HyukjinKwon commented on PR #46417:
URL: https://github.com/apache/spark/pull/46417#issuecomment-2100307118
```
======================================================================
ERROR [2.158s]: test_between_time
(pyspark.pandas.tests.connect.series.test_parity_compute.SeriesParityComputeTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/series/test_compute.py",
line 578, in test_between_time
self.assert_eq(
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
536, in assert_eq
robj = self._to_pandas(right)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/testing/pandasutils.py", line
557, in _to_pandas
return obj.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
1834, in main
process()
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1826, in process
serializer.dump_stream(out_iter, outfile)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
line 531, in dump_stream
return ArrowStreamSerializer.dump_stream(self,
init_stream_yield_batches(), stream)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
line 104, in dump_stream
for batch in iterator:
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/sql/pandas/serializers.py",
line 524, in init_stream_yield_batches
for series in iterator:
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1529, in func
for result_batch, result_type in result_iter:
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/groupby.py",
line 2295, in rename_output
pdf = func(pdf)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/accessors.py", line
350, in new_func
return original_func(o, *args, **kwds)
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 3612, in pandas_between_time
return pdf.between_time(start_time, end_time, include_start,
include_end).reset_index()
File
"/usr/share/miniconda/envs/server-env/lib/python3.10/site-packages/pandas/core/generic.py",
line 9371, in between_time
raise TypeError("Index must be DatetimeIndex")
TypeError: Index must be DatetimeIndex
======================================================================
ERROR [0.249s]: test_factorize
(pyspark.pandas.tests.connect.series.test_parity_compute.SeriesParityComputeTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/series/test_compute.py",
line 426, in test_factorize
kcodes, kuniques = psser.factorize()
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/base.py",
line 1766, in factorize
new_scol = null_scol.otherwise(map_scol[self.spark.column])
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/column.py", line
465, in __getitem__
return Column(UnresolvedExtractValue(self._expr,
LiteralExpression._from_value(k)))
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/expressions.py",
line 336, in _from_value
return LiteralExpression(value=value,
dataType=LiteralExpression._infer_type(value))
File
"/home/runner/work/spark/spark-3.5/python/pyspark/sql/connect/expressions.py",
line 329, in _infer_type
raise PySparkTypeError(
pyspark.errors.exceptions.base.PySparkTypeError: [UNSUPPORTED_DATA_TYPE]
Unsupported DataType `Column`.
----------------------------------------------------------------------
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
