35-学习笔记尚硅谷数仓搭建-DWS层最近n日汇总表及历史至今汇总表建表语句

目录

一、交易域用户商品粒度订单最近n日汇总表

二、交易域省份粒度订单最近n日汇总表

三、交易域用户粒度订单历史至今汇总表

四、用户域用户粒度登录历史至今汇总表

---

一、交易域用户商品粒度订单最近n日汇总表

建表语句

DROP TABLE IF EXISTS dws_trade_user_sku_order_nd;
CREATE EXTERNAL TABLE dws_trade_user_sku_order_nd
(
    `user_id`                     STRING COMMENT '用户ID',
    `sku_id`                      STRING COMMENT 'SKU_ID',
    `sku_name`                    STRING COMMENT 'SKU名称',
    `category1_id`               STRING COMMENT '一级品类ID',
    `category1_name`             STRING COMMENT '一级品类名称',
    `category2_id`               STRING COMMENT '二级品类ID',
    `category2_name`             STRING COMMENT '二级品类名称',
    `category3_id`               STRING COMMENT '三级品类ID',
    `category3_name`             STRING COMMENT '三级品类名称',
    `tm_id`                       STRING COMMENT '品牌ID',
    `tm_name`                     STRING COMMENT '品牌名称',
    `order_count_7d`             STRING COMMENT '最近7日下单次数',
    `order_num_7d`               BIGINT COMMENT '最近7日下单件数',
    `order_original_amount_7d`   DECIMAL(16, 2) COMMENT '最近7日下单原始金额',
    `activity_reduce_amount_7d`  DECIMAL(16, 2) COMMENT '最近7日活动优惠金额',
    `coupon_reduce_amount_7d`    DECIMAL(16, 2) COMMENT '最近7日优惠券优惠金额',
    `order_total_amount_7d`      DECIMAL(16, 2) COMMENT '最近7日下单最终金额',
    `order_count_30d`            BIGINT COMMENT '最近30日下单次数',
    `order_num_30d`              BIGINT COMMENT '最近30日下单件数',
    `order_original_amount_30d`  DECIMAL(16, 2) COMMENT '最近30日下单原始金额',
    `activity_reduce_amount_30d` DECIMAL(16, 2) COMMENT '最近30日活动优惠金额',
    `coupon_reduce_amount_30d`   DECIMAL(16, 2) COMMENT '最近30日优惠券优惠金额',
    `order_total_amount_30d`     DECIMAL(16, 2) COMMENT '最近30日下单最终金额'
) COMMENT '交易域用户商品粒度订单最近n日汇总表'
    PARTITIONED BY (`dt` STRING)
    STORED AS ORC
    LOCATION '/warehouse/gmall/dws/dws_trade_user_sku_order_nd'
    TBLPROPERTIES ('orc.compress' = 'snappy');

数据装载

insert overwrite table dws_trade_user_sku_order_nd partition(dt='2022-06-08')
select
    user_id,
    sku_id,
    sku_name,
    category1_id,
    category1_name,
    category2_id,
    category2_name,
    category3_id,
    category3_name,
    tm_id,
    tm_name,
    sum(if(dt>=date_add('2022-06-08',-6),order_count_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),order_num_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),order_original_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),activity_reduce_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),coupon_reduce_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),order_total_amount_1d,0)),
    sum(order_count_1d),
    sum(order_num_1d),
    sum(order_original_amount_1d),
    sum(activity_reduce_amount_1d),
    sum(coupon_reduce_amount_1d),
    sum(order_total_amount_1d)
from dws_trade_user_sku_order_1d
where dt>=date_add('2022-06-08',-29)
group by  user_id,sku_id,sku_name,category1_id,category1_name,category2_id,category2_name,category3_id,category3_name,tm_id,tm_name;

