sadhen commented on a change in pull request #32026:
URL: https://github.com/apache/spark/pull/32026#discussion_r606036073
##########
File path: python/pyspark/sql/tests/test_arrow.py
##########
@@ -196,6 +197,33 @@ def test_pandas_round_trip(self):
pdf_arrow = df.toPandas()
assert_frame_equal(pdf_arrow, pdf)
+ def test_udt_roundtrip(self):
+ pdf = pd.DataFrame({'point': pd.Series([ExamplePoint(1.0, 1.0),
ExamplePoint(2.0, 2.0)])})
+ schema = StructType([StructField('point', ExamplePointUDT(), False)])
+ with
self.sql_conf({"spark.sql.execution.arrow.pyspark.fallback.enabled": True}):
+ df = self.spark.createDataFrame(pdf, schema)
+ pdf_arrow = df.toPandas()
+ assert_frame_equal(pdf_arrow, pdf)
+ with
self.sql_conf({"spark.sql.execution.arrow.pyspark.fallback.enabled": False}):
+ df = self.spark.createDataFrame(pdf, schema)
+ pdf_arrow = df.toPandas()
+ assert_frame_equal(pdf_arrow, pdf)
+
+ def test_array_udt_roundtrip(self):
+ pdf = pd.DataFrame({'points': pd.Series([
+ [ExamplePoint(1.0, 1.0), ExamplePoint(1.0, 2.0), ExamplePoint(1.0,
3.0)],
Review comment:
See `_deserialize_pandas_with_udt`, support for StructType is postponed
in later PRs.
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
