hive:数据库“行专列”操作---使用collect_set/collect_list/collect_all & row_number()over(partition by 分组字段 [order by 排序字段])

方案一:请参考《数据库“行专列”操作---使用row_number()over(partition by 分组字段 [order by 排序字段])》,该方案是sqlserver,oracle,mysql,hive均适用的。

在hive中的方案分为以下两种方案:

创建测试表,并插入测试数据:

--hive 测试 行转列 collect_set collect_list
create table tommyduan_test(
gridid string,
height int,
cell string,
mrcount int,
weakmrcount int
); insert into tommyduan_test values('g1',1,'cell1',12,3);
insert into tommyduan_test values('g1',1,'cell2',22,3);
insert into tommyduan_test values('g1',1,'cell3',23,3);
insert into tommyduan_test values('g1',1,'cell4',1,3);
insert into tommyduan_test values('g1',1,'cell5',3,3);
insert into tommyduan_test values('g1',1,'cell6',4,3);
insert into tommyduan_test values('g1',1,'cell19',21,3); insert into tommyduan_test values('g2',1,'cell4',1,3);
insert into tommyduan_test values('g2',1,'cell5',3,3);
insert into tommyduan_test values('g2',1,'cell6',4,3);
insert into tommyduan_test values('g2',1,'cell19',21,3);

方案二:使用collect_set方案

注意:collect_set是一个set集合,不允许重复的记录插入

select gridid,height,collect_list(cell) cellArray,collect_list(mrcount) mrcountArray,collect_list(weakmrcount) weakmrcountArray
from (
select gridid,height,cell,mrcount,weakmrcount,row_number()over(partition by gridid,height order by mrcount desc) rn
from tommyduan_test
group by gridid,height,cell,mrcount,weakmrcount
) t10
where rn<4
group by gridid,height;
+---------+---------+-----------------------------+---------------+-------------------+--+
| gridid | height | cellarray | mrcountarray | weakmrcountarray |
+---------+---------+-----------------------------+---------------+-------------------+--+
| g1 | 1 | ["cell3","cell2","cell19"] | [23,22,21] | [3,3,3] |
| g2 | 1 | ["cell19","cell6","cell5"] | [21,4,3] | [3,3,3] |
+---------+---------+-----------------------------+---------------+-------------------+--+ select gridid,height,
(case when size(cellArray)>0 then cellArray[] else '-9999' end) as cell1,
(case when size(cellArray)>0 then mrcountArray[] else '-9999' end) as cell1_mrcount,
(case when size(cellArray)>0 then weakmrcountArray[] else '-9999' end) as cell1_weakmrcount,
(case when size(cellArray)>1 then cellArray[] else '-9999' end) as cell2,
(case when size(cellArray)>1 then mrcountArray[] else '-9999' end) as cell2_mrcount,
(case when size(cellArray)>1 then weakmrcountArray[] else '-9999' end) as cell2_weakmrcount,
(case when size(cellArray)>2 then cellArray[] else '-9999' end) as cell3,
(case when size(cellArray)>2 then mrcountArray[] else '-9999' end) as cell3_mrcount,
(case when size(cellArray)>2 then weakmrcountArray[] else '-9999' end) as cell3_weakmrcount
from
(
select gridid,height,collect_list(cell) cellArray,collect_list(mrcount) mrcountArray,collect_list(weakmrcount) weakmrcountArray
from (
select gridid,height,cell,mrcount,weakmrcount,row_number()over(partition by gridid,height order by mrcount desc) rn
from tommyduan_test
group by gridid,height,cell,mrcount,weakmrcount
) t10
where rn<4
group by gridid,height
) t12;
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+
| gridid | height | cell1 | cell1_mrcount | cell1_weakmrcount | cell2 | cell2_mrcount | cell2_weakmrcount | cell3 | cell3_mrcount | cell3_weakmrcount |
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+
| g1 | 1 | cell3 | 23 | 3 | cell2 | 22 | 3 | cell19 | 21 | 3 |
| g2 | 1 | cell19 | 21 | 3 | cell6 | 4 | 3 | cell5 | 3 | 3 |
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+

