Spark Java 单词计数(WordCount)

所用数据：

数据地址：E://hello.txt

Spark计算基本过程：

Spark单词计数Java代码：

package RDDtest;

import java.util.Arrays;

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 org.apache.spark.api.java.function.VoidFunction;

import scala.Tuple2;

public class WordCount {

	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("WordCount").setMaster("local[*]");
		JavaSparkContext jsc = new JavaSparkContext(conf);
		JavaRDD<String> lines = jsc.textFile("E://hello.txt");
		JavaRDD<String> word = lines.flatMap(new FlatMapFunction<String, String>() {
			private static final long serialVersionUID = 1L;
			@Override
			public Iterable<String> call(String str) throws Exception {
				return Arrays.asList(str.split(" "));
			}
		});
		JavaPairRDD<String, Integer> word2int = word.mapToPair(new PairFunction<String, String, Integer>() {
			private static final long serialVersionUID = 1L;
			@Override
			public Tuple2<String, Integer> call(String word) throws Exception {
				return new Tuple2<String, Integer>(word, 1);
			}
		});
		JavaPairRDD<String, Integer> res = word2int.reduceByKey(new Function2<Integer, Integer, Integer>() {
			private static final long serialVersionUID = 1L;
			@Override
			public Integer call(Integer a, Integer b) throws Exception {
				return a + b;
			}
		});
		res.foreach(new VoidFunction<Tuple2<String,Integer>>() {
			private static final long serialVersionUID = 1L;
			@Override
			public void call(Tuple2<String, Integer> t) throws Exception {
				System.out.println(t._1+" : "+t._2);
			}
		});
	}

}

运行结果：

结语：

时间匆忙，错误之处，请批评指正，相互学习。。