| | 1 | [[PageOutline]] |
| | 2 | |
| | 3 | ◢ <[wiki:III150110/Lab8 實作八]> | <[wiki:III150110 回課程大綱]> ▲ | <[wiki:III150110/Lab10 實作十]> ◣ |
| | 4 | |
| | 5 | = 實作九 Lab 9 = |
| | 6 | |
| | 7 | {{{ |
| | 8 | #!html |
| | 9 | <div style="text-align: center;"><big style="font-weight: bold;"><big>練習豬的拉丁語<br/>Pig Latin in Practice</big></big></div> |
| | 10 | }}} |
| | 11 | |
| | 12 | {{{ |
| | 13 | #!text |
| | 14 | 以下練習,請連線至 hdp01.3du.me 操作。底下的 userXX 等於您的用戶名稱。 |
| | 15 | 以下練習,請連線至 hdp02.3du.me 操作。底下的 userXX 等於您的用戶名稱。 |
| | 16 | 以下練習,請連線至 hdp03.3du.me 操作。底下的 userXX 等於您的用戶名稱。 |
| | 17 | 以下練習,請連線至 hdp04.3du.me 操作。底下的 userXX 等於您的用戶名稱。 |
| | 18 | }}} |
| | 19 | |
| | 20 | == Aggregation (Local Mode) == |
| | 21 | |
| | 22 | {{{ |
| | 23 | ~$ wget http://www.hadoop.tw/excite-small.log |
| | 24 | ~$ pig -x local |
| | 25 | grunt> log = LOAD 'excite-small.log' AS (user, timestamp, query); |
| | 26 | grunt> grpd = GROUP log BY user; |
| | 27 | grunt> cntd = FOREACH grpd GENERATE group, COUNT(log); |
| | 28 | grunt> STORE cntd INTO 'lab8_out1'; |
| | 29 | grunt> quit |
| | 30 | ~$ head lab8_out1/part-* |
| | 31 | }}} |
| | 32 | |
| | 33 | == Filter (Local Mode) == |
| | 34 | |
| | 35 | {{{ |
| | 36 | ~$ pig -x local |
| | 37 | grunt> log = LOAD 'excite-small.log' AS (user, timestamp, query); |
| | 38 | grunt> grpd = GROUP log BY user; |
| | 39 | grunt> cntd = FOREACH grpd GENERATE group, COUNT(log) AS cnt; |
| | 40 | grunt> fltrd = FILTER cntd BY cnt > 50; |
| | 41 | grunt> STORE fltrd INTO 'lab8_out2'; |
| | 42 | grunt> quit |
| | 43 | ~$ head lab8_out2/part-* |
| | 44 | }}} |
| | 45 | |
| | 46 | == Sorting (Local Mode) == |
| | 47 | |
| | 48 | {{{ |
| | 49 | ~$ pig -x local |
| | 50 | grunt> log = LOAD 'excite-small.log' AS (user, timestamp, query); |
| | 51 | grunt> grpd = GROUP log BY user; |
| | 52 | grunt> cntd = FOREACH grpd GENERATE group, COUNT(log) AS cnt; |
| | 53 | grunt> fltrd = FILTER cntd BY cnt > 50; |
| | 54 | grunt> srtd = ORDER fltrd BY cnt; |
| | 55 | grunt> STORE srtd INTO 'lab8_out3'; |
| | 56 | grunt> quit |
| | 57 | ~$ head lab8_out3/part-* |
| | 58 | }}} |
| | 59 | |
| | 60 | == Connect Pig to Hadoop (Full Distributed Mode) == |
| | 61 | |
| | 62 | {{{ |
| | 63 | ~$ hadoop fs -put excite-small.log . |
| | 64 | ~$ pig |
| | 65 | grunt> log = LOAD 'excite-small.log' AS (user, timestamp, query); |
| | 66 | grunt> grpd = GROUP log BY user; |
| | 67 | grunt> cntd = FOREACH grpd GENERATE group, COUNT(log); |
| | 68 | grunt> STORE cntd INTO 'lab8_out1'; |
| | 69 | grunt> quit |
| | 70 | ~$ hadoop fs -cat lab8_out1/part-00000 |
| | 71 | }}} |