diff options
author | Sean Owen <sowen@cloudera.com> | 2016-04-23 10:47:50 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2016-04-23 10:47:50 -0700 |
commit | be0d5d3bbebf0912c27bf41ce27b5ba214e61e19 (patch) | |
tree | 3d067a6e3aeb441217475e8fabcb4d6131575e61 /core/src/main/scala/org/apache | |
parent | a55fbe2a16aa0866ff8aca25bf9f772e6eb516a1 (diff) | |
download | spark-be0d5d3bbebf0912c27bf41ce27b5ba214e61e19.tar.gz spark-be0d5d3bbebf0912c27bf41ce27b5ba214e61e19.tar.bz2 spark-be0d5d3bbebf0912c27bf41ce27b5ba214e61e19.zip |
[SPARK-14873][CORE] Java sampleByKey methods take ju.Map but with Scala Double values; results in type Object
## What changes were proposed in this pull request?
Java `sampleByKey` methods should accept `Map` with `java.lang.Double` values
## How was this patch tested?
Existing (updated) Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes #12637 from srowen/SPARK-14873.
Diffstat (limited to 'core/src/main/scala/org/apache')
-rw-r--r-- | core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala | 18 |
1 files changed, 12 insertions, 6 deletions
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala index 2897272a8b..1c95bc4bfc 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala @@ -139,9 +139,12 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) * math.ceil(numItems * samplingRate) over all key values. */ def sampleByKey(withReplacement: Boolean, - fractions: java.util.Map[K, Double], + fractions: java.util.Map[K, jl.Double], seed: Long): JavaPairRDD[K, V] = - new JavaPairRDD[K, V](rdd.sampleByKey(withReplacement, fractions.asScala, seed)) + new JavaPairRDD[K, V](rdd.sampleByKey( + withReplacement, + fractions.asScala.mapValues(_.toDouble).toMap, // map to Scala Double; toMap to serialize + seed)) /** * Return a subset of this RDD sampled by key (via stratified sampling). @@ -154,7 +157,7 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) * Use Utils.random.nextLong as the default seed for the random number generator. */ def sampleByKey(withReplacement: Boolean, - fractions: java.util.Map[K, Double]): JavaPairRDD[K, V] = + fractions: java.util.Map[K, jl.Double]): JavaPairRDD[K, V] = sampleByKey(withReplacement, fractions, Utils.random.nextLong) /** @@ -168,9 +171,12 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) * two additional passes. */ def sampleByKeyExact(withReplacement: Boolean, - fractions: java.util.Map[K, Double], + fractions: java.util.Map[K, jl.Double], seed: Long): JavaPairRDD[K, V] = - new JavaPairRDD[K, V](rdd.sampleByKeyExact(withReplacement, fractions.asScala, seed)) + new JavaPairRDD[K, V](rdd.sampleByKeyExact( + withReplacement, + fractions.asScala.mapValues(_.toDouble).toMap, // map to Scala Double; toMap to serialize + seed)) /** * Return a subset of this RDD sampled by key (via stratified sampling) containing exactly @@ -186,7 +192,7 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) */ def sampleByKeyExact( withReplacement: Boolean, - fractions: java.util.Map[K, Double]): JavaPairRDD[K, V] = + fractions: java.util.Map[K, jl.Double]): JavaPairRDD[K, V] = sampleByKeyExact(withReplacement, fractions, Utils.random.nextLong) /** |