慢慢改变维度 - Hive中的SCD1和SCD2实现

时间：2016-05-26 22:36:48

标签： hadoop hive data-warehouse

我正在寻找Hive（1.2.1）中的SCD1和SCD2实现。我知道在Hive（0.14）之前加载SCD1和SCD2表的解决方法。以下是使用变通方法http://hortonworks.com/blog/four-step-strategy-incremental-updates-hive/

加载SCD1和SCD2的链接

现在Hive支持ACID操作，只是想知道是否有更好或更直接的加载方法。

5 个答案:

答案 0 :(得分：2)

由于HDFS是不可变存储，因此可以认为版本控制数据和保存历史记录（SCD2）应该是加载维度的默认行为。您可以在Hadoop SQL查询引擎（Hive，Impala，Drill等）中创建一个View，它使用窗口函数检索当前状态/最新值。您可以在我的博文中找到有关dimensional models on Hadoop的更多信息，例如如何处理大维度和事实表。

答案 1 :(得分：1)

好吧，我使用两个临时表来处理它：

    drop table if exists administrator_tmp1;
drop table if exists administrator_tmp2;

set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nonstrict;

--review_administrator
CREATE TABLE if not exists review_administrator(
    admin_id bigint ,
    admin_name string,
    create_time string,
    email string ,
    password string,
    status_description string,
    token string ,
    expire_time string ,
    granter_user_id bigint ,
    admin_time string ,
    effect_start_date string ,
    effect_end_date string 
)
partitioned by (current_row_indicator string comment 'current, expired')
stored as parquet;

--tmp1 is used for saving origin data
CREATE TABLE if not exists administrator_tmp1(
    admin_id bigint ,
    admin_name string,
    create_time string,
    email string ,
    password string ,
    status_description string ,
    token string ,
    expire_time string ,
    granter_user_id bigint ,
    admin_time string ,
    effect_start_date string ,
    effect_end_date string 
)
partitioned by (current_row_indicator string comment 'current, expired:')
stored as parquet;

--tmp2 saving the scd data
CREATE TABLE if not exists administrator_tmp2(
    admin_id bigint ,
    admin_name string,
    create_time string,
    email string ,
    password string ,
    status_description string ,
    token string ,
    expire_time string ,
    granter_user_id bigint ,
    admin_time string ,
    effect_start_date string ,
    effect_end_date string 
)
partitioned by (current_row_indicator string comment 'current, expired')
stored as parquet;

--insert origin data into tmp1
INSERT OVERWRITE TABLE administrator_tmp1 PARTITION(current_row_indicator)
SELECT 
    user_id as admin_id,
    name as admin_name,
    time as create_time,
    email as email,
    password as password,
    status as status_description,
    token as token,
    expire_time as expire_time,
    admin_id as granter_user_id,
    admin_time as admin_time,
    '{{ ds }}' as effect_start_date,
    '9999-12-31' as effect_end_date,
    'current' as current_row_indicator
FROM 
    ks_db_origin.gifshow_administrator_origin
;

--insert scd data into tmp2
--for the data unchanged
INSERT INTO TABLE administrator_tmp2 PARTITION(current_row_indicator)
SELECT
    t2.admin_id,
    t2.admin_name,
    t2.create_time,
    t2.email,
    t2.password,
    t2.status_description,
    t2.token,
    t2.expire_time,
    t2.granter_user_id,
    t2.admin_time,
    t2.effect_start_date,
    t2.effect_end_date as effect_end_date,
    t2.current_row_indicator
FROM
    administrator_tmp1 t1
INNER JOIN 
    (
        SELECT * FROM review_administrator 
        WHERE current_row_indicator = 'current'
    ) t2
ON 
    t1.admin_id = t2.admin_id
AND t1.admin_name = t2.admin_name
AND t1.create_time = t2.create_time
AND t1.email = t2.email
AND t1.password = t2.password
AND t1.status_description = t2.status_description
AND t1.token = t2.token
AND t1.expire_time = t2.expire_time
AND t1.granter_user_id = t2.granter_user_id
AND t1.admin_time = t2.admin_time
;

