aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py2
1 files changed, 2 insertions, 0 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 879655dc53..08d0474026 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -521,6 +521,8 @@ class RDD(object):
# the key-space into bins such that the bins have roughly the same
# number of (key, value) pairs falling into them
rddSize = self.count()
+ if not rddSize:
+ return self # empty RDD
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()