Hive-1.2.1_06_累计报表查询

1. 数据准备

 # 本地数据准备
 [yun@mini01 hive]$ pwd
 /app/software/hive
 [yun@mini01 hive]$ ll /app/software/hive/t_access_times.dat
 -rw-rw-r--  yun yun  Jul  : /app/software/hive/t_access_times.dat
 [yun@mini01 hive]$ cat /app/software/hive/t_access_times.dat
 A,--,
 A,--,
 B,--,
 A,--,
 B,--,
 A,--,
 A,--,
 A,--,
 B,--,
 B,--,
 A,--,
 B,--,
 A,--,
 B,--,
 A,--,
 B,--,
 A,--,
 B,--,
 A,--,
 # hive 建表
 hive (test_db)> create table t_access_times(username string,month string,salary int)
               > row format delimited fields terminated by ',';
 OK
 Time taken: 0.16 seconds

 # 数据上传  从desc formatted t_access_times; 可获取Location信息
 : jdbc:hive2://mini01:10000> load data local inpath '/app/software/hive/t_access_times.dat' [overwrite] into table t_access_times; # 上传
 INFO  : Loading data to table test_db.t_access_times from file:/app/software/hive/t_access_times.dat
 INFO  : Table test_db.t_access_times stats: [numFiles=, totalSize=]
 No rows affected (0.764 seconds)
 : jdbc:hive2://mini01:10000> select * from t_access_times; # 查询数据
 +--------------------------+-----------------------+------------------------+--+
 | t_access_times.username  | t_access_times.month  | t_access_times.salary  |
 +--------------------------+-----------------------+------------------------+--+
 | A                        | --            |                       |
 | A                        | --            |                      |
 | B                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                      |
 | A                        | --            |                       |
 | A                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                      |
 | B                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                       |
 | A                        | --            |                       |
 | B                        | --            |                       |
 | A                        | --            |                       |
 +--------------------------+-----------------------+------------------------+--+
  rows selected (0.102 seconds)
 # 根据月份查询  去掉月份字段中的天信息
 : jdbc:hive2://mini01:10000> select a.username, substr(a.month,1,7) month, a.salary from t_access_times a;
 +-------------+----------+-----------+--+
 | a.username  |  month   | a.salary  |
 +-------------+----------+-----------+--+
 | A           | -  |          |
 | A           | -  |         |
 | B           | -  |          |
 | A           | -  |          |
 | B           | -  |         |
 | A           | -  |          |
 | A           | -  |          |
 | A           | -  |          |
 | B           | -  |         |
 | B           | -  |          |
 | A           | -  |          |
 | B           | -  |          |
 | A           | -  |          |
 | B           | -  |          |
 | A           | -  |          |
 | B           | -  |          |
 | A           | -  |          |
 | B           | -  |          |
 | A           | -  |          |
 +-------------+----------+-----------+--+
  rows selected (0.078 seconds)

2. 用户一个月总金额

 # 或者使用 select x.username, x.month, sum(x.salary) from (select a.username, substr(a.month,,) month, a.salary from t_access_times a) x group by x.username, x.month;
 : jdbc:hive2://mini01:10000> select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7);
 INFO  : Number of reduce tasks not specified. Estimated from input data size:
 INFO  : In order to change the average load for a reducer (in bytes):
 INFO  :   set hive.exec.reducers.bytes.per.reducer=<number>
 INFO  : In order to limit the maximum number of reducers:
 INFO  :   set hive.exec.reducers.max=<number>
 INFO  : In order to set a constant number of reducers:
 INFO  :   set mapreduce.job.reduces=<number>
 INFO  : number of splits:
 INFO  : Submitting tokens for job: job_1531893043061_0002
 INFO  : The url to track the job: http://mini02:8088/proxy/application_1531893043061_0002/
 INFO  : Starting Job = job_1531893043061_0002, Tracking URL = http://mini02:8088/proxy/application_1531893043061_0002/
 INFO  : Kill Command = /app/hadoop/bin/hadoop job  -kill job_1531893043061_0002
 INFO  : Hadoop job information for Stage-: number of mappers: ; number of reducers:
 INFO  : -- ::, Stage- map = %,  reduce = %
 INFO  : -- ::, Stage- map = %,  reduce = %, Cumulative CPU 3.08 sec
 INFO  : -- ::, Stage- map = %,  reduce = %, Cumulative CPU 5.53 sec
 INFO  : MapReduce Total cumulative CPU time:  seconds  msec
 INFO  : Ended Job = job_1531893043061_0002
 +-------------+----------+------+--+
 | a.username  |  month   | _c2  |
 +-------------+----------+------+--+
 | A           | -  |    |
 | A           | -  |    |
 | A           | -  |    |
 | B           | -  |    |
 | B           | -  |    |
 | B           | -  |    |
 +-------------+----------+------+--+
  rows selected (18.755 seconds)

