离线数仓搭建_12_DWD层业务数据创建

Posted 2022-09-28 Fang GL

文章目录

• • 13.2 DWD层（业务数据）
  • • 13.2.1 评价事实表（事务型事实表）
    • 13.2.2 订单明细事实表（事务型事实表）
    • 13.2.3 退单事实表（事务型事实表）
    • 13.2.4 加购事实表（周期型快照事实表，每日快照）
    • 13.2.5 收藏事实表（周期型快照事实表，每日快照）
    • 13.2.6 优惠券领用事实表（累积型快照事实表）
    • 13.2.7 支付事实表（累积型快照事实表）
    • 13.2.8 退款事实表（累积型快照事实表）
    • 13.2.9 订单事实表（累积型快照事实表）
    • 13.2.10 DWD层业务数据首日装载脚本
    • 13.2.11 DWD层业务数据每日装载脚本

上文访问：离线数仓搭建_11_DWD层用户行为日志创建
下文访问：尽请期待！

13.2 DWD层（业务数据）

13.2.1 评价事实表（事务型事实表）

1）建表语句

DROP TABLE IF EXISTS dwd_comment_info;
CREATE EXTERNAL TABLE dwd_comment_info(
    `id` STRING COMMENT '编号',
    `user_id` STRING COMMENT '用户ID',
    `sku_id` STRING COMMENT '商品sku',
    `spu_id` STRING COMMENT '商品spu',
    `order_id` STRING COMMENT '订单ID',
    `appraise` STRING COMMENT '评价(好评、中评、差评、默认评价)',
    `create_time` STRING COMMENT '评价时间'
) COMMENT '评价事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_comment_info/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_comment_info partition (dt)
select
    id,
    user_id,
    sku_id,
    spu_id,
    order_id,
    appraise,
    create_time,
    date_format(create_time,'yyyy-MM-dd')
from ods_comment_info
where dt='2020-06-14';

（2）每日装载

insert overwrite table dwd_comment_info partition(dt='2020-06-15')
select
    id,
    user_id,
    sku_id,
    spu_id,
    order_id,
    appraise,
    create_time
from ods_comment_info where dt='2020-06-15';

13.2.2 订单明细事实表（事务型事实表）

1）建表语句

DROP TABLE IF EXISTS dwd_order_detail;
CREATE EXTERNAL TABLE dwd_order_detail (
    `id` STRING COMMENT '订单编号',
    `order_id` STRING COMMENT '订单号',
    `user_id` STRING COMMENT '用户id',
    `sku_id` STRING COMMENT 'sku商品id',
    `province_id` STRING COMMENT '省份ID',
    `activity_id` STRING COMMENT '活动ID',
    `activity_rule_id` STRING COMMENT '活动规则ID',
    `coupon_id` STRING COMMENT '优惠券ID',
    `create_time` STRING COMMENT '创建时间',
    `source_type` STRING COMMENT '来源类型',
    `source_id` STRING COMMENT '来源编号',
    `sku_num` BIGINT COMMENT '商品数量',
    `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_final_amount` DECIMAL(16,2) COMMENT '最终价格分摊'
) COMMENT '订单明细事实表表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_order_detail/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

（1）首日装载

insert overwrite table dwd_order_detail partition(dt)
select
    od.id,
    od.order_id,
    oi.user_id,
    od.sku_id,
    oi.province_id,
    oda.activity_id,
    oda.activity_rule_id,
    odc.coupon_id,
    od.create_time,
    od.source_type,
    od.source_id,
    od.sku_num,
    od.order_price*od.sku_num,
    od.split_activity_amount,
    od.split_coupon_amount,
    od.split_final_amount,
    date_format(create_time,'yyyy-MM-dd')
from
(
    select
        *
    from ods_order_detail
    where dt='2020-06-14'
)od
left join
(
    select
        id,
        user_id,
        province_id
    from ods_order_info
    where dt='2020-06-14'
)oi
on od.order_id=oi.id
left join
(
    select
        order_detail_id,
        activity_id,
        activity_rule_id
    from ods_order_detail_activity
    where dt='2020-06-14'
)oda
on od.id=oda.order_detail_id
left join
(
    select
        order_detail_id,
        coupon_id
    from ods_order_detail_coupon
    where dt='2020-06-14'
)odc
on od.id=odc.order_detail_id;

