轉自:http://blog.fens.me/hadoop-hive-intro/
Hive的基本使用
1. 進入hive控制檯
~ cd /home/cos/toolkit/hive-0.9.0
~ bin/hive shell
Logging initialized using configuration in file:/home/cos/toolkit/hive-0.9.0/conf/hive-log4j.properties
Hive history file=/tmp/cos/hive_job_log_cos_201307160003_95040367.txt
hive>
新建表
#創建數據(文本以tab分隔)
~ vi /home/cos/demo/t_hive.txt
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
#創建新表
hive> CREATE TABLE t_hive (a int, b int, c int) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';
OK
Time taken: 0.489 seconds
#導入數據t_hive.txt到t_hive表
hive> LOAD DATA LOCAL INPATH '/home/cos/demo/t_hive.txt' OVERWRITE INTO TABLE t_hive ;
Copying data from file:/home/cos/demo/t_hive.txt
Copying file: file:/home/cos/demo/t_hive.txt
Loading data to table default.t_hive
Deleted hdfs://c1.wtmart.com:9000/user/hive/warehouse/t_hive
OK
Time taken: 0.397 seconds
查看錶和數據
#查看錶
hive> show tables;
OK
t_hive
Time taken: 0.099 seconds
#正則匹配表名
hive>show tables '*t*';
OK
t_hive
Time taken: 0.065 seconds
#查看錶數據
hive> select * from t_hive;
OK
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
Time taken: 0.264 seconds
#查看錶結構
hive> desc t_hive;
OK
a int
b int
c int
Time taken: 0.1 seconds
修改表
#增加一個字段
hive> ALTER TABLE t_hive ADD COLUMNS (new_col String);
OK
Time taken: 0.186 seconds
hive> desc t_hive;
OK
a int
b int
c int
new_col string
Time taken: 0.086 seconds
#重命令表名
~ ALTER TABLE t_hive RENAME TO t_hadoop;
OK
Time taken: 0.45 seconds
hive> show tables;
OK
t_hadoop
Time taken: 0.07 seconds
刪除表
hive> DROP TABLE t_hadoop;
OK
Time taken: 0.767 seconds
hive> show tables;
OK
Time taken: 0.064 seconds
3. Hive交互式模式
- quit,exit: 退出交互式shell
- reset: 重置配置爲默認值
- set <key>=<value> : 修改特定變量的值(如果變量名拼寫錯誤,不會報錯)
- set : 輸出用戶覆蓋的hive配置變量
- set -v : 輸出所有Hadoop和Hive的配置變量
- add FILE[S] *, add JAR[S] *, add ARCHIVE[S] * : 添加 一個或多個 file, jar, archives到分佈式緩存
- list FILE[S], list JAR[S], list ARCHIVE[S] : 輸出已經添加到分佈式緩存的資源。
- list FILE[S] *, list JAR[S] *,list ARCHIVE[S] * : 檢查給定的資源是否添加到分佈式緩存
- delete FILE[S] *,delete JAR[S] *,delete ARCHIVE[S] * : 從分佈式緩存刪除指定的資源
- ! <command> : 從Hive shell執行一個shell命令
- dfs <dfs command> : 從Hive shell執行一個dfs命令
- <query string> : 執行一個Hive 查詢,然後輸出結果到標準輸出
- source FILE <filepath>: 在CLI裏執行一個hive腳本文件
4. 數據導入
還以剛纔的t_hive爲例。
#創建表結構
hive> CREATE TABLE t_hive (a int, b int, c int) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';
從操作本地文件系統加載數據(LOCAL)
hive> LOAD DATA LOCAL INPATH '/home/cos/demo/t_hive.txt' OVERWRITE INTO TABLE t_hive ;
Copying data from file:/home/cos/demo/t_hive.txt
Copying file: file:/home/cos/demo/t_hive.txt
Loading data to table default.t_hive
Deleted hdfs://c1.wtmart.com:9000/user/hive/warehouse/t_hive
OK
Time taken: 0.612 seconds
#在HDFS中查找剛剛導入的數據
~ hadoop fs -cat /user/hive/warehouse/t_hive/t_hive.txt
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
從HDFS加載數據
創建表t_hive2
hive> CREATE TABLE t_hive2 (a int, b int, c int) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t';
#從HDFS加載數據
hive> LOAD DATA INPATH '/user/hive/warehouse/t_hive/t_hive.txt' OVERWRITE INTO TABLE t_hive2;
Loading data to table default.t_hive2
Deleted hdfs://c1.wtmart.com:9000/user/hive/warehouse/t_hive2
OK
Time taken: 0.325 seconds
#查看數據
hive> select * from t_hive2;
OK
