itholic commented on code in PR #39469:
URL: https://github.com/apache/spark/pull/39469#discussion_r1065282290
##########
python/pyspark/sql/tests/connect/test_connect_basic.py:
##########
@@ -1071,6 +1071,25 @@ def test_to_pandas(self):
self.spark.sql(query).toPandas(),
)
+ def test_create_dataframe_from_pandas_with_ns_timestamp(self):
+ """Truncate the timestamps for nanoseconds."""
+ from datetime import datetime, timezone, timedelta
+ from pandas import Timestamp
+ import pandas as pd
+
+ pdf = pd.DataFrame(
+ {
+ "naive": [datetime(2019, 1, 1, 0)],
+ "aware": [
+ Timestamp(
+ year=2019, month=1, day=1, nanosecond=1,
tz=timezone(timedelta(hours=-8))
+ )
+ ],
+ }
+ )
+ rows = self.connect.createDataFrame(pdf).collect()
+ self.assertEqual(1, len(rows))
Review Comment:
Only comparing the number of rows is enough and don't we need to verify the
data ??
##########
python/pyspark/sql/connect/session.py:
##########
@@ -215,7 +215,31 @@ def createDataFrame(
_inferred_schema: Optional[StructType] = None
if isinstance(data, pd.DataFrame):
- _table = pa.Table.from_pandas(data)
+ from pandas.api.types import ( # type: ignore[attr-defined]
+ is_datetime64_dtype,
+ is_datetime64tz_dtype,
+ )
+
+ # We need double conversions for the truncation, first truncate to
microseconds.
+ for col in data:
+ print("Checking", col)
Review Comment:
Maybe should we remove the printout ?
--
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]
