hadoop学习笔记之-pig安装及操作实例

[grid@gc ~]$ tar xzvf pig-0.9.2.tar.gz

[grid@gc ~]$ pwd

/home/grid

[grid@gc ~]$ ls

abcd  Desktop  eclipse  hadoop  hadoop-0.20.2  hadoop-code  hbase-0.90.5  input  javaer.log  javaer.log~  pig-0.9.2  workspace

2.       pig本地模式配置环境

所有文件和执行过程都在本地，一般用于测试程序

--编辑环境变量

[grid@gc ~]$ vi .bash_profile

PATH=$PATH:$HOME/bin:/usr/java/jdk1.6.0_18/bin:/home/grid/pig-0.9.2/bin

JAVA_HOME=/usr #注意是java目录的上级目录

export PATH

export LANG=zh_CN

[grid@gc ~]$ source .bash_profile

--进入grunt shell

[grid@gc ~]$ pig -x local

2013-01-09 13:29:10,959 [main] INFO  org.apache.pig.Main - Logging error messages to: /home/grid/pig_1357709350959.log

2013-01-09 13:29:13,080 [main] INFO  org.apache.pig.backend.hadoop.executionengine.HExecutionEngine - Connecting to hadoop file system at: file:///

grunt>

3.       pig的map-reduce模式配置环境

实际工作的环境

--编辑环境变量

PATH=$PATH:$HOME/bin:/usr/java/jdk1.6.0_18/bin:/home/grid/pig-0.9.2/bin:/home/grid/hadoop-0.20.2/bin

export JAVA_HOME=/usr

export PIG_CLASSPATH=/home/grid/pig-0.9.2/conf

export PATH

export LANG=zh_CN

--进入grunt shell

[grid@gc ~]$ pig

2013-01-09 13:55:42,303 [main] INFO  org.apache.pig.Main - Logging error messages to: /home/grid/pig_1357710942292.log

2013-01-09 13:55:45,432 [main] INFO  org.apache.pig.backend.hadoop.executionengine.HExecutionEngine - Connecting to hadoop file system at: hdfs://gc:9000

2013-01-09 13:55:47,409 [main] INFO  org.apache.pig.backend.hadoop.executionengine.HExecutionEngine - Connecting to map-reduce job tracker at: gc:9001

grunt>

注意：因为pig要对hdfs进行操作，在启动grunt shell时之前要必需确保hadoop已经启动。

4.       Pig的运行方法

Ø         pig脚本：将程序写入.pig文件中

Ø         Grunt：运行Pig命令的交互式shell环境

Ø         嵌入式方式

Grunt方法：

--自动补全机制

grunt> s --按tab键

set     split   store

grunt> l  --按tab键

load   long   ls

--Autocomplete文件

--Eclipse插件PigPen

5.       pig常用命令

grunt> ls

hdfs://gc:9000/user/grid/input/Test_1<r 3>      328

hdfs://gc:9000/user/grid/input/Test_2<r 3>      134

hdfs://gc:9000/user/grid/input/abcd<r 2>        11

grunt> copyToLocal Test_1 ttt

grunt> quit

[grid@gc ~]$ ll ttt

-rwxrwxrwx 1 grid hadoop 328 01-11 05:53 ttt

Pig操作实例：

--首先在hadoop中建立week8目录，并将access_log.txt文件传入hadoop

grunt> ls

hdfs://gc:9000/user/grid/.Trash <dir>

hdfs://gc:9000/user/grid/input  <dir>

hdfs://gc:9000/user/grid/out    <dir>

hdfs://gc:9000/user/grid/output <dir>

hdfs://gc:9000/user/grid/output2        <dir>

grunt> pwd

hdfs://gc:9000/user/grid

grunt> mkdir access

grunt> cd access

grunt> copyFromLocal /home/grid/access_log.txt access.log

grunt> ls

hdfs://gc:9000/user/grid/access/access.log<r 2> 7118627

--将log文件load进表a

grunt> a = load '/user/grid/access/access.log'

>> using PigStorage(' ')

>> as (ip,a1,a3,a4,a5,a6,a7,a8);

--对a进行过滤只保留ip字段

grunt> b = foreach a generate ip;

--按ip做group by

grunt> c = group b by ip;

--按ip对c进行统计

grunt> d = foreach c generate group,COUNT($1);

--显示结果：

grunt> dump d;

2013-01-12 12:07:51,482 [main] INFO  org.apache.pig.tools.pigstats.ScriptState - Pig features used in the script: GROUP_BY

