01：油站维度设计

• 目标：掌握油站维度的需求与设计

• 路径

  • step1：需求
  • step2：设计

• 实施

  • 需求：构建油站维度表，得到油站id、油站名称、油站所属的地理区域、所属公司、油站状态等

    

  • 设计

    • 数据来源

      • ciss_base_oilstation：油站信息表

        select
            id, name, code,
            customer_id, customer_name,
            province, city, region, township,
            status, customer_classify, dt
        from one_make_dwd.ciss_base_oilstation
        where id != '' and name is not null and name != 'null' and customer_id is not null;
        

      • eos_dict_type：字典状态类别表，记录所有需要使用字典标记的表

        select * from eos_dict_type where dicttypename = '油站状态';
        

      • eos_dict_entry：字典状态明细表，记录所有具体的状态或者类别信息

        select * from eos_dict_entry where dicttypeid = 'BUSS_OILSTATION_STATUS';
        

      • ciss_base_baseinfo：客户公司信息表【公司ID、公司名称】

        select ygcode, companyname from one_make_dwd.ciss_base_baseinfo group by ygcode, companyname;
        

        • 数据有重复，做个去重

      • ciss_base_customer：客户信息表【客户id、客户省份名称、所属公司ID】

        select code, province, company from one_make_dwd.ciss_base_customer;
        

      • ciss_base_areas：行政地区信息表

        • 通过具体的id关联所有地区信息

    • 实现设计

      • 所有表按照对应字段关联，获取对应的属性字段

• 小结

  • 掌握油站维度的需求与设计

02：油站维度构建

• 目标：实现油站维度的构建

• 实施

  • 建维度表

    -- 创建油站维度表
    create external table if not exists one_make_dws.dim_oilstation(
        id string comment '油站ID'
        , name string comment '油站名称'
        , code string comment '油站编码'
        , customer_id string comment '客户ID'
        , customer_name string comment '客户名称'
        , province_id int comment '省份id'
        , province_name string comment '省份名称'
        , city_id int comment '城市id'
        , city_name string comment '城市名称'
        , county_id int comment '县城ID'
        , county_name string comment '县城名称'
        , area_id int comment '区域id'
        , area_name string comment '区域名称'
        , customer_classify_id string comment '客户分类ID'
        , customer_classify_name string comment '客户分类名称'
        , status int comment '油站状态（1、2）'
        , status_name string comment '油站状态名（正常、停用）'
        , company_id int comment '所属公司ID'
        , company_name string comment '所属公司名称'
        , customer_province_id int comment '客户所属省份ID'
        , customer_province_name string comment '客户所属省份'
    ) COMMENT '油站维度表'
    PARTITIONED BY (dt STRING)
    STORED AS TEXTFILE
    LOCATION '/data/dw/dws/one_make/dim_oilstation';
    

  • 抽取数据

    insert overwrite table one_make_dws.dim_oilstation partition (dt ='20210101')
    select oil.id, oil.name, oil.code, customer_id, customer_name
           , oil.province province_id, p.areaname province_name
           , oil.city city_id, c.areaname city_name
           , oil.region county_id, county.areaname county_name
           , oil.township area_id, a.areaname area_name
           , oil.customer_classify customer_classify_id, ede.dictname customer_classify_name
           , oil.status status, eosde.dictname status_name
           , cbc.company company_id, binfo.companyname company_name
           , proname.id customer_province_id, proname.areaname customer_province_name
    from (
         select id, name, code, customer_id, customer_name, province, city, region, township, status, customer_classify, dt
         from one_make_dwd.ciss_base_oilstation where id != '' and name is not null and name != 'null' and customer_id is not null
    	 ) oil
         left join (select id, areaname, parentid from one_make_dwd.ciss_base_areas where rank = 1) p on oil.province = p.id
         left join (select id, areaname, parentid from one_make_dwd.ciss_base_areas where rank = 2) c on oil.city = c.id
         left join (select id, areaname, parentid from one_make_dwd.ciss_base_areas where rank = 3) county on oil.region = county.id
         left join (select id, areaname, parentid from one_make_dwd.ciss_base_areas where rank = 4) a on oil.township = a.id
         left join (select dictid, dictname  from one_make_dwd.eos_dict_entry) ede on oil.customer_classify = ede.dictid
         left join (select dictid, dictname from one_make_dwd.eos_dict_entry t1  left join one_make_dwd.eos_dict_type t2 on t1.dicttypeid = t2.dicttypeid where t2.dicttypename = '油站状态') eosde on oil.status = eosde.dictid
         -- 客户所属公司id，所属公司名称，所属省份id，所属省份名称
         left join (select code, province, company from one_make_dwd.ciss_base_customer) cbc on oil.customer_id = cbc.code
         left join (select id, areaname from one_make_dwd.ciss_base_areas where rank = 1 and id != 83) proname on cbc.province = proname.areaname
         left join (select ygcode, companyname from one_make_dwd.ciss_base_baseinfo group by ygcode, companyname) binfo on cbc.company = binfo.ygcode where dt = '20210101';
    

  • 查看结果

    

• 小结

  • 实现油站维度的构建