From a21d8b07a130fc47e76a96935f272cb720ff1250 Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Thu, 17 Aug 2017 21:45:16 -0700
Subject: [PATCH] [SPARK-21778][SQL] Simpler Dataset.sample API in Scala / Java

---
 .../scala/org/apache/spark/sql/Dataset.scala  | 36 +++++++++++++++++--
 1 file changed, 34 insertions(+), 2 deletions(-)

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
index a9887eb95279..615686ccbe2b 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
@@ -1848,11 +1848,43 @@ class Dataset[T] private[sql](
     Except(logicalPlan, other.logicalPlan)
   }
 
+  /**
+   * Returns a new [[Dataset]] by sampling a fraction of rows (without replacement),
+   * using a user-supplied seed.
+   *
+   * @param fraction Fraction of rows to generate, range [0.0, 1.0].
+   * @param seed Seed for sampling.
+   *
+   * @note This is NOT guaranteed to provide exactly the fraction of the count
+   * of the given [[Dataset]].
+   *
+   * @group typedrel
+   * @since 2.3.0
+   */
+  def sample(fraction: Double, seed: Long): Dataset[T] = {
+    sample(withReplacement = false, fraction = fraction, seed = seed)
+  }
+
+  /**
+   * Returns a new [[Dataset]] by sampling a fraction of rows (without replacement).
+   *
+   * @param fraction Fraction of rows to generate, range [0.0, 1.0].
+   *
+   * @note This is NOT guaranteed to provide exactly the fraction of the count
+   * of the given [[Dataset]].
+   *
+   * @group typedrel
+   * @since 2.3.0
+   */
+  def sample(fraction: Double): Dataset[T] = {
+    sample(withReplacement = false, fraction = fraction)
+  }
+
   /**
    * Returns a new [[Dataset]] by sampling a fraction of rows, using a user-supplied seed.
    *
    * @param withReplacement Sample with replacement or not.
-   * @param fraction Fraction of rows to generate.
+   * @param fraction Fraction of rows to generate, range [0.0, 1.0].
    * @param seed Seed for sampling.
    *
    * @note This is NOT guaranteed to provide exactly the fraction of the count
@@ -1871,7 +1903,7 @@ class Dataset[T] private[sql](
    * Returns a new [[Dataset]] by sampling a fraction of rows, using a random seed.
    *
    * @param withReplacement Sample with replacement or not.
-   * @param fraction Fraction of rows to generate.
+   * @param fraction Fraction of rows to generate, range [0.0, 1.0].
    *
    * @note This is NOT guaranteed to provide exactly the fraction of the total count
    * of the given [[Dataset]].