools faq
paste
Advertisement
Guest User

Stacktrace

a guest
Apr 26th, 2016
13
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 9.04 KB | None | 0 0
raw download clone embed print report
  1. ---------------------------------------------------------------------------
  2. Py4JJavaError Traceback (most recent call last)
  3. <ipython-input-30-46176c96d218> in <module>()
  4. ----> 1 series[2].toarray()
  5.  
  6. /Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/thunder/base.pyc in toarray(self)
  7. 262 This will be slow for large datasets, and may exhaust the available memory on the driver.
  8. 263 """
  9. --> 264 return asarray(self.values).squeeze()
  10. 265
  11. 266 def tospark(self):
  12.  
  13. /Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/numpy/core/numeric.pyc in asarray(a, dtype, order)
  14. 480
  15. 481 """
  16. --> 482 return array(a, dtype, copy=False, order=order)
  17. 483
  18. 484 def asanyarray(a, dtype=None, order=None):
  19.  
  20. /Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.pyc in __array__(self)
  21. 33
  22. 34 def __array__(self):
  23. ---> 35 return self.toarray()
  24. 36
  25. 37 def cache(self):
  26.  
  27. /Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.pyc in toarray(self)
  28. 984 """
  29. 985 rdd = self._rdd if self._ordered else self._rdd.sortByKey()
  30. --> 986 x = rdd.values().collect()
  31. 987 return asarray(x).reshape(self.shape)
  32. 988
  33.  
  34. /Applications/spark-1.6.1-bin-hadoop2.6/python/pyspark/rdd.pyc in collect(self)
  35. 769 """
  36. 770 with SCCallSiteSync(self.context) as css:
  37. --> 771 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
  38. 772 return list(_load_from_socket(port, self._jrdd_deserializer))
  39. 773
  40.  
  41. /Applications/spark-1.6.1-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
  42. 811 answer = self.gateway_client.send_command(command)
  43. 812 return_value = get_return_value(
  44. --> 813 answer, self.gateway_client, self.target_id, self.name)
  45. 814
  46. 815 for temp_arg in temp_args:
  47.  
  48. /Applications/spark-1.6.1-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
  49. 306 raise Py4JJavaError(
  50. 307 "An error occurred while calling {0}{1}{2}.\n".
  51. --> 308 format(target_id, ".", name), value)
  52. 309 else:
  53. 310 raise Py4JError(
  54.  
  55. Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
  56. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 33.0 failed 1 times, most recent failure: Lost task 0.0 in stage 33.0 (TID 92, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  57. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
  58. process()
  59. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
  60. serializer.dump_stream(func(split_index, iterator), outfile)
  61. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
  62. vs = list(itertools.islice(iterator, batch))
  63. File "/Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.py", line 482, in <lambda>
  64. filtered = self._rdd.filter(lambda kv: key_check(kv[0]))
  65. File "/Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.py", line 476, in key_check
  66. out = [check(k, s) for k, s in zip(key, key_slices)]
  67. TypeError: zip argument #1 must support iteration
  68.  
  69. at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
  70. at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
  71. at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
  72. at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
  73. at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
  74. at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
  75. at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
  76. at org.apache.spark.scheduler.Task.run(Task.scala:89)
  77. at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
  78. at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
  79. at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
  80. at java.lang.Thread.run(Thread.java:745)
  81.  
  82. Driver stacktrace:
  83. at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
  84. at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
  85. at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
  86. at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
  87. at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
  88. at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
  89. at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
  90. at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
  91. at scala.Option.foreach(Option.scala:236)
  92. at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
  93. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
  94. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
  95. at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
  96. at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
  97. at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
  98. at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
  99. at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
  100. at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
  101. at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
  102. at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
  103. at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
  104. at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
  105. at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
  106. at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
  107. at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
  108. at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
  109. at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
  110. at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
  111. at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
  112. at java.lang.reflect.Method.invoke(Method.java:497)
  113. at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
  114. at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
  115. at py4j.Gateway.invoke(Gateway.java:259)
  116. at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
  117. at py4j.commands.CallCommand.execute(CallCommand.java:79)
  118. at py4j.GatewayConnection.run(GatewayConnection.java:209)
  119. at java.lang.Thread.run(Thread.java:745)
  120. Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  121. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
  122. process()
  123. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
  124. serializer.dump_stream(func(split_index, iterator), outfile)
  125. File "/Applications/spark-1.6.1-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
  126. vs = list(itertools.islice(iterator, batch))
  127. File "/Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.py", line 482, in <lambda>
  128. filtered = self._rdd.filter(lambda kv: key_check(kv[0]))
  129. File "/Users/Henry/miniconda/envs/thunder1_env/lib/python2.7/site-packages/bolt/spark/array.py", line 476, in key_check
  130. out = [check(k, s) for k, s in zip(key, key_slices)]
  131. TypeError: zip argument #1 must support iteration
  132.  
  133. at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
  134. at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
  135. at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
  136. at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
  137. at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
  138. at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
  139. at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
  140. at org.apache.spark.scheduler.Task.run(Task.scala:89)
  141. at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
  142. at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
  143. at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
  144. ... 1 more
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!