wordcount

wordcount.java

// create the Spark configuration and context
SparkConf conf = new SparkConf().setAppName("Wordcount").setMaster("local[*]");

JavaSparkContext sc = new JavaSparkContext(conf);

// load data and create an RDD of string
JavaRDD<String> tweets = sc.textFile("path_To_File")

JavaPairRDD<String, Integer> wordcount = tweets.flatMap(line -> Arrays.asList(line.toString().split(" ")))
                                               // mapper step
                                               .mapToPair(word -> new Tuple2<>(word, 1))
                                               // reducer step
                                               .reduceByKey((x, y) -> x + y);