HyukjinKwon commented on PR #46417:
URL: https://github.com/apache/spark/pull/46417#issuecomment-2101691495
```
======================================================================
ERROR [0.522s]: test_string_rsplit
(pyspark.pandas.tests.connect.test_parity_series_string.SeriesStringParityTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 319, in test_string_rsplit
self.check_func_on_series(lambda x: repr(x.str.rsplit()), self.pser[:-1])
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 51, in check_func_on_series
self.assert_eq(func(ps.from_pandas(pser)), func(pser), almost=almost)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 319, in <lambda>
self.check_func_on_series(lambda x: repr(x.str.rsplit()), self.pser[:-1])
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/series.py",
line 7342, in __repr__
pser =
self._psdf._get_or_create_repr_pandas_cache(max_display_count)[self.name]
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 13393, in _get_or_create_repr_pandas_cache
self, "_repr_pandas_cache", {n: self.head(n + 1)._to_internal_pandas()}
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 13388, in _to_internal_pandas
return self._internal.to_pandas_frame
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
1734, in mapper
result = tuple(f(*[a[o] for o in arg_offsets]) for arg_offsets, f in
udfs)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1734, in <genexpr>
result = tuple(f(*[a[o] for o in arg_offsets]) for arg_offsets, f in
udfs)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
146, in <lambda>
verify_result_length(verify_result_type(func(*a)), len(a[0])),
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/util.py", line
134, in wrapper
return f(*args, **kwargs)
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/strings.py",
line 2177, in pudf
return s.str.rsplit(pat, n)
File
"/usr/share/miniconda/envs/server-env/lib/python3.10/site-packages/pandas/core/strings/accessor.py",
line 137, in wrapper
return func(self, *args, **kwargs)
TypeError: StringMethods.rsplit() takes from 1 to 2 positional arguments but
3 were given
```
```
======================================================================
ERROR [0.455s]: test_string_split
(pyspark.pandas.tests.connect.test_parity_series_string.SeriesStringParityTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 305, in test_string_split
self.check_func_on_series(lambda x: repr(x.str.split()), self.pser[:-1])
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 51, in check_func_on_series
self.assert_eq(func(ps.from_pandas(pser)), func(pser), almost=almost)
File
"/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/test_series_string.py",
line 305, in <lambda>
self.check_func_on_series(lambda x: repr(x.str.split()), self.pser[:-1])
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/series.py",
line 7342, in __repr__
pser =
self._psdf._get_or_create_repr_pandas_cache(max_display_count)[self.name]
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 13393, in _get_or_create_repr_pandas_cache
self, "_repr_pandas_cache", {n: self.head(n + 1)._to_internal_pandas()}
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/frame.py",
line 13388, in _to_internal_pandas
return self._internal.to_pandas_frame
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
1[826](https://github.com/HyukjinKwon/spark/actions/runs/8997403746/job/24754849272#step:9:827),
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
1734, in mapper
result = tuple(f(*[a[o] for o in arg_offsets]) for arg_offsets, f in
udfs)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
1734, in <genexpr>
result = tuple(f(*[a[o] for o in arg_offsets]) for arg_offsets, f in
udfs)
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/worker.py", line
146, in <lambda>
verify_result_length(verify_result_type(func(*a)), len(a[0])),
File
"/home/runner/work/spark/spark/python/lib/pyspark.zip/pyspark/util.py", line
134, in wrapper
return f(*args, **kwargs)
File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/strings.py",
line 2030, in pudf
return s.str.split(pat, n)
File
"/usr/share/miniconda/envs/server-env/lib/python3.10/site-packages/pandas/core/strings/accessor.py",
line 137, in wrapper
return func(self, *args, **kwargs)
TypeError: StringMethods.split() takes from 1 to 2 positional arguments but
3 were given
----------------------------------------------------------------------
```
--
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
