File "/home/hadoop/anaconda2/lib/python2.7/site-packages/scipy/ndimage/filters.py", line 36, in <module> from . import _ni_support ImportError: cannot import name _ni_support #82
in ()
3 loss=loss, features_col="features_normalized",
4 label_col="label", num_epoch=1, batch_size=32)
----> 5 trained_model = trainer.train(training_set)
/home/hadoop/anaconda2/lib/python2.7/site-packages/distkeras/trainers.pyc in train(self, dataframe, shuffle)
/usr/local/spark/python/pyspark/rdd.pyc in collect(self)
822 """
823 with SCCallSiteSync(self.context) as css:
--> 824 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
825 return list(_load_from_socket(port, self._jrdd_deserializer))
826
/usr/local/spark/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py in __call__(self, *args)
1158 answer = self.gateway_client.send_command(command)
1159 return_value = get_return_value(
-> 1160 answer, self.gateway_client, self.target_id, self.name)
1161
1162 for temp_arg in temp_args:
/usr/local/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()
/usr/local/spark/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
318 raise Py4JJavaError(
319 "An error occurred while calling {0}{1}{2}.\n".
--> 320 format(target_id, ".", name), value)
321 else:
322 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 33.0 failed 1 times, most recent failure: Lost task 0.0 in stage 33.0 (TID 77, localhost, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 216, in main
func, profiler, deserializer, serializer = read_command(pickleSer, infile)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 60, in read_command
command = serializer.loads(command.value)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 562, in loads
return pickle.loads(obj)
File "/tmp/spark-aca404a0-a60e-43d2-a913-acc7ed93a7a0/userFiles-59dd8a1c-344e-4b9d-8fb0-e7982aae3d8c/distkeras/utils.py", line 5, in
from keras import backend as K
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/__init__.py", line 7, in
from . import datasets
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/datasets/__init__.py", line 4, in
from . import imdb
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/datasets/imdb.py", line 8, in
from ..preprocessing.sequence import _remove_long_seq
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/preprocessing/__init__.py", line 12, in
from . import image
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/preprocessing/image.py", line 7, in
from keras_preprocessing import image
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras_preprocessing/image.py", line 10, in
import scipy.ndimage as ndi
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/scipy/ndimage/__init__.py", line 161, in
from .filters import *
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/scipy/ndimage/filters.py", line 36, in
from . import _ni_support
ImportError: cannot import name _ni_support
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:298)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:438)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:421)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:252)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:939)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:939)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1587)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1586)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1586)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1820)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1769)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1758)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2027)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2048)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2067)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2092)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:939)
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:363)
at org.apache.spark.rdd.RDD.collect(RDD.scala:938)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:153)
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:282)
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:748)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 216, in main
func, profiler, deserializer, serializer = read_command(pickleSer, infile)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/worker.py", line 60, in read_command
command = serializer.loads(command.value)
File "/usr/local/spark/python/lib/pyspark.zip/pyspark/serializers.py", line 562, in loads
return pickle.loads(obj)
File "/tmp/spark-aca404a0-a60e-43d2-a913-acc7ed93a7a0/userFiles-59dd8a1c-344e-4b9d-8fb0-e7982aae3d8c/distkeras/utils.py", line 5, in
from keras import backend as K
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/__init__.py", line 7, in
from . import datasets
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/datasets/__init__.py", line 4, in
from . import imdb
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/datasets/imdb.py", line 8, in
from ..preprocessing.sequence import _remove_long_seq
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/preprocessing/__init__.py", line 12, in
from . import image
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras/preprocessing/image.py", line 7, in
from keras_preprocessing import image
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/keras_preprocessing/image.py", line 10, in
import scipy.ndimage as ndi
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/scipy/ndimage/__init__.py", line 161, in
from .filters import *
File "/home/hadoop/anaconda2/lib/python2.7/site-packages/scipy/ndimage/filters.py", line 36, in
from . import _ni_support
ImportError: cannot import name _ni_support
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:298)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:438)
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:421)
at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:252)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at org.apache.spark.InterruptibleIterator.foreach(InterruptibleIterator.scala:28)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
at org.apache.spark.InterruptibleIterator.to(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
at org.apache.spark.InterruptibleIterator.toBuffer(InterruptibleIterator.scala:28)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
at org.apache.spark.InterruptibleIterator.toArray(InterruptibleIterator.scala:28)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:939)
at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:939)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2067)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
when run this code trainer = SingleTrainer(keras_model=model, worker_optimizer=optimizer, loss=loss, features_col="features_normalized", label_col="label", num_epoch=1, batch_size=32) trained_model = trainer.train(training_set)
error display Py4JJavaError Traceback (most recent call last)