Changes between Initial Version and Version 1 of Hadoop_Lab5_2

Timestamp:

Sep 15, 2009, 4:43:53 PM (15 years ago)

Author:

waue

Comment:

--

Hadoop_Lab5_2

@@ +1 @@
+{{{
+#!html
+<div style="text-align: center; color: blue"><big
+ style="font-weight: bold;"><big><big>Example</big></big></big></div>
+}}}
+
+[[PageOutline]]
+
+ = 個別編譯程式 =
+
+ == 1 mapper.java ==
+ 
+ 1. new
+ 
+ || File ->  || new ->  || mapper || 
+[[Image(wiki:waue/2009/0617:file-new-mapper.png)]]
+
+-----------
+
+ 2. create
+ 
+[[Image(wiki:waue/2009/0617:3-1.png)]]
+{{{
+#!sh
+source folder-> 輸入： icas/src
+Package : Sample
+Name -> : mapper
+}}}
+----------
+
+ 3. modify
+ 
+{{{
+#!java
+package Sample;
+
+import java.io.IOException;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reporter;
+
+public class mapper extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
+    private final static IntWritable one = new IntWritable(1);
+    private Text word = new Text();
+
+    public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
+      String line = value.toString();
+      StringTokenizer tokenizer = new StringTokenizer(line);
+      while (tokenizer.hasMoreTokens()) {
+        word.set(tokenizer.nextToken());
+        output.collect(word, one);
+      }
+    }
+  }
+
+}}}
+
+建立mapper.java後，貼入程式碼
+[[Image(wiki:waue/2009/0617:3-2.png)]]
+
+------------
+
+== 2 reducer.java ==
+
+ 1. new
+
+ * File -> new -> reducer
+[[Image(wiki:waue/2009/0617:file-new-reducer.png)]]
+
+-------
+ 2. create
+[[Image(wiki:waue/2009/0617:3-3.png)]]
+
+{{{
+#!sh
+source folder-> 輸入： icas/src
+Package : Sample
+Name -> : reducer
+}}}
+
+-----------
+
+ 3. modify 
+ 
+{{{
+#!java
+package Sample;
+
+import java.io.IOException;
+import java.util.Iterator;
+
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+
+public class reducer extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
+    public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
+      int sum = 0;
+      while (values.hasNext()) {
+        sum += values.next().get();
+      }
+      output.collect(key, new IntWritable(sum));
+    }
+  }
+}}}
+
+ * File -> new -> Map/Reduce Driver
+[[Image(wiki:waue/2009/0617:file-new-mr-driver.png)]]
+----------
+
+== 3 WordCount.java (main function) ==
+
+ 1. new
+
+建立WordCount.java，此檔用來驅動mapper 與 reducer，因此選擇 Map/Reduce Driver
+
+
+[[Image(wiki:waue/2009/0617:3-4.png)]]
+------------
+
+ 2. create
+
+{{{
+#!sh
+source folder-> 輸入： icas/src
+Package : Sample
+Name -> : WordCount.java
+}}}
+
+-------
+ 3. modify
+
+{{{
+#!java
+package Sample;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.FileOutputFormat;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.TextInputFormat;
+import org.apache.hadoop.mapred.TextOutputFormat;
+
+public class WordCount {
+
+   public static void main(String[] args) throws Exception {
+     JobConf conf = new JobConf(WordCount.class);
+     conf.setJobName("wordcount");
+
+     conf.setOutputKeyClass(Text.class);
+     conf.setOutputValueClass(IntWritable.class);
+
+     conf.setMapperClass(mapper.class);
+     conf.setCombinerClass(reducer.class);
+     conf.setReducerClass(reducer.class);
+
+     conf.setInputFormat(TextInputFormat.class);
+     conf.setOutputFormat(TextOutputFormat.class);
+
+    FileInputFormat.setInputPaths(conf, new Path("/user/hadooper/input"));
