Added a note, shuffle is required for intersection.

Author: ScrapCodes

core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala

@@ -143,6 +143,8 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[JDouble, Ja
   /**
    * Return the intersection of this RDD and another one. The output will not contain any duplicate
    * elements, even if the input RDDs did.
+   *
+   * Note that this method performs a shuffle internally.
    */
   def intersection(other: JavaDoubleRDD): JavaDoubleRDD = fromRDD(srdd.intersection(other.srdd))
 

core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala

@@ -129,6 +129,8 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)])
   /**
    * Return the intersection of this RDD and another one. The output will not contain any duplicate
    * elements, even if the input RDDs did.
+   *
+   * Note that this method performs a shuffle internally.
    */
   def intersection(other: JavaPairRDD[K, V]): JavaPairRDD[K, V] =
     new JavaPairRDD[K, V](rdd.intersection(other.rdd))

core/src/main/scala/org/apache/spark/api/java/JavaRDD.scala

@@ -110,6 +110,8 @@ class JavaRDD[T](val rdd: RDD[T])(implicit val classTag: ClassTag[T])
   /**
    * Return the intersection of this RDD and another one. The output will not contain any duplicate
    * elements, even if the input RDDs did.
+   *
+   * Note that this method performs a shuffle internally.
    */
   def intersection(other: JavaRDD[T]): JavaRDD[T] = wrapRDD(rdd.intersection(other.rdd))
 

python/pyspark/rdd.py

@@ -321,10 +321,10 @@ def union(self, other):
 
     def intersection(self, other):
         """
-        Return the intersection of this RDD and another one.
-
-        Note: The output will not contain any duplicate elements, even if the
-        input RDDs did.
+        Return the intersection of this RDD and another one. The output will not 
+        contain any duplicate elements, even if the input RDDs did.
+        
+        Note that this method performs a shuffle internally.
 
         >>> rdd1 = sc.parallelize([1, 10, 2, 3, 4, 5])
         >>> rdd2 = sc.parallelize([1, 6, 2, 3, 7, 8])