Skip to content

[SPARK-3141] [PySpark] fix sortByKey() with take() #2045

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
davies wants to merge 1 commit into from
Closed

[SPARK-3141] [PySpark] fix sortByKey() with take() #2045

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 8 additions & 10 deletions python/pyspark/rdd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -575,6 +575,8 @@ def sortByKey(self, ascending=True, numPartitions=None, keyfunc=lambda x: x):
# noqa

>>> tmp = [('a', 1), ('b', 2), ('1', 3), ('d', 4), ('2', 5)]
>>> sc.parallelize(tmp).sortByKey().first()
('1', 3)
>>> sc.parallelize(tmp).sortByKey(True, 1).collect()
[('1', 3), ('2', 5), ('a', 1), ('b', 2), ('d', 4)]
>>> sc.parallelize(tmp).sortByKey(True, 2).collect()
Expand All @@ -587,14 +589,13 @@ def sortByKey(self, ascending=True, numPartitions=None, keyfunc=lambda x: x):
if numPartitions is None:
numPartitions = self._defaultReducePartitions()

def sortPartition(iterator):
return iter(sorted(iterator, key=lambda (k, v): keyfunc(k), reverse=not ascending))

if numPartitions == 1:
if self.getNumPartitions() > 1:
self = self.coalesce(1)

def sort(iterator):
return sorted(iterator, reverse=(not ascending), key=lambda (k, v): keyfunc(k))

return self.mapPartitions(sort)
return self.mapPartitions(sortPartition)

# first compute the boundary of each part via sampling: we want to partition
# the key-space into bins such that the bins have roughly the same
Expand All @@ -610,17 +611,14 @@ def sort(iterator):
bounds = [samples[len(samples) * (i + 1) / numPartitions]
for i in range(0, numPartitions - 1)]

def rangePartitionFunc(k):
def rangePartitioner(k):
p = bisect.bisect_left(bounds, keyfunc(k))
if ascending:
return p
else:
return numPartitions - 1 - p

def mapFunc(iterator):
return sorted(iterator, reverse=(not ascending), key=lambda (k, v): keyfunc(k))

return self.partitionBy(numPartitions, rangePartitionFunc).mapPartitions(mapFunc, True)
return self.partitionBy(numPartitions, rangePartitioner).mapPartitions(sortPartition, True)

def sortBy(self, keyfunc, ascending=True, numPartitions=None):
"""
Expand Down