+    FileOutputFormat.setOutputPath(conf, new Path("lab5_out2"));
+
+     JobClient.runJob(conf);
+   }
+}
+}}}
+
+三個檔完成後並存檔後，整個程式建立完成
+[[Image(wiki:waue/2009/0617:3-5.png)]]
+
+-------
+
+ * 三個檔都存檔後，可以看到icas專案下的src，bin都有檔案產生，我們用指令來check
+ 
+{{{
+$ cd workspace/icas
+$ ls src/Sample/
+mapper.java  reducer.java  WordCount.java
+$ ls bin/Sample/
+mapper.class  reducer.class  WordCount.class
+}}}
+
+
+ = eclipse 可以產生出jar檔 =
+ 
+File -> Export -> java -> JAR file [[br]]
+-> next -> 
+--------
+選擇要匯出的專案 ->
+jarfile: /home/hadooper/mytest.jar -> [[br]]
+next ->
+--------
+next ->
+--------
+main class: 選擇有Main的class   -> [[br]]
+Finish
+--------
+
+ * 以上的步驟就可以在/home/hadooper/ 產生出你的 mytest.jar
+
+ 
+ = 用Makefile 來更快速編譯 =
+ * 程式常常修改，每次都做這些動作也很累很煩，讓我們來體驗一下'''用指令比用圖形介面操作還方便'''吧
+
+ ==1 產生Makefile 檔 ==
+
+{{{
+$ cd /home/hadooper/workspace/icas/
+$ gedit Makefile
+}}}
+
+ * 輸入以下Makefile的內容 (注意 ":" 後面要接 "tab" 而不是 "空白")
+{{{
+JarFile="sample-0.1.jar"
+MainFunc="Sample.WordCount"
+LocalOutDir="/tmp/output"
+HADOOP_BIN="/opt/hadoop/bin"
+
+all:jar run output clean
+
+jar:
+        jar -cvf ${JarFile} -C bin/ .
+
+run:
+        ${HADOOP_BIN}/hadoop jar ${JarFile} ${MainFunc} input output
+
+clean:
+        ${HADOOP_BIN}/hadoop fs -rmr output
+
+output:
+        rm -rf ${LocalOutDir}
+        ${HADOOP_BIN}/hadoop fs -get output ${LocalOutDir}
+        gedit ${LocalOutDir}/part-r-00000 & 
+
+help:
+        @echo "Usage:"
+        @echo " make jar     - Build Jar File."
+        @echo " make clean   - Clean up Output directory on HDFS."
+        @echo " make run     - Run your MapReduce code on Hadoop."
+        @echo " make output  - Download and show output file"
+        @echo " make help    - Show Makefile options."
+        @echo " "
+        @echo "Example:"
+        @echo " make jar; make run; make output; make clean"
+}}}
+
+ * 或是直接下載 [http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab5/Makefile Makefile] 吧
+{{{
+$ cd /home/hadooper/workspace/icas/
+$ wget http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab5/Makefile
+}}}
+
+ == 4.2.2 執行 ==
+ 
+ * 執行Makefile，可以到該目錄下，執行make [參數]，若不知道參數為何，可以打make 或 make help
+ * make 的用法說明
+
+{{{
+$ cd /home/hadooper/workspace/icas/
+$ make
+Usage:
+ make jar     - Build Jar File.
+ make clean   - Clean up Output directory on HDFS.
+ make run     - Run your MapReduce code on Hadoop.
+ make output  - Download and show output file
+ make help    - Show Makefile options.
+ 
+Example:
+ make jar; make run; make output; make clean
+}}}
+
+ * 下面提供各種make 的參數
+ 
+ == make jar ==
+ * 1. 編譯產生jar檔
+ 
+{{{
+$ make jar
+}}}
+
+ == make run ==
+ * 2. 跑我們的wordcount 於hadoop上
+
+{{{
+$ make run
+}}}
+
+ * make run基本上能正確無誤的運作到結束，因此代表我們在eclipse編譯的程式可以順利在hadoop0.18.3的平台上運行。
+
+ * 而回到eclipse視窗，我們可以看到下方視窗run完的job會呈現出來；左方視窗也多出output資料夾，part-r-00000就是我們的結果檔
+ 
+[[Image(wiki:waue/2009/0617:4-1.png)]]
+------
+ * 因為有設定完整的javadoc, 因此可以得到詳細的解說與輔助
+[[Image(wiki:waue/2009/0617:4-2.png)]]
+
+ == make output ==
+ * 3. 這個指令是幫助使用者將結果檔從hdfs下載到local端，並且用gedit來開啟你的結果檔
+
+{{{
+$ make output
+}}}
+
+ == make clean ==
+ * 4. 這個指令用來把hdfs上的output資料夾清除。如果你還想要在跑一次make run，請先執行make clean，否則hadoop會告訴你，output資料夾已經存在，而拒絕工作喔！
+ 
+{{{
+$ make clean
+}}}
+
+
+= 練習：匯入專案 = 
+ * 將 [http://trac.nchc.org.tw/cloud/raw-attachment/wiki/Hadoop_Lab5/hadoop_sample_codes.zip nchc-sample] 給匯入到eclipse 內開發吧！