rdd.scala

def topHashtags(tweets: RDD[Tweet], n: Int): Array[(String, BigInt)] =
  tweets
    .flatMap(_.text.split("\\s+"))     // split it into words
    .filter(_.startsWith("#"))         // filter hashtag words
    .map(_.toLowerCase)                // normalize hashtags
    .map((_, BigInt(1)))               // create tuples for counting
    .reduceByKey((a, b) => a + b)      // accumulate counters
    .top(n)(Ordering.by(_._2))         // return ordered top hashtags