| | 1 | {{{ |
| | 2 | #!html |
| | 3 | <div style="text-align: center;"><big |
| | 4 | style="font-weight: bold;"><big><big>實做四: Hadoop 程式編譯</big></big></big></div> |
| | 5 | }}} |
| | 6 | [[PageOutline]] |
| | 7 | |
| | 8 | = 練習 0 : hello : 印出我們的 key value 為何 = |
| | 9 | |
| | 10 | |
| | 11 | |
| | 12 | * 下載 [http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab4/nchc-example.jar nchc-example.jar] |
| | 13 | {{{ |
| | 14 | $ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab4/nchc-example.jar |
| | 15 | }}} |
| | 16 | |
| | 17 | * 執行客製化的hadoop 程式 |
| | 18 | |
| | 19 | {{{ |
| | 20 | $ bin/hadoop jar nchc-example.jar |
| | 21 | }}} |
| | 22 | * 輸出結果 |
| | 23 | {{{ |
| | 24 | ****************************************** |
| | 25 | 歡迎使用 NCHC.Hadoop 的運算功能 |
| | 26 | 指令: |
| | 27 | Hadoop jar nchc-example-*.jar <功能> |
| | 28 | 功能: |
| | 29 | wordcount: 計算輸入資料夾內分別在每個檔案的字數統計 |
| | 30 | mwc: 統合計算所有輸入檔的字數統計 |
| | 31 | grep: 算出包指定字串的個數 |
| | 32 | nchcgrep: 整合來源檔內的每個字與其所有出現的所在列 |
| | 33 | hello: 印出內容並統計累進字數 |
| | 34 | ****************************************** |
| | 35 | |
| | 36 | }}} |
| | 37 | * 使用hello |
| | 38 | {{{ |
| | 39 | $ bin/hadoop jar nchc-example.jar hello |
| | 40 | }}} |
| | 41 | * 使用提示: |
| | 42 | {{{ |
| | 43 | hello <inDir> <outDir> <m> <r> |
| | 44 | }}} |
| | 45 | |
| | 46 | * 範例: |
| | 47 | |
| | 48 | {{{ |
| | 49 | $ bin/hadoop jar nchc-example.jar hello lab3_input lab4_out6 1 1 |
| | 50 | }}} |
| | 51 | |
| | 52 | [wiki:Hadoop_Lab4_hello_018 hello 程式碼] |
| | 53 | |
| | 54 | = 練習 1 : Word Count 初級版 = |
| | 55 | |
| | 56 | * 上傳內容到hdfs內 |
| | 57 | |
| | 58 | {{{ |
| | 59 | $ cd /opt/hadoop |
| | 60 | $ mkdir lab4_input |
| | 61 | $ echo "I like NCHC Cloud Course." > lab4_input/input1 |
| | 62 | $ echo "I like nchc Cloud Course, and we enjoy this course." > lab4_input/input2 |
| | 63 | $ bin/hadoop fs -put lab4_input lab4_input |
| | 64 | $ bin/hadoop fs -ls lab4_input |
| | 65 | }}} |
| | 66 | |
| | 67 | * 下載 [raw-attachment:wiki:jazz/Hadoop_Lab6:WordCount.java WordCount.java] 並存到/opt/hadoop; |
| | 68 | {{{ |
| | 69 | $ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/jazz/Hadoop_Lab6/WordCount.java |
| | 70 | }}} |
| | 71 | |
| | 72 | * 運作程式 |
| | 73 | |
| | 74 | {{{ |
| | 75 | $ mkdir MyJava |
| | 76 | $ javac -classpath hadoop-*-core.jar -d MyJava WordCount.java |
| | 77 | $ jar -cvf wordcount.jar -C MyJava . |
| | 78 | $ bin/hadoop jar wordcount.jar WordCount lab4_input/ lab4_out1/ |
| | 79 | $ bin/hadoop fs -cat lab4_out1/part-00000 |
| | 80 | }}} |
| | 81 | |
| | 82 | * lab4_out1 執行結果 |
| | 83 | {{{ |
| | 84 | #!text |
| | 85 | Cloud 2 |
| | 86 | Course, 1 |
| | 87 | Course. 1 |
| | 88 | I 2 |
| | 89 | NCHC 1 |
| | 90 | and 1 |
| | 91 | course. 1 |
| | 92 | enjoy 1 |
| | 93 | like 2 |
| | 94 | nchc 1 |
| | 95 | this 1 |
| | 96 | we 1 |
| | 97 | }}} |
| | 98 | ----- |
| | 99 | |
| | 100 | = 練習 2 : Word Count 進階版 = |
| | 101 | |
| | 102 | {{{ |
| | 103 | $ echo "\." >pattern.txt && echo "\," >>pattern.txt |
| | 104 | $ bin/hadoop fs -put pattern.txt ./ |
| | 105 | $ mkdir MyJava2 |
| | 106 | }}} |
| | 107 | |
| | 108 | |
| | 109 | * 下載 [raw-attachment:wiki:jazz/Hadoop_Lab6:WordCount2.java WordCount2.java] 並存到/opt/hadoop; |
| | 110 | {{{ |
| | 111 | $ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/jazz/Hadoop_Lab6/WordCount2.java |
| | 112 | }}} |
| | 113 | |
| | 114 | {{{ |
| | 115 | $ javac -classpath hadoop-*-core.jar -d MyJava2 WordCount2.java |
| | 116 | $ jar -cvf wordcount2.jar -C MyJava2 . |
| | 117 | $ bin/hadoop jar wordcount2.jar WordCount2 lab4_input lab4_out2 -skip pattern.txt |
| | 118 | $ bin/hadoop fs -cat lab4_out2/part-00000 |
| | 119 | }}} |
| | 120 | |
| | 121 | * lab4_out2 執行結果 |
| | 122 | {{{ |
| | 123 | #!text |
| | 124 | Cloud 2 |
| | 125 | Course 2 |
| | 126 | I 2 |
| | 127 | NCHC 1 |
| | 128 | and 1 |
| | 129 | course 1 |
| | 130 | enjoy 1 |
| | 131 | like 2 |
| | 132 | nchc 1 |
| | 133 | this 1 |
| | 134 | we 1 |
| | 135 | }}} |
| | 136 | |
| | 137 | {{{ |
| | 138 | $ bin/hadoop jar wordcount2.jar WordCount2 -Dwordcount.case.sensitive=false lab4_input lab4_out3 -skip pattern.txt |
| | 139 | $ bin/hadoop fs -cat lab4_out3/part-00000 |
| | 140 | }}} |
| | 141 | |
| | 142 | * lab4_out3 執行結果 |
| | 143 | {{{ |
| | 144 | #!text |
| | 145 | and 1 |
| | 146 | cloud 2 |
| | 147 | course 3 |
| | 148 | enjoy 1 |
| | 149 | i 2 |
| | 150 | like 2 |
| | 151 | nchc 2 |
| | 152 | this 1 |
| | 153 | we 1 |
| | 154 | }}} |