diff options
-rw-r--r-- | core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala | 11 | ||||
-rw-r--r-- | core/src/main/scala/org/apache/spark/rdd/RDD.scala | 6 | ||||
-rw-r--r-- | python/pyspark/rdd.py | 6 |
3 files changed, 23 insertions, 0 deletions
diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala index 645dc3bfb6..3e9beb670f 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala @@ -101,12 +101,23 @@ class JavaRDD[T](val rdd: RDD[T])(implicit val classTag: ClassTag[T]) /** * Return a sampled subset of this RDD. + * + * @param withReplacement can elements be sampled multiple times (replaced when sampled out) + * @param fraction expected size of the sample as a fraction of this RDD's size + * without replacement: probability that each element is chosen; fraction must be [0, 1] + * with replacement: expected number of times each element is chosen; fraction must be >= 0 */ def sample(withReplacement: Boolean, fraction: Double): JavaRDD[T] = sample(withReplacement, fraction, Utils.random.nextLong) /** * Return a sampled subset of this RDD. + * + * @param withReplacement can elements be sampled multiple times (replaced when sampled out) + * @param fraction expected size of the sample as a fraction of this RDD's size + * without replacement: probability that each element is chosen; fraction must be [0, 1] + * with replacement: expected number of times each element is chosen; fraction must be >= 0 + * @param seed seed for the random number generator */ def sample(withReplacement: Boolean, fraction: Double, seed: Long): JavaRDD[T] = wrapRDD(rdd.sample(withReplacement, fraction, seed)) diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index a139780d96..a4c74ed03e 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -377,6 +377,12 @@ abstract class RDD[T: ClassTag]( /** * Return a sampled subset of this RDD. + * + * @param withReplacement can elements be sampled multiple times (replaced when sampled out) + * @param fraction expected size of the sample as a fraction of this RDD's size + * without replacement: probability that each element is chosen; fraction must be [0, 1] + * with replacement: expected number of times each element is chosen; fraction must be >= 0 + * @param seed seed for the random number generator */ def sample(withReplacement: Boolean, fraction: Double, diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index bf17f513c0..c337a43c8a 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -346,6 +346,12 @@ class RDD(object): """ Return a sampled subset of this RDD. + :param withReplacement: can elements be sampled multiple times (replaced when sampled out) + :param fraction: expected size of the sample as a fraction of this RDD's size + without replacement: probability that each element is chosen; fraction must be [0, 1] + with replacement: expected number of times each element is chosen; fraction must be >= 0 + :param seed: seed for the random number generator + >>> rdd = sc.parallelize(range(100), 4) >>> rdd.sample(False, 0.1, 81).count() 10 |