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
Time taken: 0.287 seconds
從其他表導入數據
hive> INSERT OVERWRITE TABLE t_hive2 SELECT * FROM t_hive ;
Total MapReduce jobs = 2
Launching Job 1 out of 2
Number of reduce tasks is set to 0 since there's no reduce operator
Starting Job = job_201307131407_0002, Tracking URL = http://c1.wtmart.com:50030/jobdetails.jsp?jobid=job_201307131407_0002
Kill Command = /home/cos/toolkit/hadoop-1.0.3/libexec/../bin/hadoop job -Dmapred.job.tracker=hdfs://c1.wtmart.com:9001 -kill job_201307131407_0002
Hadoop job information for Stage-1: number of mappers: 1; number of reducers: 0
2013-07-16 10:32:41,979 Stage-1 map = 0%, reduce = 0%
2013-07-16 10:32:48,034 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:49,050 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:50,068 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:51,082 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:52,093 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:53,102 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.03 sec
2013-07-16 10:32:54,112 Stage-1 map = 100%, reduce = 100%, Cumulative CPU 1.03 sec
MapReduce Total cumulative CPU time: 1 seconds 30 msec
Ended Job = job_201307131407_0002
Ended Job = -314818888, job is filtered out (removed at runtime).
Moving data to: hdfs://c1.wtmart.com:9000/tmp/hive-cos/hive_2013-07-16_10-32-31_323_5732404975764014154/-ext-10000
Loading data to table default.t_hive2
Deleted hdfs://c1.wtmart.com:9000/user/hive/warehouse/t_hive2
Table default.t_hive2 stats: [num_partitions: 0, num_files: 1, num_rows: 0, total_size: 56, raw_data_size: 0]
7 Rows loaded to t_hive2
MapReduce Jobs Launched:
Job 0: Map: 1 Cumulative CPU: 1.03 sec HDFS Read: 273 HDFS Write: 56 SUCCESS
Total MapReduce CPU Time Spent: 1 seconds 30 msec
OK
Time taken: 23.227 seconds
hive> select * from t_hive2;
OK
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
Time taken: 0.134 seconds
創建表並從其他表導入數據
#刪除表
hive> DROP TABLE t_hive;
#創建表並從其他表導入數據
hive> CREATE TABLE t_hive AS SELECT * FROM t_hive2 ;
Total MapReduce jobs = 2
Launching Job 1 out of 2
Number of reduce tasks is set to 0 since there's no reduce operator
Starting Job = job_201307131407_0003, Tracking URL = http://c1.wtmart.com:50030/jobdetails.jsp?jobid=job_201307131407_0003
Kill Command = /home/cos/toolkit/hadoop-1.0.3/libexec/../bin/hadoop job -Dmapred.job.tracker=hdfs://c1.wtmart.com:9001 -kill job_201307131407_0003
Hadoop job information for Stage-1: number of mappers: 1; number of reducers: 0
2013-07-16 10:36:48,612 Stage-1 map = 0%, reduce = 0%
2013-07-16 10:36:54,648 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.13 sec
2013-07-16 10:36:55,657 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.13 sec
2013-07-16 10:36:56,666 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.13 sec
2013-07-16 10:36:57,673 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.13 sec
2013-07-16 10:36:58,683 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 1.13 sec
2013-07-16 10:36:59,691 Stage-1 map = 100%, reduce = 100%, Cumulative CPU 1.13 sec
MapReduce Total cumulative CPU time: 1 seconds 130 msec
Ended Job = job_201307131407_0003
Ended Job = -670956236, job is filtered out (removed at runtime).
