离线数仓DWD层

已于 2024-09-15 22:37:03 修改
阅读量386 收藏 9
点赞数 5
分类专栏： XM2-离线数仓-金融零售 文章标签： 数据仓库
于 2024-09-15 21:02:18 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.youkuaiyun.com/qq_45972323/article/details/137091085
版权

离线数仓DWD层

DWD层设计要点：

（1）DWD层的设计依据是维度建模理论，该层存储维度模型的事实表。
（2）DWD层的数据存储格式为orc列式存储+snappy压缩。
（3）DWD层表名的命名规范为dwd_数据域_表名_单分区增量全量标识（inc/full）

9.1 交易域加购事务事实表

1）建表语句

DROP TABLE IF EXISTS dwd_trade_cart_add_inc;
CREATE EXTERNAL TABLE dwd_trade_cart_add_inc
(
    `id`               STRING COMMENT '编号',
    `user_id`          STRING COMMENT '用户id',
    `sku_id`           STRING COMMENT '商品id',
    `date_id`          STRING COMMENT '时间id',
    `create_time`      STRING COMMENT '加购时间',
    `source_id`        STRING COMMENT '来源类型ID',
    `source_type_code` STRING COMMENT '来源类型编码',
    `source_type_name` STRING COMMENT '来源类型名称',
    `sku_num`          BIGINT COMMENT '加购物车件数'
) COMMENT '交易域加购物车事务事实表'
    PARTITIONED BY (`dt` STRING)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
    STORED AS ORC
    LOCATION '/warehouse/gmall/dwd/dwd_trade_cart_add_inc/'
    TBLPROPERTIES ('orc.compress' = 'snappy');

2）分区规划
在这里插入图片描述
3）数据装载
（1）数据流向
在这里插入图片描述

（2）首日装载

set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table dwd_trade_cart_add_inc partition (dt)
select
    id,
    user_id,
    sku_id,
    date_format(create_time,'yyyy-MM-dd') date_id,
    create_time,
    source_id,
    source_type,
    dic.dic_name,
    sku_num,
    date_format(create_time, 'yyyy-MM-dd')
from
(
    select
        data.id,
        data.user_id,
        data.sku_id,
        data.create_time,
        data.source_id,
        data.source_type,
        data.sku_num
    from ods_cart_info_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
)ci
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-14'
    and parent_code='24'
)dic
on ci.source_type=dic.dic_code;

（3）每日装载

insert overwrite table dwd_trade_cart_add_inc partition(dt='2020-06-15')
select
    id,
    user_id,
    sku_id,
    date_id,
    create_time,
    source_id,
    source_type_code,
    source_type_name,
    sku_num
from
(
    select
        data.id,
        data.user_id,
        data.sku_id,
        date_format(from_utc_timestamp(ts*1000,'GMT+8'),'yyyy-MM-dd') date_id,
        date_format(from_utc_timestamp(ts*1000,'GMT+8'),'yyyy-MM-dd HH:mm:ss') create_time,
        data.source_id,
        data.source_type source_type_code,
        if(type='insert',data.sku_num,data.sku_num-old['sku_num']) sku_num
    from ods_cart_info_inc
    where dt='2020-06-15'
    and (type='insert'
    or(type='update' and old['sku_num'] is not null and data.sku_num>cast(old['sku_num'] as int)))
)cart
left join
(
    select
        dic_code,
        dic_name source_type_name
    from ods_base_dic_full
    where dt='2020-06-15'
    and parent_code='24'
)dic
on cart.source_type_code=dic.dic_code;

