[SPARK-4860][pyspark][sql] adding sample() to JavaSchemaRDD

apache · Dec 23, 2014 · b916442 · b916442
1 parent 020cbdf
commit b916442
Showing 1 changed file with 6 additions and 0 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala
@@ -218,4 +218,10 @@ class JavaSchemaRDD(
    */
   def subtract(other: JavaSchemaRDD, p: Partitioner): JavaSchemaRDD =
     this.baseSchemaRDD.subtract(other.baseSchemaRDD, p).toJavaSchemaRDD
+
+  /**
+   * Return an RDD with a sampled version of the underlying dataset.
+   */
+  def sample(withReplacement: Boolean, fraction: Double, seed: Long): JavaSchemaRDD =
+    this.baseSchemaRDD.sample(withReplacement, fraction, seed).toJavaSchemaRDD
 }