diff options
| author | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-07-28 23:50:38 -0400 |
|---|---|---|
| committer | Matei Zaharia <matei@eecs.berkeley.edu> | 2013-07-29 02:51:43 -0400 |
| commit | d75c3086951f603ec30b2527c24559e053ed7f25 (patch) | |
| tree | 9ed6719befd62705f34c67557e51ce2a2d9bf1e8 /python/pyspark | |
| parent | 96b50e82dc0db501ab94748a23ae3237f1d82034 (diff) | |
| download | spark-d75c3086951f603ec30b2527c24559e053ed7f25.tar.gz spark-d75c3086951f603ec30b2527c24559e053ed7f25.tar.bz2 spark-d75c3086951f603ec30b2527c24559e053ed7f25.zip | |
Use None instead of empty string as it's slightly smaller/faster
Diffstat (limited to 'python/pyspark')
| -rw-r--r-- | python/pyspark/rdd.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 4aafe35d13..8734cacb0b 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -160,7 +160,7 @@ class RDD(object): >>> sorted(sc.parallelize([1, 1, 2, 3]).distinct().collect()) [1, 2, 3] """ - return self.map(lambda x: (x, "")) \ + return self.map(lambda x: (x, None)) \ .reduceByKey(lambda x, _: x) \ .map(lambda (x, _): x) |