9.2 交易域下单事务事实表

1）建表语句

DROP TABLE IF EXISTS dwd_trade_order_detail_inc;
CREATE EXTERNAL TABLE dwd_trade_order_detail_inc
(
    `id`                    STRING COMMENT '编号',
    `order_id`              STRING COMMENT '订单id',
    `user_id`               STRING COMMENT '用户id',
    `sku_id`                STRING COMMENT '商品id',
    `province_id`           STRING COMMENT '省份id',
    `activity_id`           STRING COMMENT '参与活动规则id',
    `activity_rule_id`      STRING COMMENT '参与活动规则id',
    `coupon_id`             STRING COMMENT '使用优惠券id',
    `date_id`               STRING COMMENT '下单日期id',
    `create_time`           STRING COMMENT '下单时间',
    `source_id`             STRING COMMENT '来源编号',
    `source_type_code`      STRING COMMENT '来源类型编码',
    `source_type_name`      STRING COMMENT '来源类型名称',
    `sku_num`               BIGINT COMMENT '商品数量',
    `split_original_amount` DECIMAL(16, 2) COMMENT '原始价格',
    `split_activity_amount` DECIMAL(16, 2) COMMENT '活动优惠分摊',
    `split_coupon_amount`   DECIMAL(16, 2) COMMENT '优惠券优惠分摊',
    `split_total_amount`    DECIMAL(16, 2) COMMENT '最终价格分摊'
) COMMENT '交易域下单明细事务事实表'
    PARTITIONED BY (`dt` STRING)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
    STORED AS ORC
    LOCATION '/warehouse/gmall/dwd/dwd_trade_order_detail_inc/'
    TBLPROPERTIES ('orc.compress' = 'snappy');

2）数据装载
（1）首日装载

set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table dwd_trade_order_detail_inc partition (dt)
select
    od.id,
    order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    date_format(create_time, 'yyyy-MM-dd') date_id,
    create_time,
    source_id,
    source_type,
    dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount,
    date_format(create_time,'yyyy-MM-dd')
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        data.create_time,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) od
left join
(
    select
        data.id,
        data.user_id,
        data.province_id
    from ods_order_info_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) oi
on od.order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-14'
    and parent_code='24'
)dic
on od.source_type=dic.dic_code;

（2）每日装载

insert overwrite table dwd_trade_order_detail_inc partition (dt='2020-06-15')
select
    od.id,
    order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    date_id,
    create_time,
    source_id,
    source_type,
    dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        date_format(data.create_time, 'yyyy-MM-dd') date_id,
        data.create_time,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where dt = '2020-06-15'
    and type = 'insert'
) od
left join
(
    select
        data.id,
        data.user_id,
        data.province_id
    from ods_order_info_inc
    where dt = '2020-06-15'
    and type = 'insert'
) oi
on od.order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where dt = '2020-06-15'
    and type = 'insert'
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where dt = '2020-06-15'
    and type = 'insert'
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-15'
    and parent_code='24'
)dic
on od.source_type=dic.dic_code;

9.3 交易域取消订单事务事实表

1）建表语句

DROP TABLE IF EXISTS dwd_trade_cancel_detail_inc;
CREATE EXTERNAL TABLE dwd_trade_cancel_detail_inc
(
    `id`                    STRING COMMENT '编号',
    `order_id`              STRING COMMENT '订单id',
    `user_id`               STRING COMMENT '用户id',
    `sku_id`                STRING COMMENT '商品id',
    `province_id`           STRING COMMENT '省份id',
    `activity_id`           STRING COMMENT '参与活动规则id',
    `activity_rule_id`      STRING COMMENT '参与活动规则id',
    `coupon_id`             STRING COMMENT '使用优惠券id',
    `date_id`               STRING COMMENT '取消订单日期id',
    `cancel_time`           STRING COMMENT '取消订单时间',
    `source_id`             STRING COMMENT '来源编号',
    `source_type_code`      STRING COMMENT '来源类型编码',
    `source_type_name`      STRING COMMENT '来源类型名称',
    `sku_num`               BIGINT COMMENT '商品数量',
    `split_original_amount` DECIMAL(16, 2) COMMENT '原始价格',
    `split_activity_amount` DECIMAL(16, 2) COMMENT '活动优惠分摊',
    `split_coupon_amount`   DECIMAL(16, 2) COMMENT '优惠券优惠分摊',
    `split_total_amount`    DECIMAL(16, 2) COMMENT '最终价格分摊'
) COMMENT '交易域取消订单明细事务事实表'
    PARTITIONED BY (`dt` STRING)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
    STORED AS ORC
    LOCATION '/warehouse/gmall/dwd/dwd_trade_cancel_detail_inc/'
    TBLPROPERTIES ('orc.compress' = 'snappy');

