diff options
Diffstat (limited to 'python/pyspark/rdd.py')
-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 1b18789040..c8e54ed5c6 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -595,7 +595,7 @@ class RDD(object): maxSampleSize = numPartitions * 20.0 # constant from Spark's RangePartitioner fraction = min(maxSampleSize / max(rddSize, 1), 1.0) samples = self.sample(False, fraction, 1).map(lambda (k, v): k).collect() - samples = sorted(samples, reverse=(not ascending), key=keyfunc) + samples = sorted(samples, key=keyfunc) # we have numPartitions many parts but one of the them has # an implicit boundary |