3. 将月总金额表 自己连接 自己连接

 : jdbc:hive2://mini01:10000> select * from
 : jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) A
 : jdbc:hive2://mini01:10000> inner join
 : jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) B
 : jdbc:hive2://mini01:10000> on A.username = B.username
 : jdbc:hive2://mini01:10000> ORDER BY A.username, A.`month`, B.`month`;
 INFO  : Number of reduce tasks not specified. Estimated from input data size:
 …………………………
 INFO  : Ended Job = job_1531893043061_0029
 +-------------+----------+-----------+-------------+----------+-----------+--+
 | a.username  | a.month  | a.salary  | b.username  | b.month  | b.salary  |
 +-------------+----------+-----------+-------------+----------+-----------+--+
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | A           | -  |         | A           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 | B           | -  |         | B           | -  |         |
 +-------------+----------+-----------+-------------+----------+-----------+--+
  rows selected (85.593 seconds)
 ######################################################
 # 查询后排序
 : jdbc:hive2://mini01:10000> select * from
 : jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) A
 : jdbc:hive2://mini01:10000> inner join
 : jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) B
 : jdbc:hive2://mini01:10000> on A.username = B.username
 : jdbc:hive2://mini01:10000> where A.month >= B.month
 : jdbc:hive2://mini01:10000> ORDER BY A.username, A.month, B.month;
 INFO  : Number of reduce tasks not specified. Estimated from input data size:
 …………………………
 INFO  : Ended Job = job_1531893043061_0016
 +-------------+----------+--------+-------------+----------+--------+--+
 | a.username  | a.month  | a._c2  | b.username  | b.month  | b._c2  |
 +-------------+----------+--------+-------------+----------+--------+--+
 | A           | -  |      | A           | -  |      |
 | A           | -  |      | A           | -  |      |
 | A           | -  |      | A           | -  |      |
 | A           | -  |      | A           | -  |      |
 | A           | -  |      | A           | -  |      |
 | A           | -  |      | A           | -  |      |
 | B           | -  |      | B           | -  |      |
 | B           | -  |      | B           | -  |      |
 | B           | -  |      | B           | -  |      |
 | B           | -  |      | B           | -  |      |
 | B           | -  |      | B           | -  |      |
 | B           | -  |      | B           | -  |      |
 +-------------+----------+--------+-------------+----------+--------+--+
  rows selected (83.385 seconds)

4. 累计报表

4.1. 类似数据在MySQL数据库查询

 # 使用这个SQL语句就可了，但是在HIVE中运行不了
 select A.username, A.month, A.salary , sum(B.salary) countSala from
 (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) A
 inner join
 (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) B
 on A.username = B.username
 where A.month >= B.month
 group by A.username, A.month
 ORDER BY A.username, A.month, B.month;

4.2. Hive中运行

 # 上面的SQL不能运行  所以查询列表改为了max(A.salary) salary  ；  order by 中去掉了 B.month  。
 0: jdbc:hive2://mini01:10000> select A.username, A.month, max(A.salary) salary, sum(B.salary) countSala from
 0: jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) A
 0: jdbc:hive2://mini01:10000> inner join
 0: jdbc:hive2://mini01:10000> (select a.username, substr(a.month,1,7) month, sum(a.salary) salary from t_access_times a group by a.username, substr(a.month,1,7)) B
 0: jdbc:hive2://mini01:10000> on A.username = B.username
 0: jdbc:hive2://mini01:10000> where A.month >= B.month
 0: jdbc:hive2://mini01:10000> group by A.username, A.month
 0: jdbc:hive2://mini01:10000> ORDER BY A.username, A.month;
 INFO  : Number of reduce tasks not specified. Estimated from input data size: 1
 ………………
 INFO  : Ended Job = job_1531893043061_0052
 +-------------+----------+---------+------------+--+
 | a.username  | a.month  | salary  | countsala  |
 +-------------+----------+---------+------------+--+
 | A           | 2015-01  | 33      | 33         |
 | A           | 2015-02  | 10      | 43         |
 | A           | 2015-03  | 11      | 54         |
 | B           | 2015-01  | 30      | 30         |
 | B           | 2015-02  | 15      | 45         |
 | B           | 2015-03  | 20      | 65         |
 +-------------+----------+---------+------------+--+
 6 rows selected (106.718 seconds)