2）数据装载
（1）首日装载

set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table dwd_trade_cancel_detail_inc partition (dt)
select
    od.id,
    order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    date_format(canel_time,'yyyy-MM-dd') date_id,
    canel_time,
    source_id,
    source_type,
    dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount,
    date_format(canel_time,'yyyy-MM-dd')
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) od
join
(
    select
        data.id,
        data.user_id,
        data.province_id,
        data.operate_time canel_time
    from ods_order_info_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
    and data.order_status='1003'
) oi
on od.order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-14'
    and parent_code='24'
)dic
on od.source_type=dic.dic_code;

（2）每日装载

insert overwrite table dwd_trade_cancel_detail_inc partition (dt='2020-06-15')
select
    od.id,
    order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    date_format(canel_time,'yyyy-MM-dd') date_id,
    canel_time,
    source_id,
    source_type,
    dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where (dt='2020-06-15' or dt=date_add('2020-06-15',-1))
    and (type = 'insert' or type= 'bootstrap-insert')
) od
join
(
    select
        data.id,
        data.user_id,
        data.province_id,
        data.operate_time canel_time
    from ods_order_info_inc
    where dt = '2020-06-15'
    and type = 'update'
    and data.order_status='1003'
    and array_contains(map_keys(old),'order_status')
) oi
on order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where (dt='2020-06-15' or dt=date_add('2020-06-15',-1))
    and (type = 'insert' or type= 'bootstrap-insert')
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where (dt='2020-06-15' or dt=date_add('2020-06-15',-1))
    and (type = 'insert' or type= 'bootstrap-insert')
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-15'
    and parent_code='24'
)dic
on od.source_type=dic.dic_code;

9.4 交易域支付成功事务事实表

1）建表语句

DROP TABLE IF EXISTS dwd_trade_pay_detail_suc_inc;
CREATE EXTERNAL TABLE dwd_trade_pay_detail_suc_inc
(
    `id`                    STRING COMMENT '编号',
    `order_id`              STRING COMMENT '订单id',
    `user_id`               STRING COMMENT '用户id',
    `sku_id`                STRING COMMENT '商品id',
    `province_id`           STRING COMMENT '省份id',
    `activity_id`           STRING COMMENT '参与活动规则id',
    `activity_rule_id`      STRING COMMENT '参与活动规则id',
    `coupon_id`             STRING COMMENT '使用优惠券id',
    `payment_type_code`     STRING COMMENT '支付类型编码',
    `payment_type_name`     STRING COMMENT '支付类型名称',
    `date_id`               STRING COMMENT '支付日期id',
    `callback_time`         STRING COMMENT '支付成功时间',
    `source_id`             STRING COMMENT '来源编号',
    `source_type_code`      STRING COMMENT '来源类型编码',
    `source_type_name`      STRING COMMENT '来源类型名称',
    `sku_num`               BIGINT COMMENT '商品数量',
    `split_original_amount` DECIMAL(16, 2) COMMENT '应支付原始金额',
    `split_activity_amount` DECIMAL(16, 2) COMMENT '支付活动优惠分摊',
    `split_coupon_amount`   DECIMAL(16, 2) COMMENT '支付优惠券优惠分摊',
    `split_payment_amount`  DECIMAL(16, 2) COMMENT '支付金额'
) COMMENT '交易域成功支付事务事实表'
    PARTITIONED BY (`dt` STRING)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
    STORED AS ORC
    LOCATION '/warehouse/gmall/dwd/dwd_trade_pay_detail_suc_inc/'
    TBLPROPERTIES ('orc.compress' = 'snappy');

2）数据装载
（1）首日装载

insert overwrite table dwd_trade_pay_detail_suc_inc partition (dt)
select
    od.id,
    od.order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    payment_type,
    pay_dic.dic_name,
    date_format(callback_time,'yyyy-MM-dd') date_id,
    callback_time,
    source_id,
    source_type,
    src_dic.dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount,
    date_format(callback_time,'yyyy-MM-dd')
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) od
join
(
    select
        data.user_id,
        data.order_id,
        data.payment_type,
        data.callback_time
    from ods_payment_info_inc
    where dt='2020-06-14'
    and type='bootstrap-insert'
    and data.payment_status='1602'
) pi
on od.order_id=pi.order_id
left join
(
    select
        data.id,
        data.province_id
    from ods_order_info_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) oi
on od.order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where dt = '2020-06-14'
    and type = 'bootstrap-insert'
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-14'
    and parent_code='11'
) pay_dic
on pi.payment_type=pay_dic.dic_code
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-14'
    and parent_code='24'
)src_dic
on od.source_type=src_dic.dic_code;

