Skip to content

[SPARK-11904] [PySpark] reduceByKeyAndWindow does not require checkpointing when invFunc is None #9888

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
wants to merge 3 commits into from
Closed

[SPARK-11904] [PySpark] reduceByKeyAndWindow does not require checkpointing when invFunc is None #9888

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6730f72
invFunc=None does not require checkpointing
dtolpin Nov 21, 2015
60cfd64
PEP8 failed checks fixed
dtolpin Dec 16, 2015
8a92809
made lines to be less than 100 characters long
dtolpin Dec 16, 2015
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
45 changes: 23 additions & 22 deletions python/pyspark/streaming/dstream.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,31 +542,32 @@ def reduceByKeyAndWindow(self, func, invFunc, windowDuration, slideDuration=None

reduced = self.reduceByKey(func, numPartitions)

def reduceFunc(t, a, b):
b = b.reduceByKey(func, numPartitions)
r = a.union(b).reduceByKey(func, numPartitions) if a else b
if filterFunc:
r = r.filter(filterFunc)
return r

def invReduceFunc(t, a, b):
b = b.reduceByKey(func, numPartitions)
joined = a.leftOuterJoin(b, numPartitions)
return joined.mapValues(lambda kv: invFunc(kv[0], kv[1])
if kv[1] is not None else kv[0])

jreduceFunc = TransformFunction(self._sc, reduceFunc, reduced._jrdd_deserializer)
if invFunc:
def reduceFunc(t, a, b):
b = b.reduceByKey(func, numPartitions)
r = a.union(b).reduceByKey(func, numPartitions) if a else b
if filterFunc:
r = r.filter(filterFunc)
return r

def invReduceFunc(t, a, b):
b = b.reduceByKey(func, numPartitions)
joined = a.leftOuterJoin(b, numPartitions)
return joined.mapValues(lambda kv: invFunc(kv[0], kv[1])
if kv[1] is not None else kv[0])

jreduceFunc = TransformFunction(self._sc, reduceFunc, reduced._jrdd_deserializer)
jinvReduceFunc = TransformFunction(self._sc, invReduceFunc, reduced._jrdd_deserializer)
if slideDuration is None:
slideDuration = self._slideDuration
dstream = self._sc._jvm.PythonReducedWindowedDStream(
reduced._jdstream.dstream(),
jreduceFunc, jinvReduceFunc,
self._ssc._jduration(windowDuration),
self._ssc._jduration(slideDuration))
return DStream(dstream.asJavaDStream(), self._ssc, self._sc.serializer)
else:
jinvReduceFunc = None
if slideDuration is None:
slideDuration = self._slideDuration
dstream = self._sc._jvm.PythonReducedWindowedDStream(reduced._jdstream.dstream(),
jreduceFunc, jinvReduceFunc,
self._ssc._jduration(windowDuration),
self._ssc._jduration(slideDuration))
return DStream(dstream.asJavaDStream(), self._ssc, self._sc.serializer)
return reduced.window(windowDuration, slideDuration).reduceByKey(func, numPartitions)

def updateStateByKey(self, updateFunc, numPartitions=None):
"""
Expand Down