Fixed validation of relativeSD in countApproxDistinct

nemccarthy · May 7, 2015 · 122d378 · 122d378
1 parent 32cdc81
commit 122d378
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -1151,8 +1151,8 @@ abstract class RDD[T: ClassTag](
    */
   @Experimental
   def countApproxDistinct(p: Int, sp: Int): Long = withScope {
-    require(p >= 4, s"p ($p) must be at least 4")
-    require(sp <= 32, s"sp ($sp) cannot be greater than 32")
+    require(p >= 4, s"p ($p) must be >= 4")
+    require(sp <= 32, s"sp ($sp) must be <= 32")
     require(sp == 0 || p <= sp, s"p ($p) cannot be greater than sp ($sp)")
     val zeroCounter = new HyperLogLogPlus(p, sp)
     aggregate(zeroCounter)(
@@ -1177,8 +1177,9 @@ abstract class RDD[T: ClassTag](
    *                   It must be greater than 0.000017.
    */
   def countApproxDistinct(relativeSD: Double = 0.05): Long = withScope {
+    require(relativeSD > 0.000017, s"accuracy ($relativeSD) must be greater than 0.000017")
     val p = math.ceil(2.0 * math.log(1.054 / relativeSD) / math.log(2)).toInt
-    countApproxDistinct(p, 0)
+    countApproxDistinct(if (p < 4) 4 else p, 0)
   }
 
   /**

diff --git a/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala b/core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala
@@ -89,6 +89,8 @@ class RDDSuite extends FunSuite with SharedSparkContext {
     val simpleRdd = sc.makeRDD(uniformDistro, 10)
     assert(error(simpleRdd.countApproxDistinct(8, 0), size) < 0.2)
     assert(error(simpleRdd.countApproxDistinct(12, 0), size) < 0.1)
+    assert(error(simpleRdd.countApproxDistinct(0.02), size) < 0.1)
+    assert(error(simpleRdd.countApproxDistinct(0.5), size) < 0.22)
   }
 
   test("SparkContext.union") {