Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/11445#discussion_r54620370
--- Diff: python/pyspark/sql/dataframe.py ---
@@ -267,44 +267,6 @@ def take(self, num):
self._jdf, num)
return list(_load_from_socket(port,
BatchedSerializer(PickleSerializer())))
- @ignore_unicode_prefix
- @since(1.3)
- def map(self, f):
- """ Returns a new :class:`RDD` by applying a the ``f`` function to
each :class:`Row`.
-
- This is a shorthand for ``df.rdd.map()``.
-
- >>> df.map(lambda p: p.name).collect()
- [u'Alice', u'Bob']
- """
- return self.rdd.map(f)
-
- @ignore_unicode_prefix
- @since(1.3)
- def flatMap(self, f):
- """ Returns a new :class:`RDD` by first applying the ``f``
function to each :class:`Row`,
- and then flattening the results.
-
- This is a shorthand for ``df.rdd.flatMap()``.
-
- >>> df.flatMap(lambda p: p.name).collect()
- [u'A', u'l', u'i', u'c', u'e', u'B', u'o', u'b']
- """
- return self.rdd.flatMap(f)
-
- @since(1.3)
- def mapPartitions(self, f, preservesPartitioning=False):
- """Returns a new :class:`RDD` by applying the ``f`` function to
each partition.
-
- This is a shorthand for ``df.rdd.mapPartitions()``.
-
- >>> rdd = sc.parallelize([1, 2, 3, 4], 4)
- >>> def f(iterator): yield 1
- >>> rdd.mapPartitions(f).sum()
- 4
- """
- return self.rdd.mapPartitions(f, preservesPartitioning)
-
--- End diff --
Should we also remove `foreach` and `foreachPartition`?
---
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]