（2）每日装载

insert overwrite table dwd_order_detail partition(dt='2020-06-15')
select
    od.id,
    od.order_id,
    oi.user_id,
    od.sku_id,
    oi.province_id,
    oda.activity_id,
    oda.activity_rule_id,
    odc.coupon_id,
    od.create_time,
    od.source_type,
    od.source_id,
    od.sku_num,
    od.order_price*od.sku_num,
    od.split_activity_amount,
    od.split_coupon_amount,
    od.split_final_amount
from
(
    select
        *
    from ods_order_detail
    where dt='2020-06-15'
)od
left join
(
    select
        id,
        user_id,
        province_id
    from ods_order_info
    where dt='2020-06-15'
)oi
on od.order_id=oi.id
left join
(
    select
        order_detail_id,
        activity_id,
        activity_rule_id
    from ods_order_detail_activity
    where dt='2020-06-15'
)oda
on od.id=oda.order_detail_id
left join
(
    select
        order_detail_id,
        coupon_id
    from ods_order_detail_coupon
    where dt='2020-06-15'
)odc
on od.id=odc.order_detail_id;

13.2.3 退单事实表（事务型事实表）

1）建表语句

DROP TABLE IF EXISTS dwd_order_refund_info;
CREATE EXTERNAL TABLE dwd_order_refund_info(
    `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',
    `refund_type` STRING COMMENT '退单类型',
    `refund_num` BIGINT COMMENT '退单件数',
    `refund_amount` DECIMAL(16,2) COMMENT '退单金额',
    `refund_reason_type` STRING COMMENT '退单原因类型',
    `create_time` STRING COMMENT '退单时间'
) COMMENT '退单事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_order_refund_info/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_order_refund_info partition(dt)
select
    ri.id,
    ri.user_id,
    ri.order_id,
    ri.sku_id,
    oi.province_id,
    ri.refund_type,
    ri.refund_num,
    ri.refund_amount,
    ri.refund_reason_type,
    ri.create_time,
    date_format(ri.create_time,'yyyy-MM-dd')
from
(
    select * from ods_order_refund_info where dt='2020-06-14'
)ri
left join
(
    select id,province_id from ods_order_info where dt='2020-06-14'
)oi
on ri.order_id=oi.id;

（2）每日装载

insert overwrite table dwd_order_refund_info partition(dt='2020-06-15')
select
    ri.id,
    ri.user_id,
    ri.order_id,
    ri.sku_id,
    oi.province_id,
    ri.refund_type,
    ri.refund_num,
    ri.refund_amount,
    ri.refund_reason_type,
    ri.create_time
from
(
    select * from ods_order_refund_info where dt='2020-06-15'
)ri
left join
(
    select id,province_id from ods_order_info where dt='2020-06-15'
)oi
on ri.order_id=oi.id;

3）查询加载结果

13.2.4 加购事实表（周期型快照事实表，每日快照）

1）建表语句

DROP TABLE IF EXISTS dwd_cart_info;
CREATE EXTERNAL TABLE dwd_cart_info(
    `id` STRING COMMENT '编号',
    `user_id` STRING COMMENT '用户ID',
    `sku_id` STRING COMMENT '商品ID',
    `source_type` STRING COMMENT '来源类型',
    `source_id` STRING COMMENT '来源编号',
    `cart_price` DECIMAL(16,2) COMMENT '加入购物车时的价格',
    `is_ordered` STRING COMMENT '是否已下单',
    `create_time` STRING COMMENT '创建时间',
    `operate_time` STRING COMMENT '修改时间',
    `order_time` STRING COMMENT '下单时间',
    `sku_num` BIGINT COMMENT '加购数量'
) COMMENT '加购事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_cart_info/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_cart_info partition(dt='2020-06-14')
select
    id,
    user_id,
    sku_id,
    source_type,
    source_id,
    cart_price,
    is_ordered,
    create_time,
    operate_time,
    order_time,
    sku_num
from ods_cart_info
where dt='2020-06-14';

（2）每日装载

insert overwrite table dwd_cart_info partition(dt='2020-06-15')
select
    id,
    user_id,
    sku_id,
    source_type,
    source_id,
    cart_price,
    is_ordered,
    create_time,
    operate_time,
    order_time,
    sku_num
from ods_cart_info
where dt='2020-06-15';

13.2.5 收藏事实表（周期型快照事实表，每日快照）

1）建表语句

DROP TABLE IF EXISTS dwd_favor_info;
CREATE EXTERNAL TABLE dwd_favor_info(
    `id` STRING COMMENT '编号',
    `user_id` STRING  COMMENT '用户id',
    `sku_id` STRING  COMMENT 'skuid',
    `spu_id` STRING  COMMENT 'spuid',
    `is_cancel` STRING  COMMENT '是否取消',
    `create_time` STRING  COMMENT '收藏时间',
    `cancel_time` STRING  COMMENT '取消时间'
) COMMENT '收藏事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_favor_info/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_favor_info partition(dt='2020-06-14')
select
    id,
    user_id,
    sku_id,
    spu_id,
    is_cancel,
    create_time,
    cancel_time
from ods_favor_info
where dt='2020-06-14';