--for the data changed , update the effect_end_date
INSERT INTO TABLE administrator_tmp2 PARTITION(current_row_indicator)
SELECT
    t2.admin_id,
    t2.admin_name,
    t2.create_time,
    t2.email,
    t2.password,
    t2.status_description,
    t2.token,
    t2.expire_time,
    t2.granter_user_id,
    t2.admin_time,
    t2.effect_start_date as effect_start_date,
    '{{ yesterday_ds }}' as effect_end_date,
    'expired' as current_row_indicator
FROM
    administrator_tmp1 t1
INNER JOIN 
    (
        SELECT * FROM review_administrator 
        WHERE current_row_indicator = 'current'
    ) t2
ON 
    t1.admin_id = t2.admin_id
WHERE NOT 
    (
        t1.admin_name = t2.admin_name
    AND t1.create_time = t2.create_time
    AND t1.email = t2.email
    AND t1.password = t2.password
    AND t1.status_description = t2.status_description
    AND t1.token = t2.token
    AND t1.expire_time = t2.expire_time
    AND t1.granter_user_id = t2.granter_user_id
    AND t1.admin_time = t2.admin_time
    )
;

--for the changed data and the new data
INSERT INTO TABLE administrator_tmp2 PARTITION(current_row_indicator)
SELECT
    t1.admin_id,
    t1.admin_name,
    t1.create_time,
    t1.email,
    t1.password,
    t1.status_description,
    t1.token,
    t1.expire_time,
    t1.granter_user_id,
    t1.admin_time,
    t1.effect_start_date,
    t1.effect_end_date,
    t1.current_row_indicator
FROM
    administrator_tmp1 t1
LEFT OUTER JOIN 
    (
        SELECT * FROM review_administrator 
        WHERE current_row_indicator = 'current'
    ) t2
ON 
    t1.admin_id = t2.admin_id
AND t1.admin_name = t2.admin_name
AND t1.create_time = t2.create_time
AND t1.email = t2.email
AND t1.password = t2.password
AND t1.status_description = t2.status_description
AND t1.token = t2.token
AND t1.expire_time = t2.expire_time
AND t1.granter_user_id = t2.granter_user_id
AND t1.admin_time = t2.admin_time
WHERE t2.admin_id IS NULL
;

--for the data already marked by 'expired'
INSERT INTO TABLE administrator_tmp2 PARTITION(current_row_indicator)
SELECT
    t1.admin_id,
    t1.admin_name,
    t1.create_time,
    t1.email,
    t1.password,
    t1.status_description,
    t1.token,
    t1.expire_time,
    t1.granter_user_id,
    t1.admin_time,
    t1.effect_start_date,
    t1.effect_end_date,
    t1.current_row_indicator
FROM
    review_administrator t1
WHERE t1.current_row_indicator = 'expired'
;

--populate the dim table
INSERT OVERWRITE TABLE review_administrator PARTITION(current_row_indicator)
SELECT
    t1.admin_id,
    t1.admin_name,
    t1.create_time,
    t1.email,
    t1.password,
    t1.status_description,
    t1.token,
    t1.expire_time,
    t1.granter_user_id,
    t1.admin_time,
    t1.effect_start_date,
    t1.effect_end_date,
    t1.current_row_indicator
FROM
    administrator_tmp2 t1
;

--drop the two temp table
drop table administrator_tmp1;
drop table administrator_tmp2;


-- --example data
-- --2017-01-01
-- insert into table review_administrator PARTITION(current_row_indicator)
-- SELECT '1','a','2016-12-31','a@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-01','9999-12-31','current' 
-- FROM default.sample_07 limit 1;

-- --2017-01-02
-- insert into table administrator_tmp1 PARTITION(current_row_indicator)
-- SELECT '1','a','2016-12-31','a01@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-02','9999-12-31','current' 
-- FROM default.sample_07 limit 1;

