用户留存模型

– 数据准备(这里应该是分区表，每个分区存放当天活跃用户id，为图方便放在了一个表里)

– 创建hive表

CREATE TABLE `active`(
  `id` string,
  `ds` string)
ROW FORMAT SERDE
  'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
WITH SERDEPROPERTIES (
  'field.delim'='\t')
STORED AS INPUTFORMAT
  'org.apache.hadoop.mapred.TextInputFormat'
OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'

– 加载数据

load data local inpath './active.dat' into table active;

– 设计留存表

CREATE TABLE `user_left_info_day`(
  `ds` string,
  `liucun_map` map<string,string>)
ROW FORMAT SERDE
  'org.apache.hadoop.hive.serde2.lazy.