remove importance sampler

mengxr · mengxr · commit 60be09e9e1e8 · 2014-07-23T19:41:33.000-07:00
diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala
@@ -19,15 +19,14 @@ package org.apache.spark
 
 import java.io.{IOException, ObjectInputStream, ObjectOutputStream}
 
-import org.apache.spark.util.random.{XORShiftRandom, SamplingUtils}
-
 import scala.collection.mutable.ArrayBuffer
 import scala.reflect.{ClassTag, classTag}
 import scala.util.hashing.byteswap32
 
 import org.apache.spark.rdd.RDD
 import org.apache.spark.serializer.JavaSerializer
 import org.apache.spark.util.{CollectionsUtils, Utils}
+import org.apache.spark.util.random.{XORShiftRandom, SamplingUtils}
 
 /**
  * An object that defines how the elements in a key-value pair RDD are partitioned by key.
diff --git a/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala b/core/src/main/scala/org/apache/spark/util/random/RandomSampler.scala
@@ -106,28 +106,3 @@ class PoissonSampler[T](mean: Double) extends RandomSampler[T, T] {
 
   override def clone = new PoissonSampler[T](mean)
 }
-
-/**
- * :: DeveloperApi ::
- * A sampler selects items based on their importance scores defined in the keys.
- *
- * The importance score should be within range `[0, 1]`. Items with scores less than or equal to 0
- * would never get selected, while items with scores greater than or equal to 1 would always get
- * selected.
- *
- * @param ratio sampling probability
- * @tparam T item type
- */
-@DeveloperApi
-class ImportanceSampler[T](ratio: Double) extends RandomSampler[(Double, T), (Double, T)] {
-
-  private[random] var rng: Random = new XORShiftRandom
-
-  override def setSeed(seed: Long) = rng.setSeed(seed)
-
-  override def sample(items: Iterator[(Double, T)]): Iterator[(Double, T)] = {
-    items.filter(item => rng.nextDouble() < ratio)
-  }
-
-  override def clone = new ImportanceSampler[T](ratio)
-}