Moving data to: hdfs://c1.wtmart.com:9000/tmp/hive-cos/hive_2013-07-16_10-36-39_986_1343249562812540343/-ext-10001
Moving data to: hdfs://c1.wtmart.com:9000/user/hive/warehouse/t_hive
Table default.t_hive stats: [num_partitions: 0, num_files: 1, num_rows: 0, total_size: 56, raw_data_size: 0]
7 Rows loaded to hdfs://c1.wtmart.com:9000/tmp/hive-cos/hive_2013-07-16_10-36-39_986_1343249562812540343/-ext-10000
MapReduce Jobs Launched:
Job 0: Map: 1 Cumulative CPU: 1.13 sec HDFS Read: 272 HDFS Write: 56 SUCCESS
Total MapReduce CPU Time Spent: 1 seconds 130 msec
OK
Time taken: 20.13 seconds
hive> select * from t_hive;
OK
16 2 3
61 12 13
41 2 31
17 21 3
71 2 31
1 12 34
11 2 34
Time taken: 0.109 seconds
僅複製表結構不導數據
hive> CREATE TABLE t_hive3 LIKE t_hive;
hive> select * from t_hive3;
OK
Time taken: 0.077 seconds
從MySQL數據庫導入數據
我們將在介紹Sqoop時講。
5. 數據導出
從HDFS複製到HDFS其他位置
~ hadoop fs -cp /user/hive/warehouse/t_hive /
~ hadoop fs -ls /t_hive
Found 1 items
-rw-r--r-- 1 cos supergroup 56 2013-07-16 10:41 /t_hive/000000_0
~ hadoop fs -cat /t_hive/000000_0
1623
611213
41231
17213
71231
11234
11234
通過Hive導出到本地文件系統
hive> INSERT OVERWRITE LOCAL DIRECTORY '/tmp/t_hive' SELECT * FROM t_hive;
Total MapReduce jobs = 1
Launching Job 1 out of 1
Number of reduce tasks is set to 0 since there's no reduce operator
Starting Job = job_201307131407_0005, Tracking URL = http://c1.wtmart.com:50030/jobdetails.jsp?jobid=job_201307131407_0005
Kill Command = /home/cos/toolkit/hadoop-1.0.3/libexec/../bin/hadoop job -Dmapred.job.tracker=hdfs://c1.wtmart.com:9001 -kill job_201307131407_0005
Hadoop job information for Stage-1: number of mappers: 1; number of reducers: 0
2013-07-16 10:46:24,774 Stage-1 map = 0%, reduce = 0%
2013-07-16 10:46:30,823 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:31,833 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:32,844 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:33,856 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:34,865 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:35,873 Stage-1 map = 100%, reduce = 0%, Cumulative CPU 0.87 sec
2013-07-16 10:46:36,884 Stage-1 map = 100%, reduce = 100%, Cumulative CPU 0.87 sec
MapReduce Total cumulative CPU time: 870 msec
Ended Job = job_201307131407_0005
Copying data to local directory /tmp/t_hive
Copying data to local directory /tmp/t_hive
7 Rows loaded to /tmp/t_hive
MapReduce Jobs Launched:
Job 0: Map: 1 Cumulative CPU: 0.87 sec HDFS Read: 271 HDFS Write: 56 SUCCESS
Total MapReduce CPU Time Spent: 870 msec
OK
Time taken: 23.369 seconds
#查看本地操作系統
hive> ! cat /tmp/t_hive/000000_0;
hive> 1623
611213
41231
17213
71231
11234
11234
6. Hive查詢HiveQL
注:以下代碼將去掉map,reduce的日誌輸出部分。
普通查詢:排序,列別名,嵌套子查詢
hive> FROM (
> SELECT b,c as c2 FROM t_hive
> ) t
> SELECT t.b, t.c2
> WHERE b>2
