求pv

pv定义

衡量网站用户访问的网页的数量，PV与来访者的数量成正比，但是PV并不直接决定页面的正式来访者数量，如同一个来访者通过不断的刷新页面，也可以制造出非常高的PV。

实现代码

public class TestPV {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf()
                .setMaster("local").setAppName("transformation");
        JavaSparkContext jsc = new JavaSparkContext(conf);

        JavaRDD<String> lineRDD = jsc.textFile("data/pvuvdata.txt");

        lineRDD.flatMap(new FlatMapFunction<String, Tuple2<String, String>>() {
            @Override
            public Iterator<Tuple2<String, String>> call(String s) throws Exception {
                String[] str = s.split(" ");
                Tuple2<String, String> tuple2= new Tuple2<String, String>(str[5], str[0]);
                List<Tuple2<String, String>> list = new ArrayList<>();
                list.add(tuple2);
                return list.iterator();
            }
        }).mapToPair(new PairFunction<Tuple2<String, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<String, String> tuple2) throws Exception {
                Tuple2<String, Integer> tuple = new Tuple2<String, Integer>(tuple2._1, 1);
                return tuple;
            }
        }).reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer integer, Integer integer2) throws Exception {
                return integer+integer2;
            }
        }).foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                System.out.println(stringIntegerTuple2);
            }
        });

        jsc.stop();
    }
}