-- insert into table administrator_tmp1 PARTITION(current_row_indicator)
-- SELECT '2','b','2016-12-31','a@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-02','9999-12-31','current' 
-- FROM default.sample_07 limit 1;

-- --2017-01-03
-- --id 1 is changed
-- insert into table administrator_tmp1 PARTITION(current_row_indicator)
-- SELECT '1','a','2016-12-31','a03@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-03','9999-12-31','current' 
-- FROM default.sample_07 limit 1;
-- --id 2 is not changed at all
-- insert into table administrator_tmp1 PARTITION(current_row_indicator)
-- SELECT '2','b','2016-12-31','a@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-03','9999-12-31','current' 
-- FROM default.sample_07 limit 1;
-- --id 3 is a new record
-- insert into table administrator_tmp1 PARTITION(current_row_indicator)
-- SELECT '3','c','2016-12-31','c@ks.com','password','open','token1','2017-12-31',
-- 0,'2017-12-31','2017-01-03','9999-12-31','current' 
-- FROM default.sample_07 limit 1;

-- --now dim table will show you the right SCD.

答案 2 :(得分：0)

以下是使用独占联接方法在Hive中缓慢更改尺寸类型2的详细实现。

假设源正在发送完整的数据文件，即旧记录，更新记录和新记录。

Steps-

  1. 将最新文件数据加载到STG表

  2. 从HIST表中选择所有过期的记录

    select * from HIST_TAB where exp_dt != '2099-12-31'

  3. 使用内部连接选择所有未从STG和HIST更改的记录，并在HIST.column = STG.column上进行过滤，如下所示

    select hist.* from HIST_TAB hist inner join STG_TAB stg on hist.key = stg.key where hist.column = stg.column

  4. 使用与HIST_TAB的排他左联接选择所有从STG_TAB更改的新记录和更新记录，并设置如下的到期和生效日期

    select stg.*, eff_dt (yyyy-MM-dd), exp_dt (2099-12-31) from STG_TAB stg left join (select * from HIST_TAB where exp_dt = '2099-12-31') hist on hist.key = stg.key where hist.key is null or hist.column != stg.column

  5. 使用与STG表的排他左联接从HIST表中选择所有更新的旧记录，并设置其到期日期，如下所示：

    select hist.*, exp_dt(yyyy-MM-dd) from (select * from HIST_TAB where exp_dt = '2099-12-31') hist left join STG_TAB stg on hist.key= stg.key where hist.key is null or hist.column!= stg.column

  6. unionall从2-5查询并将覆盖结果插入到HIST表中

在这里可以找到SCD类型2的更详细的实现-

https://github.com/sahilbhange/slowly-changing-dimension

答案 3 :(得分：0)

drop table if exists harsha.emp;

drop table if exists harsha.emp_tmp1;

drop table if exists harsha.emp_tmp2;

drop table if exists harsha.init_load;

show databases;
use harsha;
show tables;

create table harsha.emp (eid int,ename string,sal int,loc string,dept int,start_date timestamp,end_date timestamp,current_status string)
comment "emp scd implementation"
row format delimited
fields terminated by ','
lines terminated by '\n'
;

create table harsha.emp_tmp1 (eid int,ename string,sal int,loc string,dept int,start_date timestamp,end_date timestamp,current_status string)
comment "emp scd implementation"
row format delimited
fields terminated by ','
lines terminated by '\n'
;

create table harsha.emp_tmp2 (eid int,ename string,sal int,loc string,dept int,start_date timestamp,end_date timestamp,current_status string)
comment "emp scd implementation"
row format delimited
fields terminated by ','
lines terminated by '\n'
;

create table harsha.init_load (eid int,ename string,sal int,loc string,dept int) 
row format delimited
fields terminated by ','
lines terminated by '\n'
;

show tables;

