Java examples for Big Data:apache spark
counting of words in input list of sentences using apache spark
import java.util.Arrays; import java.util.List; import java.util.Map; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaSparkContext; import scala.Tuple2; public class WordCountDemo { public static void main(String[] args) { final SparkConf sparkConf = new SparkConf().setAppName("Word Count Demo").setMaster("local"); /*from w w w . jav a 2 s . co m*/ try(final JavaSparkContext jSC = new JavaSparkContext(sparkConf)) { final List<String> sentences = Arrays.asList( "All Programming Tutorials", "Getting Started With Apache Spark", "Developing Java Applications In Apache Spark", "Getting Started With RDDs In Apache Spark" ); final Map<String, Object> wordsCount = jSC.parallelize(sentences) .flatMap((x) -> Arrays.asList(x.split(" "))) .mapToPair((x) -> new Tuple2<String, Integer>(x, 1)) .countByKey(); System.out.println(wordsCount); } } }