2013-01-12 12:07:51,827 [main] INFO  org.apache.pig.newplan.logical.rules.ColumnPruneVisitor - Columns pruned for a: $1, $2, $3, $4, $5, $6, $7

2013-01-12 12:07:54,727 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MRCompiler - File concatenation threshold: 100 optimistic? false

2013-01-12 12:07:54,775 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.CombinerOptimizer - Choosing to move algebraic foreach to combiner

2013-01-12 12:07:55,003 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MultiQueryOptimizer - MR plan size before optimization: 1

2013-01-12 12:07:55,007 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MultiQueryOptimizer - MR plan size after optimization: 1

2013-01-12 12:07:56,316 [main] INFO  org.apache.pig.tools.pigstats.ScriptState - Pig script settings are added to the job

2013-01-12 12:07:56,683 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - mapred.job.reduce.markreset.buffer.percent is not set, set to default 0.3

2013-01-12 12:07:56,701 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - creating jar file Job9027177661900375605.jar

2013-01-12 12:08:12,923 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - jar file Job9027177661900375605.jar created

2013-01-12 12:08:13,040 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - Setting up single store job

2013-01-12 12:08:13,359 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - BytesPerReducer=1000000000 maxReducers=999 totalInputFileSize=7118627

2013-01-12 12:08:13,360 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.JobControlCompiler - Neither PARALLEL nor default parallelism is set for this job. Setting number of reducers to 1

2013-01-12 12:08:13,616 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 1 map-reduce job(s) waiting for submission.

2013-01-12 12:08:14,164 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 0% complete

2013-01-12 12:08:19,125 [Thread-21] INFO  org.apache.hadoop.mapreduce.lib.input.FileInputFormat - Total input paths to process : 1

2013-01-12 12:08:19,154 [Thread-21] INFO  org.apache.pig.backend.hadoop.executionengine.util.MapRedUtil - Total input paths to process : 1

2013-01-12 12:08:19,231 [Thread-21] INFO  org.apache.pig.backend.hadoop.executionengine.util.MapRedUtil - Total input paths (combined) to process : 1

2013-01-12 12:08:30,207 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - HadoopJobId: job_201301091247_0001

2013-01-12 12:08:30,208 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - More information at: http://gc:50030/jobdetails.jsp?jobid=job_201301091247_0001

2013-01-12 12:10:28,459 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 6% complete

2013-01-12 12:10:34,050 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 29% complete

2013-01-12 12:10:38,567 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 50% complete

2013-01-12 12:11:28,357 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - 100% complete

2013-01-12 12:11:28,367 [main] INFO  org.apache.pig.tools.pigstats.SimplePigStats - Script Statistics:

HadoopVersion   PigVersion      UserId  StartedAt       FinishedAt      Features

0.20.2  0.9.2   grid    2013-01-12 12:07:56     2013-01-12 12:11:28     GROUP_BY

Success!

Job Stats (time in seconds):

JobId   Maps    Reduces MaxMapTime      MinMapTIme      AvgMapTime      MaxReduceTime   MinReduceTime   AvgReduceTime   Alias   Feature Outputs

job_201301091247_0001   1       1       58      58      58      25      25      25      a,b,c,d GROUP_BY,COMBINER       hdfs://gc:9000/tmp/temp-1148213696/tmp-241551689,

Input(s):

Successfully read 28134 records (7118627 bytes) from: "/user/grid/access/access.log"

Output(s):

Successfully stored 476 records (14039 bytes) in: "hdfs://gc:9000/tmp/temp-1148213696/tmp-241551689"

Counters:

Total records written : 476

Total bytes written : 14039

Spillable Memory Manager spill count : 0

Total bags proactively spilled: 0

Total records proactively spilled: 0

Job DAG:

job_201301091247_0001

2013-01-12 12:11:28,419 [main] INFO  org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher - Success!

2013-01-12 12:11:28,760 [main] INFO  org.apache.hadoop.mapreduce.lib.input.FileInputFormat - Total input paths to process : 1

2013-01-12 12:11:28,761 [main] INFO  org.apache.pig.backend.hadoop.executionengine.util.MapRedUtil - Total input paths to process : 1

(127.0.0.1,2)

(1.59.65.67,2)

(112.4.2.19,9)

(112.4.2.51,80)

(60.2.99.33,42)

(69.28.58.5,1)

(69.28.58.6,9)

(69.28.58.8,5)

(1.193.3.227,3)

(1.202.221.3,6)

(117.136.9.4,6)

(121.31.62.3,26)

(182.204.8.4,59)

(183.9.112.2,25)

(221.12.37.6,25)

(223.4.16.88,2)

