[SPARK-16875][SQL] Add args checking for DataSet randomSplit and sample

core/src/main/scala/org/apache/spark/rdd/RDD.scala

@@ -474,12 +474,17 @@ abstract class RDD[T: ClassTag](
   def sample(
       withReplacement: Boolean,
       fraction: Double,
-      seed: Long = Utils.random.nextLong): RDD[T] = withScope {
-    require(fraction >= 0.0, "Negative fraction value: " + fraction)
-    if (withReplacement) {
-      new PartitionwiseSampledRDD[T, T](this, new PoissonSampler[T](fraction), true, seed)
-    } else {
-      new PartitionwiseSampledRDD[T, T](this, new BernoulliSampler[T](fraction), true, seed)
+      seed: Long = Utils.random.nextLong): RDD[T] = {
+    require(fraction >= 0,
+      s"Fraction must be nonnegative, but got ${fraction}")
+
+    withScope {
+      require(fraction >= 0.0, "Negative fraction value: " + fraction)
+      if (withReplacement) {
+        new PartitionwiseSampledRDD[T, T](this, new PoissonSampler[T](fraction), true, seed)
+      } else {
+        new PartitionwiseSampledRDD[T, T](this, new BernoulliSampler[T](fraction), true, seed)
+      }
     }
   }
 
@@ -493,14 +498,22 @@ abstract class RDD[T: ClassTag](
    */
   def randomSplit(
       weights: Array[Double],
-      seed: Long = Utils.random.nextLong): Array[RDD[T]] = withScope {
-    val sum = weights.sum
-    val normalizedCumWeights = weights.map(_ / sum).scanLeft(0.0d)(_ + _)
-    normalizedCumWeights.sliding(2).map { x =>
-      randomSampleWithRange(x(0), x(1), seed)
-    }.toArray
+      seed: Long = Utils.random.nextLong): Array[RDD[T]] = {
+    require(weights.forall(_ >= 0),
+      s"Weights must be nonnegative, but got ${weights.mkString("[", ",", "]")}")
+    require(weights.sum > 0,
+      s"Sum of weights must be positive, but got ${weights.mkString("[", ",", "]")}")
+
+    withScope {
+      val sum = weights.sum
+      val normalizedCumWeights = weights.map(_ / sum).scanLeft(0.0d)(_ + _)
+      normalizedCumWeights.sliding(2).map { x =>
+        randomSampleWithRange(x(0), x(1), seed)
+      }.toArray
+    }
   }
 
+
   /**
    * Internal method exposed for Random Splits in DataFrames. Samples an RDD given a probability
    * range.

sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala

@@ -1542,8 +1542,13 @@ class Dataset[T] private[sql](
    * @group typedrel
    * @since 1.6.0
    */
-  def sample(withReplacement: Boolean, fraction: Double, seed: Long): Dataset[T] = withTypedPlan {
-    Sample(0.0, fraction, withReplacement, seed, logicalPlan)()
+  def sample(withReplacement: Boolean, fraction: Double, seed: Long): Dataset[T] = {
+    require(fraction >= 0,
+      s"Fraction must be nonnegative, but got ${fraction}")
+
+    withTypedPlan {
+      Sample(0.0, fraction, withReplacement, seed, logicalPlan)()
+    }
   }
 
   /**
@@ -1571,6 +1576,11 @@ class Dataset[T] private[sql](
    * @since 2.0.0
    */
   def randomSplit(weights: Array[Double], seed: Long): Array[Dataset[T]] = {
+    require(weights.forall(_ >= 0),
+      s"Weights must be nonnegative, but got ${weights.mkString("[", ",", "]")}")
+    require(weights.sum > 0,
+      s"Sum of weights must be positive, but got ${weights.mkString("[", ",", "]")}")
+
     // It is possible that the underlying dataframe doesn't guarantee the ordering of rows in its
     // constituent partitions each time a split is materialized which could result in
     // overlapping splits. To prevent this, we explicitly sort each input partition to make the