Github user wesm commented on a diff in the pull request:
https://github.com/apache/spark/pull/18664#discussion_r146062157
--- Diff: python/pyspark/sql/types.py ---
@@ -1619,11 +1619,39 @@ 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):
+ """ Convert timezone aware timestamps to timezone-naive in local time
+ """
+ from pandas.api.types import is_datetime64tz_dtype
+ for column, series in df.iteritems():
+ # TODO: handle nested timestamps?
+ if is_datetime64tz_dtype(series.dtype):
+ df[column] =
series.dt.tz_convert('tzlocal()').dt.tz_localize(None)
+ return df
+
+
+def _check_series_convert_timestamps_internal(s):
+ """ Convert a tz-naive timestamp in local tz to UTC normalized for
Spark internal storage
+ """
+ from pandas.api.types import is_datetime64_dtype
+ # TODO: handle nested timestamps?
--- End diff --
Arrays are supported in pyarrow (but perhaps not for timestamps? If that's
true could you open a JIRA?), or do you mean something else?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
