Github user BryanCutler commented on a diff in the pull request:
https://github.com/apache/spark/pull/19646#discussion_r149491411
--- Diff: python/pyspark/sql/session.py ---
@@ -416,6 +417,50 @@ def _createFromLocal(self, data, schema):
data = [schema.toInternal(row) for row in data]
return self._sc.parallelize(data), schema
+ def _get_numpy_record_dtypes(self, rec):
+ """
+ Used when converting a pandas.DataFrame to Spark using
to_records(), this will correct
+ the dtypes of records so they can be properly loaded into Spark.
+ :param rec: a numpy record to check dtypes
+ :return corrected dtypes for a numpy.record or None if no
correction needed
+ """
+ import numpy as np
+ cur_dtypes = rec.dtype
+ col_names = cur_dtypes.names
+ record_type_list = []
+ has_rec_fix = False
+ for i in xrange(len(cur_dtypes)):
+ curr_type = cur_dtypes[i]
+ # If type is a datetime64 timestamp, convert to microseconds
+ # NOTE: if dtype is datetime[ns] then np.record.tolist() will
output values as longs,
+ # conversion from [us] or lower will lead to py datetime
objects, see SPARK-22417
+ if curr_type == np.dtype('datetime64[ns]'):
+ curr_type = 'datetime64[us]'
+ has_rec_fix = True
+ record_type_list.append((str(col_names[i]), curr_type))
+ return record_type_list if has_rec_fix else None
+
+ def _convert_from_pandas(self, pdf, schema):
--- End diff --
yes, it isn't used in the conversion any more, but I think it should still
be here for the case when it's None and then assigned to a list of the pdf
column names. That way we can keep all pandas related code in this method.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
