Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/18664#discussion_r147126818
--- Diff: python/pyspark/sql/types.py ---
@@ -1619,11 +1619,38 @@ def to_arrow_type(dt):
arrow_type = pa.decimal(dt.precision, dt.scale)
elif type(dt) == StringType:
arrow_type = pa.string()
+ elif type(dt) == DateType:
+ arrow_type = pa.date32()
+ elif type(dt) == TimestampType:
+ # Timestamps should be in UTC, JVM Arrow timestamps require a
timezone to be read
+ arrow_type = pa.timestamp('us', tz='UTC')
else:
raise TypeError("Unsupported type in conversion to Arrow: " +
str(dt))
return arrow_type
+def _check_dataframe_localize_timestamps(df):
--- End diff --
tiny nit: `df` -> `pdf`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