(27.9.110.75,122)

(61.189.63.2,24)

(69.28.58.12,3)

(111.161.72.7,1)

(117.136.12.6,61)

(117.136.19.9,4)

(117.136.2.98,1)

(117.136.20.3,1)

(117.136.20.9,1)

(117.136.3.46,5)

(117.136.4.18,5)

(117.136.4.19,1)

(117.136.5.39,9)

(117.136.5.70,1)

(117.136.5.73,17)

(117.136.7.67,5)

(117.136.8.11,32)

(117.136.8.48,1)

(117.136.8.52,1)

(117.136.8.97,2)

(117.136.9.52,2)

(117.136.9.68,7)

(117.24.22.57,2)

(121.28.95.48,1597)

(122.96.75.15,6)

(124.42.114.9,1)

(125.46.45.78,236)

(125.88.73.21,1)

(182.48.112.2,870)

(183.12.74.40,31)

(207.46.13.95,2)

(210.51.195.5,77)

(218.1.115.55,1)

(218.5.72.173,3)

(27.188.55.59,96)

(27.9.230.128,25)

(59.41.62.100,339)

(61.213.92.56,2)

(61.55.185.38,25)

(61.55.185.61,25)

(61.55.186.17,14)

(61.55.186.20,14)

(61.55.186.22,14)

(65.52.108.66,2)

(71.45.41.139,45)

(72.14.202.80,4)

(72.14.202.81,2)

(72.14.202.82,4)

(72.14.202.83,3)

(72.14.202.84,2)

(72.14.202.85,5)

(72.14.202.86,2)

(72.14.202.87,3)

(72.14.202.89,2)

(72.14.202.90,1)

(72.14.202.91,5)

(72.14.202.92,3)

(72.14.202.93,2)

(72.14.202.94,2)

(72.14.202.95,5)

(74.125.16.80,1)

(89.126.54.40,305)

(99.76.10.239,60)

(1.192.138.149,31)

(110.16.198.88,27)

(110.17.170.72,1)

(111.161.72.31,25)

(112.101.64.91,3)

(112.224.3.119,58)

(112.242.79.68,24)

(112.64.190.54,25)

(112.97.192.54,1)

(112.97.24.116,7)

(112.97.24.178,15)

(112.97.24.243,18)

(114.80.93.215,1)

(114.81.255.37,5)

(116.116.8.161,46)

(116.228.79.74,1)

(116.30.81.181,111)

(116.48.155.51,3)

(116.7.101.166,97)

(117.136.1.247,1)

(117.136.10.44,5)

(117.136.10.51,6)

(117.136.10.53,1)

(117.136.12.91,1)

(117.136.14.41,1)

(117.136.14.45,1)

(117.136.14.78,13)

(117.136.15.59,1)

(117.136.15.96,25)

(117.136.19.11,1)

(117.136.2.131,7)

(117.136.2.142,1)

(117.136.2.230,1)

(117.136.2.237,37)

(117.136.20.10,1)

(117.136.20.78,55)

(117.136.20.86,17)

(117.136.22.31,3)

(117.136.23.47,7)

(117.136.24.85,32)

(117.136.24.98,1)

(117.136.25.43,9)

(117.136.26.16,1)

(117.136.30.47,9)

(117.136.30.66,1)

(117.136.30.79,8)

(117.136.31.34,1)

(117.136.31.57,5)

(117.136.31.94,4)

(117.136.32.23,30)

(117.136.33.82,1)

(117.136.33.83,4)

(117.136.33.84,1)

(117.136.33.85,1)

(117.136.33.86,1)

(117.136.33.87,1)

(117.136.35.46,1)

(117.136.36.15,1)

(117.136.36.63,1)

(117.136.5.208,5)

(117.136.5.221,9)

(117.136.6.232,8)

(117.136.8.186,24)

(117.136.9.198,9)

(117.136.9.222,1)

(117.26.107.22,4)

(119.164.105.9,53)

(120.197.26.43,9)

(120.68.17.229,26)

(120.84.24.200,773)

(121.14.162.28,125)

(121.14.77.216,1)

(121.14.95.213,11)

(121.41.128.23,27)

(122.118.190.5,1)

(122.241.54.67,1)

(122.89.138.26,54)

(123.125.71.15,1)

(123.125.71.96,1)

(124.115.0.111,7)

(124.115.0.169,13)

(124.72.71.149,1)

(124.74.27.218,84)

(125.77.31.163,25)

(125.89.75.100,5)

(14.217.19.126,80)

(157.55.17.200,3)

(180.95.186.78,26)

(183.13.196.98,11)