方案三:使用collect_list/collect_all方案

注意:collect_set是一个set集合,不允许重复的记录插入

select gridid,height,collect_set(cell),collect_set(mrcount),collect_set(weakmrcount)
from (select * from tommyduan_test order by gridid,height,mrcount desc) t10
group by gridid,height;
+---------+---------+-------------------------------------------------------------+----------------------+------+--+
| gridid | height | _c2 | _c3 | _c4 |
+---------+---------+-------------------------------------------------------------+----------------------+------+--+
| g1 | 1 | ["cell3","cell2","cell19","cell1","cell6","cell5","cell4"] | [23,22,21,12,4,3,1] | [] |
| g2 | 1 | ["cell19","cell6","cell5","cell4"] | [21,4,3,1] | [] |
+---------+---------+-------------------------------------------------------------+----------------------+------+--+ select gridid,height,collect_set(cell) cellArray,collect_set(mrcount) mrcountArray,collect_set(weakmrcount) weakmrcountArray
from (
select gridid,height,cell,mrcount,weakmrcount,row_number()over(partition by gridid,height order by mrcount desc) rn
from tommyduan_test
group by gridid,height,cell,mrcount,weakmrcount
) t10
where rn<4
group by gridid,height;
+---------+---------+-----------------------------+---------------+-------------------+--+
| gridid | height | cellarray | mrcountarray | weakmrcountarray |
+---------+---------+-----------------------------+---------------+-------------------+--+
| g1 | 1 | ["cell3","cell2","cell19"] | [23,22,21] | [] |
| g2 | 1 | ["cell19","cell6","cell5"] | [21,4,3] | [] |
+---------+---------+-----------------------------+---------------+-------------------+--+ select gridid,height,collect_set(concat_ws(',',cell,cast(mrcount as string), cast(weakmrcount as string))) as cellArray
from (
select gridid,height,cell,mrcount,weakmrcount,row_number()over(partition by gridid,height order by mrcount desc) rn
from tommyduan_test
group by gridid,height,cell,mrcount,weakmrcount
) t10
where rn<4
group by gridid,height
+---------+---------+--------------------------------------------+--+
| gridid | height | cellarray |
+---------+---------+--------------------------------------------+--+
| g1 | 1 | ["cell3,23,3","cell2,22,3","cell19,21,3"] |
| g2 | 1 | ["cell19,21,3","cell6,4,3","cell5,3,3"] |
+---------+---------+--------------------------------------------+--+ select gridid,height,
(case when size(cellArray)>0 then split(cellArray[],'_')[] else '-9999' end) as cell1,
(case when size(cellArray)>0 then split(cellArray[],'_')[] else '-9999' end) as cell1_mrcount,
(case when size(cellArray)>0 then split(cellArray[],'_')[] else '-9999' end) as cell1_weakmrcount,
(case when size(cellArray)>1 then split(cellArray[],'_')[] else '-9999' end) as cell2,
(case when size(cellArray)>1 then split(cellArray[],'_')[] else '-9999' end) as cell2_mrcount,
(case when size(cellArray)>1 then split(cellArray[],'_')[] else '-9999' end) as cell2_weakmrcount,
(case when size(cellArray)>2 then split(cellArray[],'_')[] else '-9999' end) as cell3,
(case when size(cellArray)>2 then split(cellArray[],'_')[] else '-9999' end) as cell3_mrcount,
(case when size(cellArray)>2 then split(cellArray[],'_')[] else '-9999' end) as cell3_weakmrcount
from
(
select gridid,height,collect_set(concat_ws('_',cell,cast(mrcount as string), cast(weakmrcount as string))) as cellArray
from (
select gridid,height,cell,mrcount,weakmrcount,row_number()over(partition by gridid,height order by mrcount desc) rn
from tommyduan_test
group by gridid,height,cell,mrcount,weakmrcount
) t10
where rn<4
group by gridid,height
) t12;
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+
| gridid | height | cell1 | cell1_mrcount | cell1_weakmrcount | cell2 | cell2_mrcount | cell2_weakmrcount | cell3 | cell3_mrcount | cell3_weakmrcount |
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+
| g1 | 1 | cell3 | 23 | 3 | cell2 | 22 | 3 | cell19 | 21 | 3 |
| g2 | 1 | cell19 | 21 | 3 | cell6 | 4 | 3 | cell5 | 3 | 3 |
+---------+---------+---------+----------------+--------------------+--------+----------------+--------------------+---------+----------------+--------------------+--+
上一篇:Win下执行Swing程序的BAT文件 和 Linux下执行Swing程序的SH文件


下一篇:SQL Server 2008中增强的"汇总"技巧