Big Data Processing - Case Study 2 (Spark)

wordCount.scala

val input_file = sc. textFile("/Users/mmafrar/WordCount/input_file.txt")

input_file.collect

val word = input_file.flatMap(line => line.split(" "))

word.collect

val mapdata = word. map (word => (word, 1))

val reducedata = mapdata. reduceByKey (_+_)

reducedata.collect

reducedata.saveAsTextFile ("/Users/mmafrar/WordCount/output_folder")