HyukjinKwon commented on PR #46417:
URL: https://github.com/apache/spark/pull/46417#issuecomment-2100355577
```
======================================================================
ERROR [2.060s]: test_frame_apply_batch_without_shortcut
(pyspark.pandas.tests.connect.test_parity_categorical.CategoricalParityTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_categorical.py",
line 476, in test_frame_apply_batch_without_shortcut
self.test_frame_apply_batch()
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_categorical.py",
line 457, in test_frame_apply_batch
self.assert_eq(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
525, in assert_eq
return assertPandasOnSparkEqual(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
457, in assertPandasOnSparkEqual
actual = actual.to_pandas()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 5428, in to_pandas
return self._to_pandas()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 5434, in _to_pandas
return self._internal.to_pandas_frame.copy()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/utils.py",
line 600, in wrapped_lazy_property
setattr(self, attr_name, fn(self))
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/internal.py", line
1115, in to_pandas_frame
pdf = sdf.toPandas()
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/dataframe.py",
line 1663, in toPandas
return self._session.client.to_pandas(query)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 873, in to_pandas
table, schema, metrics, observed_metrics, _ = self._execute_and_fetch(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1283, in _execute_and_fetch
for response in self._execute_and_fetch_as_iterator(req):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1264, in _execute_and_fetch_as_iterator
self._handle_error(error)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1503, in _handle_error
self._handle_rpc_error(error)
return cloudpickle.loads(obj, encoding=encoding)
ModuleNotFoundError: No module named 'pandas.core.indexes.numeric'
======================================================================
ERROR [1.477s]: test_series_transform_batch_without_shortcut
(pyspark.pandas.tests.connect.test_parity_categorical.CategoricalParityTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_categorical.py",
line
[602](https://github.com/HyukjinKwon/spark/actions/runs/8997403746/job/24725108255#step:9:603),
in test_series_transform_batch_without_shortcut
self.test_series_transform_batch()
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_categorical.py",
line 583, in test_series_transform_batch
self.assert_eq(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
525, in assert_eq
return assertPandasOnSparkEqual(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
457, in assertPandasOnSparkEqual
actual = actual.to_pandas()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/series.py",
line 1718, in to_pandas
return self._to_pandas()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/series.py",
line 1724, in _to_pandas
return self._to_internal_pandas().copy()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/series.py",
line 7333, in _to_internal_pandas
return self._psdf._internal.to_pandas_frame[self.name]
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/utils.py",
line 600, in wrapped_lazy_property
setattr(self, attr_name, fn(self))
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/internal.py", line
1115, in to_pandas_frame
pdf = sdf.toPandas()
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/dataframe.py",
line 1663, in toPandas
return self._session.client.to_pandas(query)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 873, in to_pandas
table, schema, metrics, observed_metrics, _ = self._execute_and_fetch(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1283, in _execute_and_fetch
for response in self._execute_and_fetch_as_iterator(req):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1264, in _execute_and_fetch_as_iterator
self._handle_error(error)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1503, in _handle_error
self._handle_rpc_error(error)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/client/core.py",
line 1539, in _handle_rpc_error
raise convert_exception(info, status.message) from None
pyspark.errors.exceptions.connect.PythonException:
An exception was thrown from the Python worker. Please see the stack trace
below.
Traceback (most recent call last):
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1818, in main
func, profiler, deserializer, serializer = read_udfs(pickleSer, infile,
eval_type)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1728, in read_udfs
read_single_udf(
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
783, in read_single_udf
f, return_type = read_command(pickleSer, infile)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker_util.py",
line 64, in read_command
command = serializer._read_with_length(file)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/serializers.py",
line 173, in _read_with_length
return self.loads(obj)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/serializers.py",
line 473, in loads
return cloudpickle.loads(obj, encoding=encoding)
ModuleNotFoundError: No module named 'pandas.core.indexes.numeric'
----------------------------------------------------------------------
```
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
