java spark 单词统计_用Spark写一个简单的wordcount词频统计程序

public class WordCountLocal {

public static void main(String[] args) {

SparkConf conf = new SparkConf().setAppName("WordCountLocal").setMaster("local[2]");

JavaSparkContext sc = new JavaSparkContext(conf);

JavaRDD words = sc.textFile("c:.//words.txt").flatMap(new FlatMapFunction() {

@Override

public Iterable call(String line) throws Exception {

return Arrays.asList(line.split(" "));

}

});

JavaPairRDD mapToPair = words.mapToPair(new PairFunction() {

@Override

public Tuple2 call(String word) throws Exception {

return new Tuple2(word,1);

}

});

JavaPairRDD result = mapToPair.reduceByKey(new Function2() {

@Override

public Integer call(Integer v1, Integer v2) throws Exception {

return v1 + v2;

}

});

result.foreach(new VoidFunction>() {

@Override

public void call(Tuple2 wordCount) throws Exception {

System.out.println(wordCount._1 + " appear " + wordCount._2 + " times!");

}

});

sc.close();

}

}