Vote count:
0
I get this weird error message
Traceback (most recent call last):
File "/home/user/inverted-index.py", line 79, in <module>
sc.wholeTextFiles(data_dir).flatMap(update).groupByKey().map(store)
File "/home/user/spark/python/pyspark/rdd.py", line 1650, in groupByKey
numPartitions).mapValues(lambda x: ResultIterable(x))
File "/home/user/spark/python/pyspark/rdd.py", line 1564, in combineByKey
numPartitions = self._defaultReducePartitions()
File "/home/user/spark/python/pyspark/rdd.py", line 1952, in _defaultReducePartitions
return self.getNumPartitions()
File "/home/user/spark/python/pyspark/rdd.py", line 391, in getNumPartitions
return self._jrdd.partitions().size()
File "/home/user/spark/python/pyspark/rdd.py", line 2013, in _jrdd
pickled_command = ser.dumps(command)
File "/home/user/spark/python/pyspark/serializers.py", line 364, in dumps
return cloudpickle.dumps(obj, 2)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 802, in dumps
cp.dump(obj)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 140, in dump
return pickle.Pickler.dump(self, obj)
File "/usr/lib/python2.7/pickle.py", line 224, in dump
self.save(obj)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/usr/lib/python2.7/pickle.py", line 548, in save_tuple
save(element)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 259, in save_function
self.save_function_tuple(obj, [themodule])
File "/home/user/spark/python/pyspark/cloudpickle.py", line 316, in save_function_tuple
save(closure)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/usr/lib/python2.7/pickle.py", line 600, in save_list
self._batch_appends(iter(obj))
File "/usr/lib/python2.7/pickle.py", line 636, in _batch_appends
save(tmp[0])
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 254, in save_function
self.save_function_tuple(obj, modList)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 314, in save_function_tuple
save(f_globals)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 331, in save
self.save_reduce(obj=obj, *rv)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 632, in save_reduce
save(state)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 331, in save
self.save_reduce(obj=obj, *rv)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 632, in save_reduce
save(state)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 331, in save
self.save_reduce(obj=obj, *rv)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 632, in save_reduce
save(state)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 545, in save_inst
self.save_inst_logic(obj)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 535, in save_inst_logic
save(stuff)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 545, in save_inst
self.save_inst_logic(obj)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 535, in save_inst_logic
save(stuff)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 331, in save
self.save_reduce(obj=obj, *rv)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 598, in save_reduce
save(cls)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 464, in save_global
d),obj=obj)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 613, in save_reduce
save(args)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/usr/lib/python2.7/pickle.py", line 548, in save_tuple
save(element)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 181, in save_dict
pickle.Pickler.save_dict(self, obj)
File "/usr/lib/python2.7/pickle.py", line 649, in save_dict
self._batch_setitems(obj.iteritems())
File "/usr/lib/python2.7/pickle.py", line 681, in _batch_setitems
save(v)
File "/usr/lib/python2.7/pickle.py", line 331, in save
self.save_reduce(obj=obj, *rv)
File "/home/user/spark/python/pyspark/cloudpickle.py", line 598, in save_reduce
save(cls)
File "/usr/lib/python2.7/pickle.py", line 286, in save
f(self, obj) # Call unbound method with explicit self
File "/home/user/spark/python/pyspark/cloudpickle.py", line 439, in save_global
raise pickle.PicklingError("Can't pickle builtin %s" % obj)
pickle.PicklingError: Can't pickle builtin <type 'method_descriptor'>
My update func returns a list of tuples of type (key, (value1, value2)) and all of them are strings
What is going wrong?
asked 44 secs ago
Spark can't pickle method_descriptor
Aucun commentaire:
Enregistrer un commentaire