(183.60.140.16,1)

(183.60.193.30,2)

(202.194.31.45,1)

(210.72.33.200,3)

(211.137.59.23,4)

(211.137.59.33,43)

(211.139.92.11,40)

(211.140.5.100,34)

(211.140.5.103,43)

(211.140.5.114,9)

(211.140.5.116,6)

(211.140.5.122,1)

(211.140.7.199,4)

(211.140.7.200,4)

(211.141.86.10,9)

(218.1.102.166,27)

(218.16.245.42,24)

(218.19.42.168,181)

(218.20.24.203,4597)

(218.205.245.7,1)

(218.213.137.2,28)

(220.231.59.40,1)

(221.176.4.134,8)

(222.170.20.46,11)

(222.186.17.98,2)

(222.73.191.55,124)

(222.73.75.245,7)

(27.115.124.75,470)

(58.242.249.66,2)

(58.249.34.251,7)

(59.151.120.36,31)

(59.151.120.38,59)

(59.61.141.119,26)

(60.247.116.29,28)

(61.154.14.122,61)

(61.155.206.81,165)

(61.164.72.118,27)

(61.50.174.137,1)

(65.52.109.151,3)

(66.249.71.135,19)

(66.249.71.136,16)

(66.249.71.137,14)

(72.14.199.185,4)

(72.14.199.186,4)

(72.14.199.187,2)

(72.30.142.220,3)

(110.75.174.219,1)

(110.75.174.221,1)

(110.75.174.223,1)

(112.64.188.188,10)

(112.64.188.217,7)

(112.64.190.235,16)

(112.64.190.237,9)

(112.64.191.122,4)

(113.57.218.226,45)

(113.90.101.196,22)

(114.106.216.63,24)

(114.215.28.225,2)

(114.247.10.132,243)

(114.43.237.117,167)

(114.98.146.181,26)

(115.168.51.143,8)

(115.168.76.178,3)

(115.236.48.226,439)

(116.235.194.89,171)

(117.135.129.28,8)

(117.135.129.58,2)

(117.135.129.59,7)

(117.136.10.141,30)

(117.136.10.158,21)

(117.136.10.180,9)

(117.136.10.186,4)

(117.136.11.131,1)

(117.136.11.145,1)

(117.136.11.190,1)

(117.136.12.147,1)

(117.136.12.183,4)

(117.136.12.192,32)

(117.136.12.206,4)

(117.136.12.209,4)

(117.136.15.110,1)

(117.136.15.146,5)

(117.136.16.131,1)

(117.136.16.142,1)

(117.136.16.201,30)

(117.136.16.203,1)

(117.136.19.105,10)

(117.136.19.148,7)

(117.136.19.198,1)

(117.136.23.130,3)

(117.136.23.238,30)

(117.136.23.253,4)

(117.136.24.130,1)

(117.136.24.131,6)

(117.136.24.200,1)

(117.136.24.201,21)

(117.136.26.137,1)

(117.136.27.251,1)

(117.136.30.147,3)

(117.136.30.152,5)

(117.136.31.144,1647)

(117.136.31.147,65)

(117.136.31.149,1)

(117.136.31.150,1)

(117.136.31.152,6)

(117.136.31.158,7)

(117.136.31.177,1)

(117.136.33.188,1)

(117.136.33.206,5)

(117.136.37.132,1)

(118.192.33.111,4)

(119.146.220.12,1850)

(120.204.201.77,5)

(121.14.162.124,124)

(121.28.205.250,42)

(123.120.41.159,2)

(123.124.240.11,1)

(123.147.244.39,37)

(124.115.10.252,1)

(124.207.169.57,1)

(124.207.169.59,3)

(124.238.242.36,13)

(124.238.242.43,18)

(124.238.242.47,26)

(124.238.242.65,13)

(124.238.242.68,13)

(14.153.238.175,2)

(14.213.176.184,133)

(159.226.202.12,2)

(159.226.202.13,2)

(175.136.16.158,2)

(180.153.201.34,12)

(180.153.201.35,9)

(180.153.227.27,3)

(180.153.227.28,4)

(180.153.227.29,5)

(180.153.227.31,2)

(180.153.227.32,3)

(180.153.227.34,2)

(180.153.227.36,2)

(180.153.227.37,4)

(180.153.227.40,2)

(180.153.227.41,3)

(180.153.227.42,1)

(180.153.227.44,3)

(180.153.227.45,1)

(180.153.227.47,1)

(180.153.227.52,1)

(180.153.227.53,5)

(180.153.227.54,1)

(180.153.227.55,6)