insert into table harsha.emp select 101 as eid,'aaaa' as ename,3400 as sal,'chicago' as loc,10 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 102 as eid,'abaa' as ename,6400 as sal,'ny' as loc,10 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 103 as eid,'abca' as ename,2300 as sal,'sfo' as loc,20 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 104 as eid,'afga' as ename,3000 as sal,'seattle' as loc,10 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 105 as eid,'ikaa' as ename,1400 as sal,'LA' as loc,30 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 106 as eid,'cccc' as ename,3499 as sal,'spokane' as loc,20 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

insert into table harsha.emp select 107 as eid,'toiz' as ename,4000 as sal,'WA.DC' as loc,40 as did,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from (select '123')x;

load data local inpath 'Documents/hadoop_scripts/t3.txt' into table harsha.emp;

load data local inpath 'Documents/hadoop_scripts/t4.txt' into table harsha.init_load;

insert into table harsha.emp_tmp1 select eid,ename,sal,loc,dept,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status 
from harsha.init_load;

insert into table harsha.emp_tmp2
select a.eid,a.ename,a.sal,a.loc,a.dept,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'updated' as current_status from emp_tmp1 a
left outer join emp b on
a.eid=b.eid and 
a.ename=b.ename and
a.sal=b.sal and 
a.loc = b.loc and 
a.dept = b.dept
where b.eid is null
union all
select a.eid,a.ename,a.sal,a.loc,a.dept,from_unixtime(unix_timestamp()) as start_date,from_unixtime(unix_timestamp('9999-12-31 23:59:59','yyyy-mm-dd hh:mm:ss')) as end_date,'current' as current_status from emp_tmp1 a
left outer join emp b on
a.eid = b.eid and
a.ename=b.ename and
a.sal=b.sal and 
a.loc=b.loc and 
a.dept=b.dept
where b.eid is not null
union all
select b.eid,b.ename,b.sal,b.loc,b.dept,b.start_date as start_date,from_unixtime(unix_timestamp()) as end_date,'expired' as current_status from emp b
inner join emp_tmp1 a on
a.eid=b.eid  
where
a.ename <> b.ename or
a.sal <> b.sal or 
a.loc <> b.loc or 
a.dept <> b.dept 
;

insert into table harsha.emp select eid,ename,sal,loc,dept,start_date,end_date,current_status from emp_tmp2;

records including expired:

select * from harsha.emp order by eid;

latest recods:

select a.* from emp a inner join (select eid ,max(start_date) as start_date from emp where current_status <> 'expired' group by eid) b on a.eid=b.eid and a.start_date=b.start_date;

答案 4 :(得分：-2)

在使用SCDs管理数据时，我确实使用了另一种方法：

  1. 永远不要更新历史文件或表格中存在的数据。

  2. 确保将新行与最新一代进行比较，例如，加载逻辑将添加控制列：loaded_on，checksum，如果需要，还会添加一个序列列如果在同一天发生多个加载，则将新数据与最新一代进行比较时，将使用控制列和数据中存在的关键列（如客户或产品密钥）。

    3. 现在，通过计算所涉及的所有列的checksum但控制列，为每行创建一个独特的指纹，确实可以实现神奇。然后，指纹（checksum）列将用于确定与最近一代相比是否有任何列发生了更改（最近一代基于基于key，loaded_on和序列的最新数据状态）

    现在，您知道来自每日更新的行是否是新的，因为没有上一代或者来自每日更新的行需要在历史文件或表中创建新行（新一代），如果来自每日更新的行没有任何更改，则不需要创建行，因为与上一代相比没有区别。

    可以使用Apache Spark构建所需的逻辑类型，在单个语句中，您可以要求Spark连接任意datatypes的任意数量的列，然后计算hash用于指纹打印的值。

    现在，您可以开发一个基于spark的实用程序，该实用程序将接受任何数据源并输出组织良好，干净且缓慢的维度感知历史文件，表格，...最后，永远不会更新追加！

相关问题
最新问题