> LIMIT 2;
12 13
21 3
連接查詢:JOIN
hive> SELECT t1.a,t1.b,t2.a,t2.b
> FROM t_hive t1 JOIN t_hive2 t2 on t1.a=t2.a
> WHERE t1.c>10;
1 12 1 12
11 2 11 2
41 2 41 2
61 12 61 12
71 2 71 2
聚合查詢1:count, avg
hive> SELECT count(*), avg(a) FROM t_hive;
7 31.142857142857142
聚合查詢2:count, distinct
hive> SELECT count(DISTINCT b) FROM t_hive;
3
聚合查詢3:GROUP BY, HAVING
#GROUP BY
hive> SELECT avg(a),b,sum(c) FROM t_hive GROUP BY b,c
16.0 2 3
56.0 2 62
11.0 2 34
61.0 12 13
1.0 12 34
17.0 21 3
#HAVING
hive> SELECT avg(a),b,sum(c) FROM t_hive GROUP BY b,c HAVING sum(c)>30
56.0 2 62
11.0 2 34
1.0 12 34
7. Hive視圖
Hive視圖和數據庫視圖的概念是一樣的,我們還以t_hive爲例。
hive> CREATE VIEW v_hive AS SELECT a,b FROM t_hive where c>30;
hive> select * from v_hive;
41 2
71 2
1 12
11 2
刪除視圖
hive> DROP VIEW IF EXISTS v_hive;
OK
Time taken: 0.495 seconds
8. Hive分區表
分區表是數據庫的基本概念,但很多時候數據量不大,我們完全用不到分區表。Hive是一種OLAP數據倉庫軟件,涉及的數據量是非常大的,所以分區表在這個場景就顯得非常重要!!
下面我們重新定義一個數據表結構:t_hft
創建數據
~ vi /home/cos/demo/t_hft_20130627.csv
000001,092023,9.76
000002,091947,8.99
000004,092002,9.79
000005,091514,2.2
000001,092008,9.70
000001,092059,9.45
~ vi /home/cos/demo/t_hft_20130628.csv
000001,092023,9.76
000002,091947,8.99
000004,092002,9.79
000005,091514,2.2
000001,092008,9.70
000001,092059,9.45
創建數據表
DROP TABLE IF EXISTS t_hft;
CREATE TABLE t_hft(
SecurityID STRING,
tradeTime STRING,
PreClosePx DOUBLE
) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
創建分區數據表
根據業務:按天和股票ID進行分區設計
DROP TABLE IF EXISTS t_hft;
CREATE TABLE t_hft(
SecurityID STRING,
tradeTime STRING,
PreClosePx DOUBLE
) PARTITIONED BY (tradeDate INT)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
導入數據
#20130627
hive> LOAD DATA LOCAL INPATH '/home/cos/demo/t_hft_20130627.csv' OVERWRITE INTO TABLE t_hft PARTITION (tradeDate=20130627);
Copying data from file:/home/cos/demo/t_hft_20130627.csv
Copying file: file:/home/cos/demo/t_hft_20130627.csv
Loading data to table default.t_hft partition (tradedate=20130627)
#20130628
hive> LOAD DATA LOCAL INPATH '/home/cos/demo/t_hft_20130628.csv' OVERWRITE INTO TABLE t_hft PARTITION (tradeDate=20130628);
Copying data from file:/home/cos/demo/t_hft_20130628.csv
Copying file: file:/home/cos/demo/t_hft_20130628.csv
Loading data to table default.t_hft partition (tradedate=20130628)
查看分區表
hive> SHOW PARTITIONS t_hft;
tradedate=20130627
tradedate=20130628
Time taken: 0.082 seconds
查詢數據
hive> select * from t_hft where securityid='000001';
000001 092023 9.76 20130627
000001 092008 9.7 20130627
000001 092059 9.45 20130627
000001 092023 9.76 20130628
000001 092008 9.7 20130628
000001 092059 9.45 20130628
hive> select * from t_hft where tradedate=20130627 and PreClosePx<9;
000002 091947 8.99 20130627
000005 091514 2.2 20130627
Hive基於使用完成,這些都是日常的操作。後面我會繼續講一下,HiveQL優化及Hive的運維。
轉載請註明出處:
http://blog.fens.me/hadoop-hive-intro/