From 3a3d59c9a35035dccbac64602d579d503cb35999 Mon Sep 17 00:00:00 2001 From: Vinod K C Date: Fri, 8 May 2015 14:55:58 +0530 Subject: [PATCH] Reverted removal of validation relativeSD<0.000017 --- python/pyspark/rdd.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 42a452fa56907..545c5ad20cb96 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -2237,6 +2237,8 @@ def countApproxDistinct(self, relativeSD=0.05): >>> 16 < n < 24 True """ + if relativeSD < 0.000017: + raise ValueError("relativeSD should be greater than 0.000017") # the hash space in Java is 2^32 hashRDD = self.map(lambda x: portable_hash(x) & 0xFFFFFFFF) return hashRDD._to_java_object_rdd().countApproxDistinct(relativeSD)