Hive简单实操

---

前言

此为hive数据仓库部分实操Hive QL，仅供学习使用。

---

一、导入数据

load data (local) inpath "xx" into table xx;

二、insert导出

insert overwrite (local) directory 
'/opt/module/hive/data/export/student1'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
select * from student;

三、实操

1

SELECT
videoId,
views
FROM
gulivideo_orc
ORDER BY
views DESC
LIMIT 10;

2

SELECT
t1.category_name ,
COUNT(t1.videoId) hot
FROM
(
SELECT
videoId,
category_name
FROM
gulivideo_orc
lateral VIEW explode(category) gulivideo_orc_tmp AS category_name
) t1
GROUP BY
t1.category_name
ORDER BY
hot
DESC
LIMIT 10

3

SELECT
t2.category_name,
COUNT(t2.videoId) video_sum
FROM
(
SELECT
t1.videoId,
category_name
FROM
(
SELECT
videoId,
views ,
category
FROM
gulivideo_orc
ORDER BY
views
DESC
LIMIT 20
) t1
lateral VIEW explode(t1.category) t1_tmp AS category_name
) t2
GROUP BY t2.category_name

4

SELECT
t6.category_name,
t6.video_sum,
rank() over(ORDER BY t6.video_sum DESC ) rk
FROM
(
SELECT
t5.category_name,
COUNT(t5.relatedid_id) video_sum
FROM
(
SELECT
t4.relatedid_id,
category_name
FROM
(
SELECT
t2.relatedid_id ,
t3.category
FROM
(
SELECT
relatedid_id
FROM
(
SELECT
videoId,
views,
relatedid
FROM
gulivideo_orc
ORDER BY
views
DESC
LIMIT 50
)t1
lateral VIEW explode(t1.relatedid) t1_tmp AS relatedid_id
)t2
JOIN
gulivideo_orc t3
ON
t2.relatedid_id = t3.videoId
) t4
lateral VIEW explode(t4.category) t4_tmp AS category_name
) t5
GROUP BY
t5.category_name
ORDER BY
video_sum
DESC
) t6

5

SELECT
t1.videoId,
t1.views,
t1.category_name
FROM
(
SELECT
videoId,
views,
category_name
FROM gulivideo_orc
lateral VIEW explode(category) gulivideo_orc_tmp AS category_name
)t1
WHERE
t1.category_name = "Music"
ORDER BY
t1.views
DESC
LIMIT 10

6

SELECT
t2.videoId,
t2.views,
t2.category_name,
t2.rk
FROM
(
SELECT
t1.videoId,
t1.views,
t1.category_name,
rank() over(PARTITION BY t1.category_name ORDER BY t1.views DESC ) rk
FROM
(
SELECT
videoId,
views,
category_name
FROM gulivideo_orc
lateral VIEW explode(category) gulivideo_orc_tmp AS category_name
)t1
)t2
WHERE t2.rk <=10

7

SELECT
t2.videoId,
t2.views,
t2.uploader
FROM
(
SELECT
uploader,
videos
FROM gulivideo_user_orc
ORDER BY
videos
DESC
LIMIT 10
) t1
JOIN gulivideo_orc t2
ON t1.uploader = t2.uploader
ORDER BY
t2.views
DESC