| | 1 | [[PageOutline]] |
| | 2 | |
| | 3 | ◢ <[wiki:NCTU110329/Lab5 實作五]> | <[wiki:NCTU110329 回課程大綱]> ▲ | <[wiki:NCTU110329/Lab7 實作七]> ◣ |
| | 4 | |
| | 5 | = 實作六 = |
| | 6 | |
| | 7 | {{{ |
| | 8 | #!html |
| | 9 | <div style="text-align: center;"><big style="font-weight: bold;"><big>MapReduce 程式編譯<br/>Compiling Hadoop MapReduce Java Program</big></big></div> |
| | 10 | }}} |
| | 11 | |
| | 12 | = Practice 1 : Word Count (Basic) = |
| | 13 | |
| | 14 | * 上傳內容到 HDFS 內[[BR]]upload data to HDFS |
| | 15 | |
| | 16 | {{{ |
| | 17 | $ cd /opt/hadoop |
| | 18 | $ mkdir lab4_input |
| | 19 | $ echo "I like NCHC Cloud Course." > lab4_input/input1 |
| | 20 | $ echo "I like nchc Cloud Course, and we enjoy this course." > lab4_input/input2 |
| | 21 | $ bin/hadoop fs -put lab4_input lab4_input |
| | 22 | $ bin/hadoop fs -ls lab4_input |
| | 23 | }}} |
| | 24 | |
| | 25 | * 下載 [http://secuse.nchc.org.tw/class/WordCount.java WordCount.java] 並存到/opt/hadoop;[[BR]]Download [http://trac.nchc.org.tw/cloud/raw-attachment/wiki/WordCount/WordCount.java WordCount.java] and save to /opt/hadoop |
| | 26 | {{{ |
| | 27 | ~$ cd /opt/hadoop |
| | 28 | /opt/hadoop$ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/WordCount/WordCount.java |
| | 29 | }}} |
| | 30 | |
| | 31 | * 運作程式[[BR]]Compile WordCount.java and run it by '''hadoop jar''' command |
| | 32 | |
| | 33 | {{{ |
| | 34 | $ mkdir MyJava |
| | 35 | $ javac -classpath hadoop-*-core.jar -d MyJava WordCount.java |
| | 36 | $ jar -cvf wordcount.jar -C MyJava . |
| | 37 | $ bin/hadoop jar wordcount.jar WordCount lab4_input/ lab4_out1/ |
| | 38 | $ bin/hadoop fs -cat lab4_out1/part-00000 |
| | 39 | }}} |
| | 40 | |
| | 41 | * lab4_out1 執行結果 [[BR]]You should see results like this : |
| | 42 | {{{ |
| | 43 | #!text |
| | 44 | Cloud 2 |
| | 45 | Course, 1 |
| | 46 | Course. 1 |
| | 47 | I 2 |
| | 48 | NCHC 1 |
| | 49 | and 1 |
| | 50 | course. 1 |
| | 51 | enjoy 1 |
| | 52 | like 2 |
| | 53 | nchc 1 |
| | 54 | this 1 |
| | 55 | we 1 |
| | 56 | }}} |
| | 57 | ----- |
| | 58 | |
| | 59 | = Practice 2 : Word Count (Advanced) = |
| | 60 | |
| | 61 | {{{ |
| | 62 | $ echo "\." >pattern.txt && echo "\," >>pattern.txt |
| | 63 | $ bin/hadoop fs -put pattern.txt ./ |
| | 64 | $ mkdir MyJava2 |
| | 65 | }}} |
| | 66 | |
| | 67 | |
| | 68 | * 下載 [raw-attachment:wiki:Hadoop_Lab4:WordCount2.java WordCount2.java] 並存到/opt/hadoop;[[BR]]Download [raw-attachment:wiki:Hadoop_Lab4:WordCount2.java WordCount2.java] to /opt/hadoop |
| | 69 | {{{ |
| | 70 | ~$ cd /opt/hadoop |
| | 71 | /opt/hadoop$ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab4/WordCount2.java |
| | 72 | }}} |
| | 73 | |
| | 74 | {{{ |
| | 75 | $ javac -classpath hadoop-*-core.jar -d MyJava2 WordCount2.java |
| | 76 | $ jar -cvf wordcount2.jar -C MyJava2 . |
| | 77 | $ bin/hadoop jar wordcount2.jar WordCount2 lab4_input lab4_out2 -skip pattern.txt |
| | 78 | $ bin/hadoop fs -cat lab4_out2/part-00000 |
| | 79 | }}} |
| | 80 | |
| | 81 | * lab4_out2 執行結果[[BR]]You should see results like this: |
| | 82 | {{{ |
| | 83 | #!text |
| | 84 | Cloud 2 |
| | 85 | Course 2 |
| | 86 | I 2 |
| | 87 | NCHC 1 |
| | 88 | and 1 |
| | 89 | course 1 |
| | 90 | enjoy 1 |
| | 91 | like 2 |
| | 92 | nchc 1 |
| | 93 | this 1 |
| | 94 | we 1 |
| | 95 | }}} |
| | 96 | |
| | 97 | * Let's given case insensitive and ignore pattern for this example |
| | 98 | {{{ |
| | 99 | /opt/hadoop$ bin/hadoop jar wordcount2.jar WordCount2 -Dwordcount.case.sensitive=false lab4_input lab4_out3 -skip pattern.txt |
| | 100 | /opt/hadoop$ bin/hadoop fs -cat lab4_out3/part-00000 |
| | 101 | }}} |
| | 102 | |
| | 103 | * lab4_out3 執行結果[[BR]]You should see results like this: |
| | 104 | {{{ |
| | 105 | #!text |
| | 106 | and 1 |
| | 107 | cloud 2 |
| | 108 | course 3 |
| | 109 | enjoy 1 |
| | 110 | i 2 |
| | 111 | like 2 |
| | 112 | nchc 2 |
| | 113 | this 1 |
| | 114 | we 1 |
| | 115 | }}} |