[
https://issues.apache.org/jira/browse/SPARK-54486?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-54486:
---------------------------------
Description:
{code}
======================================================================
ERROR [0.090s]: test_to_feather
(pyspark.pandas.tests.connect.io.test_parity_feather.FeatherParityTests.test_to_feather)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-4.0/python/pyspark/pandas/tests/io/test_feather.py",
line 43, in test_to_feather
self.psdf.to_feather(path2)
File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/frame.py", line
2682, in to_feather
return validate_arguments_and_invoke_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/utils.py", line
591, in validate_arguments_and_invoke_function
return pandas_func(**args)
^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/core/frame.py",
line 2938, in to_feather
to_feather(self, path, **kwargs)
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/io/feather_format.py",
line 66, in to_feather
feather.write_feather(df, handles.handle, **kwargs)
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/feather.py",
line 156, in write_feather
table = Table.from_pandas(df, preserve_index=preserve_index)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "pyarrow/table.pxi", line 4795, in pyarrow.lib.Table.from_pandas
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
line 663, in dataframe_to_arrays
pandas_metadata = construct_metadata(
^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
line 281, in construct_metadata
b'pandas': json.dumps({
^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/__init__.py", line
231, in dumps
return _default_encoder.encode(obj)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
200, in encode
chunks = self.iterencode(o, _one_shot=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
258, in iterencode
return _iterencode(o, 0)
^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
180, in default
raise TypeError(f'Object of type {o.__class__.__name__} '
TypeError: Object of type PlanMetrics is not JSON serializable
----------------------------------------------------------------------
{code}
was:
```
======================================================================
ERROR [0.090s]: test_to_feather
(pyspark.pandas.tests.connect.io.test_parity_feather.FeatherParityTests.test_to_feather)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-4.0/python/pyspark/pandas/tests/io/test_feather.py",
line 43, in test_to_feather
self.psdf.to_feather(path2)
File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/frame.py", line
2682, in to_feather
return validate_arguments_and_invoke_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/utils.py", line
591, in validate_arguments_and_invoke_function
return pandas_func(**args)
^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/core/frame.py",
line 2938, in to_feather
to_feather(self, path, **kwargs)
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/io/feather_format.py",
line 66, in to_feather
feather.write_feather(df, handles.handle, **kwargs)
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/feather.py",
line 156, in write_feather
table = Table.from_pandas(df, preserve_index=preserve_index)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "pyarrow/table.pxi", line 4795, in pyarrow.lib.Table.from_pandas
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
line 663, in dataframe_to_arrays
pandas_metadata = construct_metadata(
^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
line 281, in construct_metadata
b'pandas': json.dumps({
^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/__init__.py", line
231, in dumps
return _default_encoder.encode(obj)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
200, in encode
chunks = self.iterencode(o, _one_shot=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
258, in iterencode
return _iterencode(o, 0)
^^^^^^^^^^^^^^^^^
File
"/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py", line
180, in default
raise TypeError(f'Object of type {o.__class__.__name__} '
TypeError: Object of type PlanMetrics is not JSON serializable
----------------------------------------------------------------------
```
> Reeanble test_to_feather
> ------------------------
>
> Key: SPARK-54486
> URL: https://issues.apache.org/jira/browse/SPARK-54486
> Project: Spark
> Issue Type: Sub-task
> Components: Tests
> Affects Versions: 4.1.0, 4.0.1, 4.2.0
> Reporter: Hyukjin Kwon
> Priority: Major
>
> {code}
> ======================================================================
> ERROR [0.090s]: test_to_feather
> (pyspark.pandas.tests.connect.io.test_parity_feather.FeatherParityTests.test_to_feather)
> ----------------------------------------------------------------------
> Traceback (most recent call last):
> File
> "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/tests/io/test_feather.py",
> line 43, in test_to_feather
> self.psdf.to_feather(path2)
> File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/frame.py",
> line 2682, in to_feather
> return validate_arguments_and_invoke_function(
> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> File "/home/runner/work/spark/spark-4.0/python/pyspark/pandas/utils.py",
> line 591, in validate_arguments_and_invoke_function
> return pandas_func(**args)
> ^^^^^^^^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/core/frame.py",
> line 2938, in to_feather
> to_feather(self, path, **kwargs)
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pandas/io/feather_format.py",
> line 66, in to_feather
> feather.write_feather(df, handles.handle, **kwargs)
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/feather.py",
> line 156, in write_feather
> table = Table.from_pandas(df, preserve_index=preserve_index)
> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> File "pyarrow/table.pxi", line 4795, in pyarrow.lib.Table.from_pandas
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
> line 663, in dataframe_to_arrays
> pandas_metadata = construct_metadata(
> ^^^^^^^^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/site-packages/pyarrow/pandas_compat.py",
> line 281, in construct_metadata
> b'pandas': json.dumps({
> ^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/__init__.py",
> line 231, in dumps
> return _default_encoder.encode(obj)
> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py",
> line 200, in encode
> chunks = self.iterencode(o, _one_shot=True)
> ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py",
> line 258, in iterencode
> return _iterencode(o, 0)
> ^^^^^^^^^^^^^^^^^
> File
> "/opt/hostedtoolcache/Python/3.11.14/x64/lib/python3.11/json/encoder.py",
> line 180, in default
> raise TypeError(f'Object of type {o.__class__.__name__} '
> TypeError: Object of type PlanMetrics is not JSON serializable
> ----------------------------------------------------------------------
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
