zhengruifeng commented on code in PR #39469:
URL: https://github.com/apache/spark/pull/39469#discussion_r1065705581
##########
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)
+ if is_datetime64tz_dtype(data[col].dtype):
+ data[col] = data[col].astype("datetime64[us, UTC]")
+ elif is_datetime64_dtype(data[col].dtype):
+ data[col] = data[col].astype("datetime64[us]")
+
+ # Create a new schema and change the types to the truncated
microseconds.
+ pd_schema = pa.Schema.from_pandas(data)
+ new_schema = pa.schema([])
+ for x in range(len(pd_schema.types)):
+ f = pd_schema.field(x)
+ if isinstance(f.type, pa.TimestampType) and f.type.unit ==
"ns":
Review Comment:
what if the `TimestampType` is in a nested types? For example, `Struct[Long,
TimestampType]` ?
maybe add a TODO here
--
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]
