TypeError: Type is not JSON serializable: numpy.float64
mt467 opened this issue · comments
Ran the below command for one grib bz2 file for batch processing:
weather-mv --uris "gs://xxxxxx/A4D0113xxxxxxx.bz2" --output_table xxxx-xxx.xxxx.ecmwf_realtime_test_a4 --region us-central1 --runner DataflowRunner --setup_file ./setup.py --project xxxx-xxx --temp_location gs://xxxxxx-test/tmp
The table was not available in the BQ so the pipeline creates it on the go.
Below is the error traceback:
Traceback (most recent call last):
File "/usr/local/lib/python3.7/site-packages/dataflow_worker/batchworker.py", line 651, in do_work
work_executor.execute()
File "/usr/local/lib/python3.7/site-packages/dataflow_worker/executor.py", line 179, in execute
op.start()
File "dataflow_worker/shuffle_operations.py", line 63, in dataflow_worker.shuffle_operations.GroupedShuffleReadOperation.start
File "dataflow_worker/shuffle_operations.py", line 64, in dataflow_worker.shuffle_operations.GroupedShuffleReadOperation.start
File "dataflow_worker/shuffle_operations.py", line 79, in dataflow_worker.shuffle_operations.GroupedShuffleReadOperation.start
File "dataflow_worker/shuffle_operations.py", line 80, in dataflow_worker.shuffle_operations.GroupedShuffleReadOperation.start
File "dataflow_worker/shuffle_operations.py", line 84, in dataflow_worker.shuffle_operations.GroupedShuffleReadOperation.start
File "apache_beam/runners/worker/operations.py", line 353, in apache_beam.runners.worker.operations.Operation.output
File "apache_beam/runners/worker/operations.py", line 215, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive
File "dataflow_worker/shuffle_operations.py", line 261, in dataflow_worker.shuffle_operations.BatchGroupAlsoByWindowsOperation.process
File "dataflow_worker/shuffle_operations.py", line 268, in dataflow_worker.shuffle_operations.BatchGroupAlsoByWindowsOperation.process
File "apache_beam/runners/worker/operations.py", line 353, in apache_beam.runners.worker.operations.Operation.output
File "apache_beam/runners/worker/operations.py", line 215, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive
File "apache_beam/runners/worker/operations.py", line 712, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/worker/operations.py", line 713, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/common.py", line 1234, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 1299, in apache_beam.runners.common.DoFnRunner._reraise_augmented
File "apache_beam/runners/common.py", line 1232, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 571, in apache_beam.runners.common.SimpleInvoker.invoke_process
File "apache_beam/runners/common.py", line 1395, in apache_beam.runners.common._OutputProcessor.process_outputs
File "apache_beam/runners/worker/operations.py", line 215, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive
File "apache_beam/runners/worker/operations.py", line 712, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/worker/operations.py", line 713, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/common.py", line 1234, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 1299, in apache_beam.runners.common.DoFnRunner._reraise_augmented
File "apache_beam/runners/common.py", line 1232, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 571, in apache_beam.runners.common.SimpleInvoker.invoke_process
File "apache_beam/runners/common.py", line 1395, in apache_beam.runners.common._OutputProcessor.process_outputs
File "apache_beam/runners/worker/operations.py", line 215, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive
File "apache_beam/runners/worker/operations.py", line 712, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/worker/operations.py", line 713, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/common.py", line 1234, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 1299, in apache_beam.runners.common.DoFnRunner._reraise_augmented
File "apache_beam/runners/common.py", line 1232, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 571, in apache_beam.runners.common.SimpleInvoker.invoke_process
File "apache_beam/runners/common.py", line 1395, in apache_beam.runners.common._OutputProcessor.process_outputs
File "apache_beam/runners/worker/operations.py", line 215, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive
File "apache_beam/runners/worker/operations.py", line 712, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/worker/operations.py", line 713, in apache_beam.runners.worker.operations.DoOperation.process
File "apache_beam/runners/common.py", line 1234, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 1315, in apache_beam.runners.common.DoFnRunner._reraise_augmented
File "apache_beam/runners/common.py", line 1232, in apache_beam.runners.common.DoFnRunner.process
File "apache_beam/runners/common.py", line 572, in apache_beam.runners.common.SimpleInvoker.invoke_process
File "/usr/local/lib/python3.7/site-packages/apache_beam/io/gcp/bigquery.py", line 1256, in process
return self._flush_batch(destination)
File "/usr/local/lib/python3.7/site-packages/apache_beam/io/gcp/bigquery.py", line 1312, in _flush_batch
skip_invalid_rows=True)
File "/usr/local/lib/python3.7/site-packages/apache_beam/io/gcp/bigquery_tools.py", line 1136, in insert_rows
for r in rows
File "/usr/local/lib/python3.7/site-packages/apache_beam/io/gcp/bigquery_tools.py", line 1136, in
for r in rows
TypeError: Type is not JSON serializable: numpy.float64 [while running 'WriteToBigQuery/_StreamToBigQuery/StreamInsertRows/ParDo(BigQueryWriteFn)']
Picking up this issue right now. The fix should be straightforward.
I was a bit confused in a conversation about this bug. I think it was fixed in 83. Closing this issue for now.
I was able to reproduce this error in a streaming pipeline, reopening.