You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Sandeep Singh (Jira)" <ji...@apache.org> on 2023/01/04 02:39:00 UTC
[jira] [Updated] (SPARK-41868) Support data type Duration(NANOSECOND)
[ https://issues.apache.org/jira/browse/SPARK-41868?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sandeep Singh updated SPARK-41868:
----------------------------------
Description:
{code:java}
import pandas as pd
from datetime import timedelta
df = self.spark.createDataFrame(pd.DataFrame({"a": [timedelta(microseconds=123)]})) {code}
{code:java}
Traceback (most recent call last):
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", line 1291, in test_create_dataframe_from_pandas_with_day_time_interval
self.assertEqual(df.toPandas().a.iloc[0], timedelta(microseconds=123))
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1031, in toPandas
return self._session.client.to_pandas(query)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 413, in to_pandas
return self._execute_and_fetch(req)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 573, in _execute_and_fetch
self._handle_error(rpc_error)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 623, in _handle_error
raise SparkConnectException(status.message, info.reason) from None
pyspark.sql.connect.client.SparkConnectException: (org.apache.spark.SparkUnsupportedOperationException) Unsupported data type: Duration(NANOSECOND){code}
was:
{code:java}
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py", line 1966, in pyspark.sql.connect.functions.hour
Failed example:
df.select(hour('ts').alias('hour')).collect()
Exception raised:
Traceback (most recent call last):
File "/usr/local/Cellar/python@3.10/3.10.8/Frameworks/Python.framework/Versions/3.10/lib/python3.10/doctest.py", line 1350, in __run
exec(compile(example.source, filename, "single",
File "<doctest pyspark.sql.connect.functions.hour[2]>", line 1, in <module>
df.select(hour('ts').alias('hour')).collect()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1017, in collect
pdf = self.toPandas()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1031, in toPandas
return self._session.client.to_pandas(query)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 413, in to_pandas
return self._execute_and_fetch(req)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 573, in _execute_and_fetch
self._handle_error(rpc_error)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 623, in _handle_error
raise SparkConnectException(status.message, info.reason) from None
pyspark.sql.connect.client.SparkConnectException: (org.apache.spark.SparkUnsupportedOperationException) Unsupported data type: Timestamp(NANOSECOND, null){code}
> Support data type Duration(NANOSECOND)
> --------------------------------------
>
> Key: SPARK-41868
> URL: https://issues.apache.org/jira/browse/SPARK-41868
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> import pandas as pd
> from datetime import timedelta
> df = self.spark.createDataFrame(pd.DataFrame({"a": [timedelta(microseconds=123)]})) {code}
> {code:java}
> Traceback (most recent call last):
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py", line 1291, in test_create_dataframe_from_pandas_with_day_time_interval
> self.assertEqual(df.toPandas().a.iloc[0], timedelta(microseconds=123))
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1031, in toPandas
> return self._session.client.to_pandas(query)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 413, in to_pandas
> return self._execute_and_fetch(req)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 573, in _execute_and_fetch
> self._handle_error(rpc_error)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 623, in _handle_error
> raise SparkConnectException(status.message, info.reason) from None
> pyspark.sql.connect.client.SparkConnectException: (org.apache.spark.SparkUnsupportedOperationException) Unsupported data type: Duration(NANOSECOND){code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org