（2）每日装载

insert overwrite table dwd_favor_info partition(dt='2020-06-15')
select
    id,
    user_id,
    sku_id,
    spu_id,
    is_cancel,
    create_time,
    cancel_time
from ods_favor_info
where dt='2020-06-15';

13.2.6 优惠券领用事实表（累积型快照事实表）

1）建表语句

DROP TABLE IF EXISTS dwd_coupon_use;
CREATE EXTERNAL TABLE dwd_coupon_use(
    `id` STRING COMMENT '编号',
    `coupon_id` STRING  COMMENT '优惠券ID',
    `user_id` STRING  COMMENT 'userid',
    `order_id` STRING  COMMENT '订单id',
    `coupon_status` STRING  COMMENT '优惠券状态',
    `get_time` STRING  COMMENT '领取时间',
    `using_time` STRING  COMMENT '使用时间(下单)',
    `used_time` STRING  COMMENT '使用时间(支付)',
    `expire_time` STRING COMMENT '过期时间'
) COMMENT '优惠券领用事实表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_coupon_use/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_coupon_use partition(dt)
select
    id,
    coupon_id,
    user_id,
    order_id,
    coupon_status,
    get_time,
    using_time,
    used_time,
    expire_time,
    coalesce(date_format(used_time,'yyyy-MM-dd'),date_format(expire_time,'yyyy-MM-dd'),'9999-99-99')
from ods_coupon_use
where dt='2020-06-14';

（2）每日装载
a.装载逻辑

b.转载语句

insert overwrite table dwd_coupon_use partition(dt)
select
    nvl(new.id,old.id),
    nvl(new.coupon_id,old.coupon_id),
    nvl(new.user_id,old.user_id),
    nvl(new.order_id,old.order_id),
    nvl(new.coupon_status,old.coupon_status),
    nvl(new.get_time,old.get_time),
    nvl(new.using_time,old.using_time),
    nvl(new.used_time,old.used_time),
    nvl(new.expire_time,old.expire_time),
    coalesce(date_format(nvl(new.used_time,old.used_time),'yyyy-MM-dd'),date_format(nvl(new.expire_time,old.expire_time),'yyyy-MM-dd'),'9999-99-99')
from
(
    select
        id,
        coupon_id,
        user_id,
        order_id,
        coupon_status,
        get_time,
        using_time,
        used_time,
        expire_time
    from dwd_coupon_use
    where dt='9999-99-99'
)old
full outer join
(
    select
        id,
        coupon_id,
        user_id,
        order_id,
        coupon_status,
        get_time,
        using_time,
        used_time,
        expire_time
    from ods_coupon_use
    where dt='2020-06-15'
)new
on old.id=new.id;

13.2.7 支付事实表（累积型快照事实表）

1）建表语句

DROP TABLE IF EXISTS dwd_payment_info;
CREATE EXTERNAL TABLE dwd_payment_info (
    `id` STRING COMMENT '编号',
    `order_id` STRING COMMENT '订单编号',
    `user_id` STRING COMMENT '用户编号',
    `province_id` STRING COMMENT '地区ID',
    `trade_no` STRING COMMENT '交易编号',
    `out_trade_no` STRING COMMENT '对外交易编号',
    `payment_type` STRING COMMENT '支付类型',
    `payment_amount` DECIMAL(16,2) COMMENT '支付金额',
    `payment_status` STRING COMMENT '支付状态',
    `create_time` STRING COMMENT '创建时间',--调用第三方支付接口的时间
    `callback_time` STRING COMMENT '完成时间'--支付完成时间，即支付成功回调时间
) COMMENT '支付事实表表'
PARTITIONED BY (`dt` STRING)
STORED AS PARQUET
LOCATION '/warehouse/gmall/dwd/dwd_payment_info/'
TBLPROPERTIES ("parquet.compression"="lzo");

2）分区规划

3）数据装载

（1）首日装载

insert overwrite table dwd_payment_info partition(dt)
select
    pi.id,
    pi.order_id,
    pi.user_id,
    oi.province_id,
    pi以上是关于离线数仓搭建_12_DWD层业务数据创建的主要内容，如果未能解决你的问题，请参考以下文章
 
 离线数仓搭建_05_电商业务简介与业务数据说明
 离线数仓DIM层和DWD层，联表后表和字段命名规则
 粗谈大数据的演变过程
 02-开始建表_离线数仓项目
 数仓搭建DWD层
 离线数仓之数据监控-Grafana