diff options
Diffstat (limited to 'core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala')
-rw-r--r-- | core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala index 043cb183ba..9f02a9b7d3 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala @@ -26,6 +26,8 @@ import org.apache.spark.storage.StorageLevel import java.lang.Double import org.apache.spark.Partitioner +import scala.collection.JavaConverters._ + class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, JavaDoubleRDD] { override val classManifest: ClassManifest[Double] = implicitly[ClassManifest[Double]] @@ -182,6 +184,44 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[Double, Jav /** (Experimental) Approximate operation to return the sum within a timeout. */ def sumApprox(timeout: Long): PartialResult[BoundedDouble] = srdd.sumApprox(timeout) + + /** + * Compute a histogram of the data using bucketCount number of buckets evenly + * spaced between the minimum and maximum of the RDD. For example if the min + * value is 0 and the max is 100 and there are two buckets the resulting + * buckets will be [0,50) [50,100]. bucketCount must be at least 1 + * If the RDD contains infinity, NaN throws an exception + * If the elements in RDD do not vary (max == min) always returns a single bucket. + */ + def histogram(bucketCount: Int): Pair[Array[scala.Double], Array[Long]] = { + val result = srdd.histogram(bucketCount) + (result._1, result._2) + } + + /** + * Compute a histogram using the provided buckets. The buckets are all open + * to the left except for the last which is closed + * e.g. for the array + * [1,10,20,50] the buckets are [1,10) [10,20) [20,50] + * e.g 1<=x<10 , 10<=x<20, 20<=x<50 + * And on the input of 1 and 50 we would have a histogram of 1,0,0 + * + * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched + * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets + * to true. + * buckets must be sorted and not contain any duplicates. + * buckets array must be at least two elements + * All NaN entries are treated the same. If you have a NaN bucket it must be + * the maximum value of the last position and all NaN entries will be counted + * in that bucket. + */ + def histogram(buckets: Array[scala.Double]): Array[Long] = { + srdd.histogram(buckets, false) + } + + def histogram(buckets: Array[Double], evenBuckets: Boolean): Array[Long] = { + srdd.histogram(buckets.map(_.toDouble), evenBuckets) + } } object JavaDoubleRDD { |