[yt-users] pickling clumps
Charles Hansen
chansen at astro.berkeley.edu
Fri May 28 11:46:46 PDT 2010
sorry, the preceding line was
outfile = open("dummy.pkl", "wb")
The type is...
In [73]: type(outfile)
Out[73]: <type 'file'>
Matthew Turk wrote:
> Hi Charles,
>
> What's "outfile" in this case? Can you send a bit more of your setup
> of the problem, or at least the output of "type(outfile)"?
>
> -Matt
>
> On Fri, May 28, 2010 at 11:32 AM, Charles Hansen
> <chansen at astro.berkeley.edu> wrote:
>
>> pf.h.save_object does work as advertised for me. Thanks for the pointer.
>> For what it is worth, clumps do not have the attribute save_object, so
>> masterclump.save_object is not a valid function.
>>
>> I tried pickling again and I can no longer even dump the clumps. I don't
>> know why the dumping 'worked' before and not now, though I have been trying
>> it on more complicated clumps than before. I pasted the error message if
>> you are interested.
>>
>> In [6]: pickle.dump(masterclump, outfile)
>> ---------------------------------------------------------------------------
>> AssertionError Traceback (most recent call last)
>>
>> /nics/c/home/chansen/lib/yt/src/yt-trunk-svn/scripts/iyt in <module>()
>> ----> 1
>> 2
>> 3
>> 4
>> 5
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in dump(obj, file,
>> protocol)
>> 1360
>> 1361 def dump(obj, file, protocol=None):
>> -> 1362 Pickler(file, protocol).dump(obj)
>> 1363
>> 1364 def dumps(obj, protocol=None):
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in dump(self, obj)
>> 222 if self.proto >= 2:
>> 223 self.write(PROTO + chr(self.proto))
>> --> 224 self.save(obj)
>> 225 self.write(STOP)
>> 226
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 329
>> 330 # Save the reduce() output and finally memoize the object
>>
>> --> 331 self.save_reduce(obj=obj, *rv)
>> 332
>> 333 def persistent_id(self, obj):
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_reduce(self,
>> func, args, state, listitems, dictitems, obj)
>> 399 else:
>> 400 save(func)
>> --> 401 save(args)
>> 402 write(REDUCE)
>> 403
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_tuple(self,
>> obj)
>> 560 write(MARK)
>> 561 for element in obj:
>> --> 562 save(element)
>> 563
>> 564 if id(obj) in memo:
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_list(self, obj)
>> 598
>> 599 self.memoize(obj)
>> --> 600 self._batch_appends(iter(obj))
>> 601
>> 602 dispatch[ListType] = save_list
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in _batch_appends(self,
>> items)
>> 613 if not self.bin:
>> 614 for x in items:
>> --> 615 save(x)
>> 616 write(APPEND)
>> 617 return
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 329
>> 330 # Save the reduce() output and finally memoize the object
>>
>> --> 331 self.save_reduce(obj=obj, *rv)
>> 332
>> 333 def persistent_id(self, obj):
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_reduce(self,
>> func, args, state, listitems, dictitems, obj)
>> 399 else:
>> 400 save(func)
>> --> 401 save(args)
>> 402 write(REDUCE)
>> 403
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_tuple(self,
>> obj)
>> 560 write(MARK)
>> 561 for element in obj:
>> --> 562 save(element)
>> 563
>> 564 if id(obj) in memo:
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_list(self, obj)
>> 598
>> 599 self.memoize(obj)
>> --> 600 self._batch_appends(iter(obj))
>> 601
>> 602 dispatch[ListType] = save_list
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in _batch_appends(self,
>> items)
>> 613 if not self.bin:
>> 614 for x in items:
>> --> 615 save(x)
>> 616 write(APPEND)
>> 617 return
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 329
>> 330 # Save the reduce() output and finally memoize the object
>>
>> --> 331 self.save_reduce(obj=obj, *rv)
>> 332
>> 333 def persistent_id(self, obj):
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_reduce(self,
>> func, args, state, listitems, dictitems, obj)
>> 399 else:
>> 400 save(func)
>> --> 401 save(args)
>> 402 write(REDUCE)
>> 403
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_tuple(self,
>> obj)
>> 560 write(MARK)
>> 561 for element in obj:
>> --> 562 save(element)
>> 563
>> 564 if id(obj) in memo:
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 284 f = self.dispatch.get(t)
>> 285 if f:
>> --> 286 f(self, obj) # Call unbound method with explicit self
>> 287 return
>> 288
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_list(self, obj)
>> 598
>> 599 self.memoize(obj)
>> --> 600 self._batch_appends(iter(obj))
>> 601
>> 602 dispatch[ListType] = save_list
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in _batch_appends(self,
>> items)
>> 613 if not self.bin:
>> 614 for x in items:
>> --> 615 save(x)
>> 616 write(APPEND)
>> 617 return
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save(self, obj)
>> 329
>> 330 # Save the reduce() output and finally memoize the object
>>
>> --> 331 self.save_reduce(obj=obj, *rv)
>> 332
>> 333 def persistent_id(self, obj):
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in save_reduce(self,
>> func, args, state, listitems, dictitems, obj)
>> 403
>> 404 if obj is not None:
>> --> 405 self.memoize(obj)
>> 406
>> 407 # More new special cases (that work with older protocols as
>>
>>
>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in memoize(self, obj)
>> 242 if self.fast:
>> 243 return
>> --> 244 assert id(obj) not in self.memo
>> 245 memo_len = len(self.memo)
>> 246 self.write(self.put(memo_len))
>>
>> AssertionError:
>>
>>
>>
>> Matthew Turk wrote:
>>
>>> Hi Britton, Charles,
>>>
>>> Britton is correct, YT has its own routine for pickling. This is a
>>> couple step process, because specifically the pickling of parameter
>>> files is somewhat ill-defined as a problem. When you initialize a
>>> parameter file, it's given a (likely) unique hash that corresponds to
>>> its location, some of its contents, last modified time (or in Enzo's
>>> case, the CurrentTimeIdentifier in the parameter file) and this is
>>> stored in ~/.yt/parameter_files.csv. By this mechanism, one can store
>>> the pointer to a parameter file that exists on disk with a
>>> bidirectional hash. When a new parameter file is opened, it checks to
>>> see if the path location in the .csv file needs to be updated, and if
>>> so, it does.
