From e3681f26fae7e87321ac991f5a0fb7517415803a Mon Sep 17 00:00:00 2001 From: Dan McClary Date: Tue, 18 Mar 2014 00:45:47 -0700 Subject: Spark 1246 add min max to stat counter Here's the addition of min and max to statscounter.py and min and max methods to rdd.py. Author: Dan McClary Closes #144 from dwmclary/SPARK-1246-add-min-max-to-stat-counter and squashes the following commits: fd3fd4b [Dan McClary] fixed error, updated test 82cde0e [Dan McClary] flipped incorrectly assigned inf values in StatCounter 5d96799 [Dan McClary] added max and min to StatCounter repr for pyspark 21dd366 [Dan McClary] added max and min to StatCounter output, updated doc 1a97558 [Dan McClary] added max and min to StatCounter output, updated doc a5c13b0 [Dan McClary] Added min and max to Scala and Java RDD, added min and max to StatCounter ed67136 [Dan McClary] broke min/max out into separate transaction, added to rdd.py 1e7056d [Dan McClary] added underscore to getBucket 37a7dea [Dan McClary] cleaned up boundaries for histogram -- uses real min/max when buckets are derived 29981f2 [Dan McClary] fixed indentation on doctest comment eaf89d9 [Dan McClary] added correct doctest for histogram 4916016 [Dan McClary] added histogram method, added max and min to statscounter --- python/pyspark/rdd.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'python/pyspark/rdd.py') diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index f3b432ff24..ae09dbff02 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -571,7 +571,26 @@ class RDD(object): return reduce(op, vals, zeroValue) # TODO: aggregate + + + def max(self): + """ + Find the maximum item in this RDD. + + >>> sc.parallelize([1.0, 5.0, 43.0, 10.0]).max() + 43.0 + """ + return self.reduce(max) + def min(self): + """ + Find the maximum item in this RDD. + + >>> sc.parallelize([1.0, 5.0, 43.0, 10.0]).min() + 1.0 + """ + return self.reduce(min) + def sum(self): """ Add up the elements in this RDD. -- cgit v1.2.3