使用JAVA Spark API统计不同值在键值对中出现的次数

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.Function;
import scala.Tuple2;

JavaSparkContext sparkContext = new JavaSparkContext("local", "KeyValueCount");

JavaRDD<Tuple2<String, Integer>> keyValuePairs = sparkContext.parallelize(Arrays.asList(
    new Tuple2<>("key1", 1),
    new Tuple2<>("key2", 2),
    new Tuple2<>("key1", 3),
    new Tuple2<>("key3", 4),
    new Tuple2<>("key2", 5),
    new Tuple2<>("key1", 6)
));

JavaPairRDD<String, Integer> counts = keyValuePairs
    .mapToPair(pair -> new Tuple2<>(pair._1(), 1))
    .reduceByKey((a, b) -> a + b);

counts.saveAsTextFile("output");
counts.foreach(pair -> System.out.println(pair._1() + ": " + pair._2()));