>>>
>>> So when pickling a YT object, it stores the minimum set of information
>>> necessary to recreate that object. For a sphere, region, etc etc,
>>> this is really just the necessary arguments to recreate the empty
>>> object, along with the hash of the parameter file that it belongs to.
>>> So the actual information necessary to pickle simple objects is very
>>> small: hash, arguments. (Called "_con_args" in the source, for
>>> Constructor Arguments.) When this is unpickled, the parameter file is
>>> recreated (or grabbed from in memory, if it has already been
>>> instantiated) and then the object is recreated.
>>>
>>> For more complicated objects, like Clumps and ExtractedSets, we have
>>> to store more information -- because the constructor arguments are
>>> much larger and more complicated. But the basic idea is the same.
>>>
>>> When using save_object, the same pickling routine gets called, but
>>> instead of being loosely affiliated and put into a separate file, it
>>> gets stored as a dataset in a the corresponding .yt file, which is
>>> itself an HDF5 file. So the results should be the same, except
>>> save_object and load_object remove the extra file from the equation.
>>>
>>> The error you're seeing above seems to be related to an incompletely
>>> saved or corrupted file; can you replicate this in a very simple,
>>> quick fashion? I would suggest getting a clump that is very, very
>>> small, taken from a small data region, and seeing if that will pickle
>>> and unpickle correctly. If it does, then we know that perhaps the
>>> previous pickle file was corrupted, or that something is wrong with
>>> the yt pickling protocol. If it doesn't work, then we *know*
>>> something is wrong with the yt pickling protocol.
>>>
>>> Best,
>>>
>>> Matt
>>>
>>> On Thu, May 27, 2010 at 6:43 PM, Britton Smith <brittonsmith at gmail.com>
>>> wrote:
>>>
>>>
>>>> Hi Chris,
>>>>
>>>> YT has its own routine designed to pickle data objects for saving and
>>>> reloading. For a given pf, you can do pf.h.save_object(object, name) and
>>>> the object will be saved to the .yt file associated with the dataset.
>>>> You
>>>> can then get it back with object = pf.h.load_object(name). I have used
>>>> this
>>>> successfully to save the mast_clump structure from clump finding.
>>>>
>>>> Britton
>>>>
>>>> On Thu, May 27, 2010 at 9:26 PM, Charles Hansen
>>>> <chansen at astro.berkeley.edu>
>>>> wrote:
>>>>
>>>>
>>>>> The find_clumps function is working correctly for me I believe, but the
>>>>> analysis takes a very long time and I'd like to save the master_clump
>>>>> object
>>>>> (from
>>>>> http://yt.enzotools.org/doc/cookbook/recipes.html#cookbook-find-clumps)
>>>>> for
>>>>> further analysis. I've tried pickling master_clump. It dumps
>>>>> correctly,
>>>>> but gives an EOF error (below) on loading. Is there another way to save
>>>>> master_clump?
>>>>>
>>>>> Thanks,
>>>>> Charles
>>>>>
>>>>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in load(file)
>>>>> 1368
>>>>> 1369 def load(file):
>>>>> -> 1370 return Unpickler(file).load()
>>>>> 1371
>>>>> 1372 def loads(str):
>>>>>
>>>>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in load(self)
>>>>> 856 while 1:
>>>>> 857 key = read(1)
>>>>> --> 858 dispatch[key](self)
>>>>> 859 except _Stop, stopinst:
>>>>> 860 return stopinst.value
>>>>>
>>>>> /nics/c/home/chansen/lib/yt/lib/python2.6/pickle.pyc in load_eof(self)
>>>>> 878
>>>>> 879 def load_eof(self):
>>>>> --> 880 raise EOFError
>>>>> 881 dispatch[''] = load_eof
>>>>> 882
>>>>>
>>>>> EOFError:
>>>>>
>>>>> _______________________________________________
>>>>> yt-users mailing list
>>>>> yt-users at lists.spacepope.org
>>>>> http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org
>>>>>
>>>>>
>>>> _______________________________________________
>>>> yt-users mailing list
>>>> yt-users at lists.spacepope.org
>>>> http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org
>>>>
>>>>
>>>>
>>>>
>>> _______________________________________________
>>> yt-users mailing list
>>> yt-users at lists.spacepope.org
>>> http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org
>>>
>>>
>> _______________________________________________
>> yt-users mailing list
>> yt-users at lists.spacepope.org
>> http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org
>>
>>
> _______________________________________________
> yt-users mailing list
> yt-users at lists.spacepope.org
> http://lists.spacepope.org/listinfo.cgi/yt-users-spacepope.org
>
More information about the yt-users
mailing list