map(f : T ) U) : RDD[T] ) RDD[U]
filter(f : T ) Bool) : RDD[T] ) RDD[T]
flatMap(f : T ) Seq[U]) : RDD[T] ) RDD[U]
sample(fraction : Float) : RDD[T] ) RDD[T] (Deterministic sampling)
groupByKey() : RDD[(K, V)] ) RDD[(K, Seq[V])]
reduceByKey(f : (V; V) ) V) : RDD[(K, V)] ) RDD[(K, V)]
union() : (RDD[T]; RDD[T]) ) RDD[T]
join() : (RDD[(K, V)]; RDD[(K, W)]) ) RDD[(K, (V, W))]
cogroup() : (RDD[(K, V)]; RDD[(K, W)]) ) RDD[(K, (Seq[V], Seq[W]))]
crossProduct() : (RDD[T]; RDD[U]) ) RDD[(T, U)]
mapValues(f : V ) W) : RDD[(K, V)] ) RDD[(K, W)] (Preserves partitioning)
sort(c : Comparator[K]) : RDD[(K, V)] ) RDD[(K, V)]
partitionBy(p : Partitioner[K]) : RDD[(K, V)] ) RDD[(K, V)]
count() : RDD[T] ) Long
collect() : RDD[T] ) Seq[T]
reduce(f : (T; T) ) T) : RDD[T] ) T
lookup(k : K) : RDD[(K, V)] ) Seq[V] (On hash/range partitioned RDDs)
save(path : String) : Outputs RDD to a storage system, e.g., HDFS
// Transformations (return a new RDD)
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[U: ClassTag](f: T => U): RDD[U] = new MappedRDD(this, sc.clean(f))
/**
* Return a new RDD by first applying a function to all elements of this
* RDD, and then flattening the results.
*/
def flatMap[U: ClassTag](f: T => TraversableOnce[U]): RDD[U] =
new FlatMappedRDD(this, sc.clean(f))
/**
* Return a new RDD containing only the elements that satisfy a predicate.
*/
def filter(f: T => Boolean): RDD[T] = new FilteredRDD(this, sc.clean(f))
......
/**
* Return a new RDD by applying a function to all elements of this RDD.
*/
def map[U: ClassTag](f: T => U): RDD[U] = new MappedRDD(this, sc.clean(f))