（2）每日装载

insert overwrite table dwd_trade_pay_detail_suc_inc partition (dt='2020-06-15')
select
    od.id,
    od.order_id,
    user_id,
    sku_id,
    province_id,
    activity_id,
    activity_rule_id,
    coupon_id,
    payment_type,
    pay_dic.dic_name,
    date_format(callback_time,'yyyy-MM-dd') date_id,
    callback_time,
    source_id,
    source_type,
    src_dic.dic_name,
    sku_num,
    split_original_amount,
    split_activity_amount,
    split_coupon_amount,
    split_total_amount
from
(
    select
        data.id,
        data.order_id,
        data.sku_id,
        data.source_id,
        data.source_type,
        data.sku_num,
        data.sku_num * data.order_price split_original_amount,
        data.split_total_amount,
        data.split_activity_amount,
        data.split_coupon_amount
    from ods_order_detail_inc
    where (dt = '2020-06-15' or dt = date_add('2020-06-15',-1))
    and (type = 'insert' or type = 'bootstrap-insert')
) od
join
(
    select
        data.user_id,
        data.order_id,
        data.payment_type,
        data.callback_time
    from ods_payment_info_inc
    where dt='2020-06-15'
    and type='update'
    and array_contains(map_keys(old),'payment_status')
    and data.payment_status='1602'
) pi
on od.order_id=pi.order_id
left join
(
    select
        data.id,
        data.province_id
    from ods_order_info_inc
    where (dt = '2020-06-15' or dt = date_add('2020-06-15',-1))
    and (type = 'insert' or type = 'bootstrap-insert')
) oi
on od.order_id = oi.id
left join
(
    select
        data.order_detail_id,
        data.activity_id,
        data.activity_rule_id
    from ods_order_detail_activity_inc
    where (dt = '2020-06-15' or dt = date_add('2020-06-15',-1))
    and (type = 'insert' or type = 'bootstrap-insert')
) act
on od.id = act.order_detail_id
left join
(
    select
        data.order_detail_id,
        data.coupon_id
    from ods_order_detail_coupon_inc
    where (dt = '2020-06-15' or dt = date_add('2020-06-15',-1))
    and (type = 'insert' or type = 'bootstrap-insert')
) cou
on od.id = cou.order_detail_id
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-15'
    and parent_code='11'
) pay_dic
on pi.payment_type=pay_dic.dic_code
left join
(
    select
        dic_code,
        dic_name
    from ods_base_dic_full
    where dt='2020-06-15'
    and parent_code='24'
)src_dic
on od.source_type=src_dic.dic_code;

9.5 交易域退单事务事实表

1）建表语句

DROP TABLE IF EXISTS dwd_trade_order_refund_inc;
CREATE EXTERNAL TABLE dwd_trade_order_refund_inc
(
    `id`                      STRING COMMENT '编号',
    `user_id`                 STRING COMMENT '用户ID',
    `order_id`                STRING COMMENT '订单ID',
    `sku_id`                  STRING COMMENT '商品ID',
    `province_id`             STRING COMMENT '地区ID',
    `date_id`                 STRING COMMENT '日期ID',
    `create_time`             STRING COMMENT '退单时间',
    `refund_type_code`        STRING COMMENT '退单类型编码',
    `refund_type_name`        STRING COMMENT '退单类型名称',
    `refund_reason_type_code` STRING COMMENT '退单原因类型编码',
    `refund_reason_type_name` STRING COMMENT '退单原因类型名称',
    `refund_reason_txt`       STRING COMMENT '退单原因描述',
    `refund_num`              BIGINT COMMENT '退单件数',
    `refund_amount`           DECIMAL(
最低0.47元/天 解锁文章
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值