二、交易域省份粒度订单最近n日汇总表

建表语句

DROP TABLE IF EXISTS dws_trade_province_order_nd;
CREATE EXTERNAL TABLE dws_trade_province_order_nd
(
    `province_id`                STRING COMMENT '省份ID',
    `province_name`              STRING COMMENT '省份名称',
    `area_code`                  STRING COMMENT '地区编码',
    `iso_code`                   STRING COMMENT '旧版国际标准地区编码',
    `iso_3166_2`                 STRING COMMENT '新版国际标准地区编码',
    `order_count_7d`             BIGINT COMMENT '最近7日下单次数',
    `order_original_amount_7d`   DECIMAL(16, 2) COMMENT '最近7日下单原始金额',
    `activity_reduce_amount_7d`  DECIMAL(16, 2) COMMENT '最近7日下单活动优惠金额',
    `coupon_reduce_amount_7d`    DECIMAL(16, 2) COMMENT '最近7日下单优惠券优惠金额',
    `order_total_amount_7d`      DECIMAL(16, 2) COMMENT '最近7日下单最终金额',
    `order_count_30d`            BIGINT COMMENT '最近30日下单次数',
    `order_original_amount_30d`  DECIMAL(16, 2) COMMENT '最近30日下单原始金额',
    `activity_reduce_amount_30d` DECIMAL(16, 2) COMMENT '最近30日下单活动优惠金额',
    `coupon_reduce_amount_30d`   DECIMAL(16, 2) COMMENT '最近30日下单优惠券优惠金额',
    `order_total_amount_30d`     DECIMAL(16, 2) COMMENT '最近30日下单最终金额'
) COMMENT '交易域省份粒度订单最近n日汇总表'
    PARTITIONED BY (`dt` STRING)
    STORED AS ORC
    LOCATION '/warehouse/gmall/dws/dws_trade_province_order_nd'
    TBLPROPERTIES ('orc.compress' = 'snappy');

数据装载

insert overwrite table dws_trade_province_order_nd partition(dt='2022-06-08')
select
    province_id,
    province_name,
    area_code,
    iso_code,
    iso_3166_2,
    sum(if(dt>=date_add('2022-06-08',-6),order_count_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),order_original_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),activity_reduce_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),coupon_reduce_amount_1d,0)),
    sum(if(dt>=date_add('2022-06-08',-6),order_total_amount_1d,0)),
    sum(order_count_1d),
    sum(order_original_amount_1d),
    sum(activity_reduce_amount_1d),
    sum(coupon_reduce_amount_1d),
    sum(order_total_amount_1d)
from dws_trade_province_order_1d
where dt>=date_add('2022-06-08',-29)
and dt<='2022-06-08'
group by province_id,province_name,area_code,iso_code,iso_3166_2;

三、交易域用户粒度订单历史至今汇总表

建表语句

DROP TABLE IF EXISTS dws_trade_user_order_td;
CREATE EXTERNAL TABLE dws_trade_user_order_td
(
    `user_id`                   STRING COMMENT '用户ID',
    `order_date_first`          STRING COMMENT '历史至今首次下单日期',
    `order_date_last`           STRING COMMENT '历史至今末次下单日期',
    `order_count_td`            BIGINT COMMENT '历史至今下单次数',
    `order_num_td`              BIGINT COMMENT '历史至今购买商品件数',
    `original_amount_td`        DECIMAL(16, 2) COMMENT '历史至今下单原始金额',
    `activity_reduce_amount_td` DECIMAL(16, 2) COMMENT '历史至今下单活动优惠金额',
    `coupon_reduce_amount_td`   DECIMAL(16, 2) COMMENT '历史至今下单优惠券优惠金额',
    `total_amount_td`           DECIMAL(16, 2) COMMENT '历史至今下单最终金额'
) COMMENT '交易域用户粒度订单历史至今汇总表'
    PARTITIONED BY (`dt` STRING)
    STORED AS ORC
    LOCATION '/warehouse/gmall/dws/dws_trade_user_order_td'
    TBLPROPERTIES ('orc.compress' = 'snappy');

首日数据装载

insert overwrite table dws_trade_user_order_td partition(dt='2022-06-08')
select
    user_id,
    min(dt) order_date_first,
    max(dt) order_date_last,
    sum(order_count_1d) order_count,
    sum(order_num_1d) order_num,
    sum(order_original_amount_1d) original_amount,
    sum(activity_reduce_amount_1d) activity_reduce_amount,
    sum(coupon_reduce_amount_1d) coupon_reduce_amount,
    sum(order_total_amount_1d) total_amount
from dws_trade_user_order_1d
group by user_id;

