• 使用随机数以及扩容表进行join代码


            /**
             * 使用随机数和扩容表进行join
             */
            
            JavaPairRDD<String, Row> expandedRDD = userid2InfoRDD.flatMapToPair(
                    
                    new PairFlatMapFunction<Tuple2<Long,Row>, String, Row>() {
    
                        private static final long serialVersionUID = 1L;
    
                        @Override
                        public Iterable<Tuple2<String, Row>> call(Tuple2<Long, Row> tuple)
                                throws Exception {
                            List<Tuple2<String, Row>> list = new ArrayList<Tuple2<String, Row>>();
                            
                            for(int i = 0; i < 10; i++) {
                                list.add(new Tuple2<String, Row>(0 + "_" + tuple._1, tuple._2));
                            }
                            
                            return list;
                        }
                        
                    });
            
            JavaPairRDD<String, String> mappedRDD = userid2PartAggrInfoRDD.mapToPair(
                    
                    new PairFunction<Tuple2<Long,String>, String, String>() {
    
                        private static final long serialVersionUID = 1L;
    
                        @Override
                        public Tuple2<String, String> call(Tuple2<Long, String> tuple)
                                throws Exception {
                            Random random = new Random();
                            int prefix = random.nextInt(10);
                            return new Tuple2<String, String>(prefix + "_" + tuple._1, tuple._2);  
                        }
                        
                    });
            
            JavaPairRDD<String, Tuple2<String, Row>> joinedRDD = mappedRDD.join(expandedRDD);
            
            JavaPairRDD<String, String> finalRDD = joinedRDD.mapToPair(
                    
                    new PairFunction<Tuple2<String,Tuple2<String,Row>>, String, String>() {
    
                        private static final long serialVersionUID = 1L;
    
                        @Override
                        public Tuple2<String, String> call(
                                Tuple2<String, Tuple2<String, Row>> tuple)
                                throws Exception {
                            String partAggrInfo = tuple._2._1;
                            Row userInfoRow = tuple._2._2;
                            
                            String sessionid = StringUtils.getFieldFromConcatString(
                                    partAggrInfo, "\|", Constants.FIELD_SESSION_ID);
                            
                            int age = userInfoRow.getInt(3);
                            String professional = userInfoRow.getString(4);
                            String city = userInfoRow.getString(5);
                            String sex = userInfoRow.getString(6);
                            
                            String fullAggrInfo = partAggrInfo + "|"
                                    + Constants.FIELD_AGE + "=" + age + "|"
                                    + Constants.FIELD_PROFESSIONAL + "=" + professional + "|"
                                    + Constants.FIELD_CITY + "=" + city + "|"
                                    + Constants.FIELD_SEX + "=" + sex;
                            
                            return new Tuple2<String, String>(sessionid, fullAggrInfo);
                        }
                        
                    });
  • 相关阅读:
    【转】为什么要报考系统架构设计师考试
    前端三大主流框架中文文档
    零散知识点-类的区别;函数式编程的简单总结;
    window.location相关方法
    Hybrid相关
    php中file_get_contents与curl的区别
    三级下拉菜单
    微信生成带参数二维码及响应操作
    开发中因长时间不用而遗忘的,持续补充中。。
    项目中用到的几个工具函数
  • 原文地址:https://www.cnblogs.com/gentle-awen/p/10144893.html
Copyright © 2020-2023  润新知