Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/21928#discussion_r206410816
--- Diff: python/pyspark/serializers.py ---
@@ -236,6 +237,11 @@ def create_array(s, t):
# TODO: need decode before converting to Arrow in Python 2
return pa.Array.from_pandas(s.apply(
lambda v: v.decode("utf-8") if isinstance(v, str) else v),
mask=mask, type=t)
+ elif t is not None and pa.types.is_decimal(t) and \
+ LooseVersion("0.9.0") <= LooseVersion(pa.__version__) <
LooseVersion("0.10.0"):
+ # TODO: see ARROW-2432. Remove when the minimum PyArrow
version becomes 0.10.0.
+ return pa.Array.from_pandas(s.apply(
+ lambda v: decimal.Decimal('NaN') if v is None else v),
mask=mask, type=t)
--- End diff --
existing test should test this `test_vectorized_udf_null_decimal`. This is
failed without the current change and PyArrow 0.9.0.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
