HyukjinKwon commented on PR #46417: URL: https://github.com/apache/spark/pull/46417#issuecomment-2101624723
``` 2024-05-08T12:03:25.2315797Z ====================================================================== 2024-05-08T12:03:25.2318738Z self.assert_eq( 2024-05-08T12:03:25.2319875Z return assertPandasOnSparkEqual( 2024-05-08T12:03:25.2321140Z actual = actual.to_pandas() 2024-05-08T12:03:25.2322246Z return self._to_pandas() 2024-05-08T12:03:25.2323357Z return self._to_internal_pandas().copy() 2024-05-08T12:03:25.2324573Z return self._psdf._internal.to_pandas_frame.index 2024-05-08T12:03:25.2325972Z setattr(self, attr_name, fn(self)) 2024-05-08T12:03:25.2326986Z pdf = sdf.toPandas() 2024-05-08T12:03:25.2328107Z return self._session.client.to_pandas(query) 2024-05-08T12:03:25.2329443Z table, schema, metrics, observed_metrics, _ = self._execute_and_fetch( 2024-05-08T12:03:25.2333343Z self._handle_rpc_error(error) 2024-05-08T12:03:25.2335758Z Traceback (most recent call last): 2024-05-08T12:03:25.2336884Z process() 2024-05-08T12:03:25.2340430Z for batch in iterator: 2024-05-08T12:03:25.2341708Z for series in iterator: 2024-05-08T12:03:25.2342700Z for result_batch, result_type in result_iter: ``` Running secret scanning on commit d31c8407a1a6a4188411ee9456ec0ca9544830e0 No Databricks code found. Allowing Push: https://github.com/HyukjinKwon/spark.git Enumerating objects: 29, done. Counting objects: 100% (29/29), done. Delta compression using up to 16 threads Compressing objects: 100% (15/15), done. Writing objects: 100% (15/15), 1.18 KiB | 1.18 MiB/s, done. Total 15 (delta 14), reused 0 (delta 0), pack-reused 0 remote: Resolving deltas: 100% (14/14), completed with 14 local objects. To https://github.com/HyukjinKwon/spark.git + 26cfd358a1e5...d31c8407a1a6 branch-3.5 -> branch-3.5 (forced update) (python3.11) ➜ spark-35 git:(branch-3.5) vi aaa (python3.11) ➜ spark-35 git:(branch-3.5) ✗ cat aaa ``` ====================================================================== ERROR [1.121s]: test_indexer_between_time (pyspark.pandas.tests.connect.indexes.test_parity_datetime.DatetimeIndexParityTests) ---------------------------------------------------------------------- Traceback (most recent call last): File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/tests/indexes/test_datetime.py", line 155, in test_indexer_between_time 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/indexes/base.py", line 524, in to_pandas return self._to_pandas() File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/indexes/base.py", line 530, in _to_pandas return self._to_internal_pandas().copy() File "/home/runner/work/spark/spark-3.5/python/pyspark/pandas/indexes/base.py", line 503, in _to_internal_pandas return self._psdf._internal.to_pandas_frame.index 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/indexes/datetimes.py", line 750, in pandas_between_time return pdf.between_time(start_time, end_time, include_start, include_end) 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 ---------------------------------------------------------------------- ``` -- 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
