zhengruifeng commented on code in PR #38979:
URL: https://github.com/apache/spark/pull/38979#discussion_r1044063886
##########
python/pyspark/sql/connect/plan.py:
##########
@@ -167,21 +169,38 @@ def _repr_html_(self) -> str:
class LocalRelation(LogicalPlan):
- """Creates a LocalRelation plan object based on a Pandas DataFrame."""
+ """Creates a LocalRelation plan object based on a PyArrow Table."""
- def __init__(self, pdf: "pandas.DataFrame") -> None:
+ def __init__(
+ self,
+ table: "pa.Table",
+ schema: Optional[Union[DataType, str, Sequence[str]]] = None,
+ ) -> None:
super().__init__(None)
- self._pdf = pdf
+ assert table is not None and isinstance(table, pa.Table)
+ self._table = table
+
+ if schema is not None:
+ assert isinstance(schema, (DataType, str, list))
+ if isinstance(schema, list):
+ assert all(isinstance(c, str) for c in schema)
+ self._schema = schema
def plan(self, session: "SparkConnectClient") -> proto.Relation:
sink = pa.BufferOutputStream()
- table = pa.Table.from_pandas(self._pdf)
- with pa.ipc.new_stream(sink, table.schema) as writer:
- for b in table.to_batches():
+ with pa.ipc.new_stream(sink, self._table.schema) as writer:
+ for b in self._table.to_batches():
writer.write_batch(b)
plan = proto.Relation()
plan.local_relation.data = sink.getvalue().to_pybytes()
+ if self._schema is not None:
+ if isinstance(self._schema, DataType):
+
plan.local_relation.datatype.CopyFrom(pyspark_types_to_proto_types(self._schema))
Review Comment:
`pyspark_types_to_proto_types` does not support `StructType` now.
I'm going to fix it in a separate PR.
--
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]
