Java Error while running Spark Word Count in Eclipse

Question

When i am trying to run a simple word count in Spark Java using Eclipse, i am getting Java error in a new popup Java Virtual Machine Launcher window which says-

A Java Exception has occurred.

 java -version
Java Virtual Machine Launcher
 java version "1.7.0_80"
Java(TM) SE Runtime Environment (build 1.7.0_80-b15)
 Java HotSpot(TM) 64-Bit Server VM (build 24.80-b11, mixed mode)

Below is the code:

package com.fd.spark;

import java.util.Arrays;
import java.util.Iterator;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;

import scala.Tuple2;


public class SparkWordCount {
public static void main(String[] args) throws Exception {
String inputFile = "/Spark/inp1";
String outputFile = "/Spark/out1";
// Create a Java Spark Context.
SparkConf conf = new SparkConf().setAppName("wordCount").setMaster("local");
    JavaSparkContext sc = new JavaSparkContext(conf);
// Load our input data.
JavaRDD<String> input = sc.textFile(inputFile);
// Split up into words.
JavaRDD<String> words = input.flatMap(
  new FlatMapFunction<String, String>() {
    public Iterator<String> call(String x) {
      return (Iterator<String>) Arrays.asList(x.split(" "));
    }});
// Transform into word and count.
JavaPairRDD<String, Integer> counts = words.mapToPair(
  new PairFunction<String, String, Integer>(){
    public Tuple2<String, Integer> call(String x){
      return new Tuple2(x, 1);
    }}).reduceByKey(new Function2<Integer, Integer, Integer>(){
        public Integer call(Integer x, Integer y){ return x + y;}});
// Save the word count back out to a text file, causing evaluation.
counts.saveAsTextFile(outputFile);
}
}

Answer 1

Use the below in Java 8 and it will work. Below is my code snippet on Java 8 using lamda functions.

public class WordCount {

    public static void main(
            String[] args) {
        SparkConf sparkConf = new SparkConf().setMaster("local").setAppName("JD Word Counter");

        JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);

        JavaRDD<String> inputFile = sparkContext.textFile(*Path_To_TXT_file*);

        JavaRDD<String> wordsFromFile = inputFile.flatMap(content -> Arrays.asList(content.split(" ")).iterator());

        JavaPairRDD<String,Integer> countData = wordsFromFile.mapToPair(t -> new Tuple2<String,Integer>(t,1)).reduceByKey((x, y) -> x + y);

        countData.collect().forEach(t -> System.out.println(t._1+" : "+t._2));
    }
}