shunping commented on issue #30513: URL: https://github.com/apache/beam/issues/30513#issuecomment-4777183082
[Update] The latest postcommit failure on Python versions other than 3.12 is due to the update of pandas (https://github.com/apache/beam/pull/39056). ``` E apache_beam.runners.dataflow.dataflow_runner.DataflowRuntimeException: Dataflow pipeline failed. State: FAILED, Error: E Traceback (most recent call last): E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/sdk_worker.py", line 310, in _execute E response = task() E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/sdk_worker.py", line 384, in <lambda> E lambda: self.create_worker().do_instruction(request), request) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/sdk_worker.py", line 663, in do_instruction E return getattr(self, request_type)( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/sdk_worker.py", line 695, in process_bundle E bundle_processor = self.bundle_processor_cache.get( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/sdk_worker.py", line 511, in get E processor = bundle_processor.BundleProcessor( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1136, in __init__ E self.ops = future.result(timeout=3600) E File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 458, in result E return self.__get_result() E File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result E raise self._exception E File "/usr/local/lib/python3.10/concurrent/futures/thread.py", line 58, in run E result = self.fn(*self.args, **self.kwargs) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1212, in create_execution_tree E return collections.OrderedDict([( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1215, in <listcomp> E get_operation(transform_id))) for transform_id in sorted( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1189, in get_operation E transform_consumers = *** E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <dictcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <listcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1189, in get_operation E transform_consumers = *** E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <dictcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <listcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1189, in get_operation E transform_consumers = *** E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <dictcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <listcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1189, in get_operation E transform_consumers = *** E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <dictcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <listcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1189, in get_operation E transform_consumers = *** E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <dictcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1190, in <listcomp> E tag: [get_operation(op) for op in pcoll_consumers[pcoll_id]] E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1036, in wrapper E result = cache[args] = func(*args) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1200, in get_operation E return transform_factory.create_operation( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1518, in create_operation E return creator(self, transform_id, transform_proto, payload, consumers) E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1849, in create_par_do E return _create_pardo_operation( E File "/usr/local/lib/python3.10/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1893, in _create_pardo_operation E dofn_data = pickler.loads(serialized_fn) E File "/usr/local/lib/python3.10/site-packages/apache_beam/internal/pickler.py", line 72, in loads E return desired_pickle_lib.loads( E File "/usr/local/lib/python3.10/site-packages/apache_beam/internal/cloudpickle_pickler.py", line 224, in loads E return _loads(s) E File "/usr/local/lib/python3.10/site-packages/apache_beam/internal/cloudpickle_pickler.py", line 229, in _loads E unpickled = cloudpickle.loads(s) E TypeError: StringDtype.__init__() takes from 1 to 2 positional arguments but 3 were given ``` There is change of signature on `StringDtype` in pandas 2.3.x: - https://github.com/pandas-dev/pandas/blob/2.2.x/pandas/core/arrays/string_.py#L118 - https://github.com/pandas-dev/pandas/blob/2.3.x/pandas/core/arrays/string_.py#L146 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
