You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Yikun Jiang (Jira)" <ji...@apache.org> on 2022/04/28 08:19:00 UTC
[jira] [Updated] (SPARK-39054) GroupByTest failed due to axis Length mismatch
[ https://issues.apache.org/jira/browse/SPARK-39054?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yikun Jiang updated SPARK-39054:
--------------------------------
Description:
{code:java}
An error occurred while calling o27083.getResult.
: org.apache.spark.SparkException: Exception thrown in awaitResult:
at org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:301)
at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:97)
at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:93)
at sun.reflect.GeneratedMethodAccessor91.invoke(Unknown Source)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 808.0 failed 1 times, most recent failure: Lost task 0.0 in stage 808.0 (TID 650) (localhost executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 686, in main
process()
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 678, in process
serializer.dump_stream(out_iter, outfile)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 343, in dump_stream
return ArrowStreamSerializer.dump_stream(self, init_stream_yield_batches(), stream)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 84, in dump_stream
for batch in iterator:
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 336, in init_stream_yield_batches
for series in iterator:
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 487, in mapper
return f(keys, vals)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 207, in <lambda>
return lambda k, v: [(wrapped(k, v), to_arrow_type(return_type))]
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 185, in wrapped
result = f(pd.concat(value_series, axis=1))
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/util.py", line 81, in wrapper
return f(*args, **kwargs)
File "/__w/spark/spark/python/pyspark/pandas/groupby.py", line 1620, in rename_output
pdf.columns = return_schema.names
File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 5588, in __setattr__
return object.__setattr__(self, name, value)
File "pandas/_libs/properties.pyx", line 70, in pandas._libs.properties.AxisProperty.__set__
File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 769, in _set_axis
self._mgr.set_axis(axis, labels)
File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/managers.py", line 214, in set_axis
self._validate_set_axis(axis, new_labels)
File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/base.py", line 69, in _validate_set_axis
raise ValueError(
ValueError: Length mismatch: Expected axis has 3 elements, new values have 2 elements {code}
was:
{code:java}
An error occurred while calling o27083.getResult.
: org.apache.spark.SparkException: Exception thrown in awaitResult:
at org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:301)
at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:97)
at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:93)
at sun.reflect.GeneratedMethodAccessor91.invoke(Unknown Source)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
at java.lang.Thread.run(Thread.java:750)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 808.0 failed 1 times, most recent failure: Lost task 0.0 in stage 808.0 (TID 650) (localhost executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 686, in main
process()
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 678, in process
serializer.dump_stream(out_iter, outfile)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 343, in dump_stream
return ArrowStreamSerializer.dump_stream(self, init_stream_yield_batches(), stream)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 84, in dump_stream
for batch in iterator:
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 336, in init_stream_yield_batches
for series in iterator:
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 487, in mapper
return f(keys, vals)
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 207, in <lambda>
return lambda k, v: [(wrapped(k, v), to_arrow_type(return_type))]
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 185, in wrapped
result = f(pd.concat(value_series, axis=1))
File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/util.py", line 81, in wrapper
return f(*args, **kwargs)
File "/__w/spark/spark/python/pyspark/pandas/groupby.py", line 1620, in rename_output
pdf.columns = return_schema.names
File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 5588, in __setattr__
return object.__setattr__(self, name, value)
File "pandas/_libs/properties.pyx", line 70, in pandas._libs.properties.AxisProperty.__set__
File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 769, in _set_axis
self._mgr.set_axis(axis, labels)
File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/managers.py", line 214, in set_axis
self._validate_set_axis(axis, new_labels)
File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/base.py", line 69, in _validate_set_axis
raise ValueError(
ValueError: Length mismatch: Expected axis has 3 elements, new values have 2 elements {code}
> GroupByTest failed due to axis Length mismatch
> ----------------------------------------------
>
> Key: SPARK-39054
> URL: https://issues.apache.org/jira/browse/SPARK-39054
> Project: Spark
> Issue Type: Sub-task
> Components: PySpark
> Affects Versions: 3.4.0
> Reporter: Yikun Jiang
> Priority: Major
>
> {code:java}
> An error occurred while calling o27083.getResult.
> : org.apache.spark.SparkException: Exception thrown in awaitResult:
> at org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:301)
> at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:97)
> at org.apache.spark.security.SocketAuthServer.getResult(SocketAuthServer.scala:93)
> at sun.reflect.GeneratedMethodAccessor91.invoke(Unknown Source)
> 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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
> at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
> at java.lang.Thread.run(Thread.java:750)
> Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 808.0 failed 1 times, most recent failure: Lost task 0.0 in stage 808.0 (TID 650) (localhost executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 686, in main
> process()
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 678, in process
> serializer.dump_stream(out_iter, outfile)
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 343, in dump_stream
> return ArrowStreamSerializer.dump_stream(self, init_stream_yield_batches(), stream)
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 84, in dump_stream
> for batch in iterator:
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py", line 336, in init_stream_yield_batches
> for series in iterator:
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 487, in mapper
> return f(keys, vals)
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 207, in <lambda>
> return lambda k, v: [(wrapped(k, v), to_arrow_type(return_type))]
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line 185, in wrapped
> result = f(pd.concat(value_series, axis=1))
> File "/__w/spark/spark/python/lib/pyspark.zip/pyspark/util.py", line 81, in wrapper
> return f(*args, **kwargs)
> File "/__w/spark/spark/python/pyspark/pandas/groupby.py", line 1620, in rename_output
> pdf.columns = return_schema.names
> File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 5588, in __setattr__
> return object.__setattr__(self, name, value)
> File "pandas/_libs/properties.pyx", line 70, in pandas._libs.properties.AxisProperty.__set__
> File "/usr/local/lib/python3.9/dist-packages/pandas/core/generic.py", line 769, in _set_axis
> self._mgr.set_axis(axis, labels)
> File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/managers.py", line 214, in set_axis
> self._validate_set_axis(axis, new_labels)
> File "/usr/local/lib/python3.9/dist-packages/pandas/core/internals/base.py", line 69, in _validate_set_axis
> raise ValueError(
> ValueError: Length mismatch: Expected axis has 3 elements, new values have 2 elements {code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org