每日数据装载（方法一）

insert overwrite table dws_trade_user_order_td partition (dt = '2022-06-09')
select nvl(old.user_id, new.user_id),
       if(old.user_id is not null, old.order_date_first, '2022-06-09'),
       if(new.user_id is not null, '2022-06-09', old.order_date_last),
       nvl(old.order_count_td, 0) + nvl(new.order_count_1d, 0),
       nvl(old.order_num_td, 0) + nvl(new.order_num_1d, 0),
       nvl(old.original_amount_td, 0) + nvl(new.order_original_amount_1d, 0),
       nvl(old.activity_reduce_amount_td, 0) + nvl(new.activity_reduce_amount_1d, 0),
       nvl(old.coupon_reduce_amount_td, 0) + nvl(new.coupon_reduce_amount_1d, 0),
       nvl(old.total_amount_td, 0) + nvl(new.order_total_amount_1d, 0)
from (
         select user_id,
                order_date_first,
                order_date_last,
                order_count_td,
                order_num_td,
                original_amount_td,
                activity_reduce_amount_td,
                coupon_reduce_amount_td,
                total_amount_td
         from dws_trade_user_order_td
         where dt = date_add('2022-06-09', -1)
     ) old
         full outer join
     (
         select user_id,
                order_count_1d,
                order_num_1d,
                order_original_amount_1d,
                activity_reduce_amount_1d,
                coupon_reduce_amount_1d,
                order_total_amount_1d
         from dws_trade_user_order_1d
         where dt = '2022-06-09'
     ) new
     on old.user_id = new.user_id;

每日数据装载（方法二）

insert overwrite table dws_trade_user_order_td partition(dt='2022-06-09')
select user_id,
       min(order_date_first)          order_date_first,
       max(order_date_last)           order_date_last,
       sum(order_count_td)            order_count_td,
       sum(order_num_td)              order_num_td,
       sum(original_amount_td)        original_amount_td,
       sum(activity_reduce_amount_td) activity_reduce_amount_td,
       sum(coupon_reduce_amount_td)   coupon_reduce_amount_td,
       sum(total_amount_td)           total_amount_td
from (
         select user_id,
                order_date_first,
                order_date_last,
                order_count_td,
                order_num_td,
                original_amount_td,
                activity_reduce_amount_td,
                coupon_reduce_amount_td,
                total_amount_td
         from dws_trade_user_order_td
         where dt = date_add('2022-06-09', -1)
         union all
         select user_id,
                '2022-06-09' order_date_first,
                '2022-06-09' order_date_last,
                order_count_1d,
                order_num_1d,
                order_original_amount_1d,
                activity_reduce_amount_1d,
                coupon_reduce_amount_1d,
                order_total_amount_1d
         from dws_trade_user_order_1d
         where dt = '2022-06-09') t1
group by user_id;

四、用户域用户粒度登录历史至今汇总表

建表语句

DROP TABLE IF EXISTS dws_user_user_login_td;
CREATE EXTERNAL TABLE dws_user_user_login_td
(
    `user_id`          STRING COMMENT '用户ID',
    `login_date_last`  STRING COMMENT '历史至今末次登录日期',
    `login_date_first` STRING COMMENT '历史至今首次登录日期',
    `login_count_td`   BIGINT COMMENT '历史至今累计登录次数'
) COMMENT '用户域用户粒度登录历史至今汇总表'
    PARTITIONED BY (`dt` STRING)
    STORED AS ORC
    LOCATION '/warehouse/gmall/dws/dws_user_user_login_td'
    TBLPROPERTIES ('orc.compress' = 'snappy');

首日数据装载

insert overwrite table dws_user_user_login_td partition (dt = '2022-06-08')
select u.id                                                         user_id,
       nvl(login_date_last, date_format(create_time, 'yyyy-MM-dd')) login_date_last,
       date_format(create_time, 'yyyy-MM-dd')                       login_date_first,
       nvl(login_count_td, 1)                                       login_count_td
from (
         select id,
                create_time
         from dim_user_zip
         where dt = '9999-12-31'
     ) u
         left join
     (
         select user_id,
                max(dt)  login_date_last,
                count(*) login_count_td
         from dwd_user_login_inc
         group by user_id
     ) l
     on u.id = l.user_id;

每日数据装载

insert overwrite table dws_user_user_login_td partition (dt = '2022-06-09')
select nvl(old.user_id, new.user_id)                                        user_id,
       if(new.user_id is null, old.login_date_last, '2022-06-09')           login_date_last,
       if(old.login_date_first is null, '2022-06-09', old.login_date_first) login_date_first,
       nvl(old.login_count_td, 0) + nvl(new.login_count_1d, 0)              login_count_td
from (
         select user_id,
                login_date_last,
                login_date_first,
                login_count_td
         from dws_user_user_login_td
         where dt = date_add('2022-06-09', -1)
     ) old
         full outer join
     (
         select user_id,
                count(*) login_count_1d
         from dwd_user_login_inc
         where dt = '2022-06-09'
         group by user_id
     ) new
     on old.user_id = new.user_id;