Github user holdenk commented on a diff in the pull request:
https://github.com/apache/spark/pull/17077#discussion_r110538670
--- Diff: python/pyspark/sql/readwriter.py ---
@@ -545,6 +545,57 @@ def partitionBy(self, *cols):
self._jwrite = self._jwrite.partitionBy(_to_seq(self._spark._sc,
cols))
return self
+ @since(2.2)
+ def bucketBy(self, numBuckets, *cols):
+ """Buckets the output by the given columns on the file system.
+
+ :param numBuckets: the number of buckets to save
+ :param cols: name of columns
+
+ >>> (df.write.format('parquet')
+ ... .bucketBy(100, 'year', 'month')
+ ... .mode("overwrite")
+ ... .saveAsTable('bucketed_table'))
+ """
+ if len(cols) == 1 and isinstance(cols[0], (list, tuple)):
+ cols = cols[0]
+
+ if not isinstance(numBuckets, int):
+ raise TypeError("numBuckets should be an int, got
{0}.".format(type(numBuckets)))
+
+ if not all(isinstance(c, basestring) for c in cols):
+ raise TypeError("cols argument should be a string or a
sequence of strings.")
+
+ col = cols[0]
+ cols = cols[1:]
+
+ self._jwrite = self._jwrite.bucketBy(numBuckets, col,
_to_seq(self._spark._sc, cols))
+ return self
+
+ @since(2.2)
+ def sortBy(self, *cols):
+ """Sorts the output in each bucket by the given columns on the
file system.
--- End diff --
Same comment as above with regards to the docstring
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
