spark Streaming word count

scala> import org.apache.spark.streaming._
import org.apache.spark.streaming._

scala> val stc = new StreamingContext(sc, Seconds(5))
stc: org.apache.spark.streaming.StreamingContext = org.apache.spark.streaming.StreamingContext@18f2d752

scala> val lines = stc.socketTextStream("localhost", 9999)
lines: org.apache.spark.streaming.dstream.ReceiverInputDStream[String] = org.apache.spark.streaming.dstream.SocketInputDStream@346995e1

scala> val words = lines.flatMap(_.split(" "))
words: org.apache.spark.streaming.dstream.DStream[String] = org.apache.spark.streaming.dstream.FlatMappedDStream@27058c08

scala> val pairs = words.map(word => (word, 1))
pairs: org.apache.spark.streaming.dstream.DStream[(String, Int)] = org.apache.spark.streaming.dstream.MappedDStream@de5d972

scala> val wordCounts = pairs.reduceByKey(_ + _)
wordCounts: org.apache.spark.streaming.dstream.DStream[(String, Int)] = org.apache.spark.streaming.dstream.ShuffledDStream@409f70ca

scala> wordCounts.print()

scala> wordCounts.foreachRDD { rdd => rdd.foreach(print) }

scala> stc.start()

scala> stc.awaitTermination()


new terminal
[cloudera@quickstart ~]$ nc -lk 9999
hi
hello hello