Flink-Reduce进行归约聚合（案例之找点击次数最活跃（即访问量最大））

最新推荐文章于 2023-12-08 17:09:54 发布

你最好看

最新推荐文章于 2023-12-08 17:09:54 发布

阅读量236

点赞数

分类专栏： flink

本文链接：https://blog.csdn.net/weixin_36857135/article/details/126649051

版权

Apache Flink 流处理数据聚合用户活跃度 Reduce

关键词由CSDN通过智能技术生成

flink 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

1. 找点击次数最活跃（即访问量最大）

package com.beibeixu.chapter05;

import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.functions.ReduceFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;


/**
 * @author beibeiking
 * @date 2022/09/01 16:16
 * 归约聚合（reduce）
 **/

public class TransformReduceTest {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);

        //从元素中读取数据
        DataStreamSource<Event> stream = env.fromElements(
                new Event("Mary", "./home", 1000L),
                new Event("Bob", "./cart", 2000L),
                new Event("Alice", "./prod?id=100", 3000L),
                new Event("Bob", "./prod?id=1", 3300L),
                new Event("Bob", "./home", 3300L),
                new Event("Alice", "./prod?id=200", 3200L),
                new Event("Bob", "./prod?id=2", 3800L),
                new Event("Bob", "./prod?id=3", 4200L)

        );

        //找点击次数最活跃（即访问量最大）
        //1.统计每个用户的访问频次
        SingleOutputStreamOperator<Tuple2<String, Long>> clicksByUser = stream.map(new MapFunction<Event, Tuple2<String, Long>>() {
                    @Override
                    public Tuple2<String, Long> map(Event event) throws Exception {
                        return Tuple2.of(event.user, 1L);
                    }
                }).keyBy(data -> data.f0)
                .reduce(new ReduceFunction<Tuple2<String, Long>>() {
                    @Override
                    public Tuple2<String, Long> reduce(Tuple2<String, Long> stringLongTuple2, Tuple2<String, Long> t1) throws Exception {
                        return Tuple2.of(stringLongTuple2.f0, stringLongTuple2.f1 + t1.f1);
                    }
                });
        clicksByUser.print("clicksByUser:");
        //2.选取当前最活跃的用户,提取第二个字段最大值
        SingleOutputStreamOperator<Tuple2<String, Long>> result = clicksByUser.keyBy(data -> "key")
                .reduce(new ReduceFunction<Tuple2<String, Long>>() {
                    @Override
                    public Tuple2<String, Long> reduce(Tuple2<String, Long> stringLongTuple2, Tuple2<String, Long> t1) throws Exception {
                        return stringLongTuple2.f1 > t1.f1 ? stringLongTuple2 : t1;
                        //如果stringLongTuple2.f1大于t1.f1，则返回stringLongTuple2，否则返回t1
                    }
                });
        result.print("result:");


        env.execute();

    }
}

输出：
clicksByUser:> (Mary,1)
clicksByUser:> (Bob,1)
clicksByUser:> (Alice,1)
clicksByUser:> (Bob,2)
clicksByUser:> (Bob,3)
clicksByUser:> (Alice,2)
clicksByUser:> (Bob,4)
clicksByUser:> (Bob,5)
result:> (Mary,1)
result:> (Bob,1)
result:> (Alice,1)
result:> (Bob,2)
result:> (Bob,3)
result:> (Bob,3)
result:> (Bob,4)
result:> (Bob,5)