实验四MapReduce编程实践实验

一、编程实现文件合并和去重操作

对于两个输入文件，即文件A和文件B，请编写MapReduce程序，对两个文件进行合并，并剔除其中重复的内容，得到一个新的输出文件C。下面是输入文件和输出文件的一个样例供参考。

    输入文件A的样例如下：

20150101 x

20150102 y

20150103 x

20150104 y

20150105 z

20150106 x

输入文件B的样例如下：

20150101 y

20150102 y

20150103 x

20150104 z

20150105 y

根据输入文件A和B合并得到的输出文件C的样例如下：

20150101 x

20150101 y

20150102 y

20150103 x

20150104 y

20150104 z

20150105 y

20150105 z

20150106 x

 

解题思路：

 

数据去重的最终目标是让原始数据中出现次数超过一次的数据在输出文件中只出现一次。由于shuffle过程会有合并相同key值记录的过程，会想到将不同文件中相同内容数据的Key设置成一样的，即是Map处理后是一样的，然后把交给Reduce，无论这个数据的value-list是怎么样，只要在最终结果输出它的key就行了。

1. 启动Hadoop

   cd /usr/local/hadoop

./sbin/start-dfs.sh

  2.创建文件A、B

    sudo mkdir MapReduce && cd MapReduce

sudo vim A

sudo vim B

 

 

 

 

 

 

  3.编写Java文件实现MapReduce

sudo vim Merge.java

源码：

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

 

public class Merge {

/**

 * @param args

 * 对A,B两个文件进行合并，并剔除其中重复的内容，得到一个新的输出文件C

 */

//重载map函数，直接将输入中的value复制到输出数据的key上

public static class Map extends Mapper<Object, Text, Text, Text>{

private static Text text = new Text();

public void map(Object key, Text value, Context context) throws IOException,InterruptedException{

text = value;

context.write(text, new Text(""));

}

}

 

//重载reduce函数，直接将输入中的key复制到输出数据的key上

public static class Reduce extends Reducer<Text, Text, Text, Text>{

public void reduce(Text key, Iterable<Text> values, Context context ) throws IOException,InterruptedException{

context.write(key, new Text(""));

}

}

 

public static void main(String[] args) throws Exception{

// TODO Auto-generated method stub

Configuration conf = new Configuration();

conf.set("fs.default.name","hdfs://localhost:9000");

String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */

if (otherArgs.length != 2) {

System.err.println("Usage: wordcount <in><out>");

System.exit(2);

}

Job job = Job.getInstance(conf,"Merge and duplicate removal");

job.setJarByClass(Merge.class);

job.setMapperClass(Map.class);

job.setCombinerClass(Reduce.class);

job.setReducerClass(Reduce.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(Text.class);

FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

System.exit(job.waitForCompletion(true) ? 0 : 1);

}

}

 

 

 

 

 

 

 

4.赋予用户相关权限

sudo chown -R hadoop /usr/local/hadoop

 

 5.添加编译所需的jar包

vim ~/.bashrc

export HADOOP_HOME=/usr/local/hadoop

exportCLASSPATH=$($HADOOP_HOME/bin/hadoop classpath):$CLASSPATH

source ~/.bashrc

 

 

 

 6.编译 Merge.java，打包生成的 class 文件为 jar 包

javac Merge.java

jar -cvf Merge.jar *.class

 

 

 

 7.使用刚生成的 Merge.jar 包

/usr/local/hadoop/bin/hadoop jar Merge.jar Merge

 

 8.查看输出结果

 /usr/local/hadoop/bin/hdfs dfs -cat output/*

 

 

 

二、编写程序实现对输入文件的排序

现在有多个输入文件，每个文件中的每行内容均为一个整数。要求读取所有文件中的整数，进行升序排序后，输出到一个新的文件中，输出的数据格式为每行两个整数，第一个数字为第二个整数的排序位次，第二个整数为原待排列的整数。下面是输入文件和输出文件的一个样例供参考。

输入文件1的样例如下：

33

37

12

40

输入文件2的样例如下：

4

16

39

5

输入文件3的样例如下：

1

45

25

根据输入文件1、2和3得到的输出文件如下：

1 1

2 4

3 5

4 12

5 16

6 25

7 33

8 37

9 39

10 40

11 45

 

Java代码：

package com.MergeSort;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

public class MergeSort {

public static class Map extends Mapper<Object,Text,IntWritable,IntWritable>{

private static IntWritable data=new IntWritable();

public void map(Object key,Text value,Context context) throws IOException, InterruptedException{

String line=value.toString();

data.set(Integer.parseInt(line));

context.write(data, new IntWritable(1));

}

}

public static class Reduce extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable>{

private static IntWritable linenum=new IntWritable(1);

public void reduce(IntWritable key,Iterable <IntWritable>values,Context context) throws IOException, InterruptedException{

for(IntWritable num:values){

context.write(linenum, key);

linenum=new IntWritable(linenum.get()+1);

}

 

}

}

 

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException{

Configuration conf=new Configuration();

conf.set("fs.defaultFS","hdfs://localhost:9000");

String[] str=new String[]{"input","output"};

String[] otherArgs=new GenericOptionsParser(conf,str).getRemainingArgs();

if(otherArgs.length!=2){

System.err.println("Usage:mergesort<in><out>");

System.exit(2);

}

Job job=Job.getInstance(conf,"mergesort");

job.setJarByClass(MergeSort.class);

job.setMapperClass(Map.class);

job.setReducerClass(Reduce.class);

job.setOutputKeyClass(IntWritable.class);

job.setOutputValueClass(IntWritable.class);

FileInputFormat.addInputPath(job,new Path(otherArgs[0]));

FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));

System.exit(job.waitForCompletion(true)?0:1);

}

}

 

 

三、对给定的表格进行信息挖掘
下面给出一个child-parent的表格，要求挖掘其中的父子辈关系，给出祖孙辈关系的表格。
输入文件内容如下：

 child parent

Steven        Lucy

Steven        Jack

Jone          Lucy

Jone          Jack

Lucy          Mary

Lucy          Frank

Jack          Alice

Jack          Jesse

David        Alice

David        Jesse

Philip        David

Philip        Alma

Mark        David

Mark        Alma

输出的文件内容如下：

grandchild       grandparent

Steven          Alice

Steven          Jesse

Jone            Alice

Jone            Jesse

Steven          Mary

Steven          Frank

Jone            Mary

Jone            Frank

Philip           Alice

Philip           Jesse

Mark           Alice

Mark           Jesse

Java代码：

package com.join;

import java.io.IOException;

import java.util.*;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class STjoin {

public static int time = 0;

    public static class Map extends Mapper<Object, Text, Text, Text> {

        public void map(Object key, Text value, Context context)

                throws IOException, InterruptedException {

            String child_name = new String();

            String parent_name = new String();

            String relation_type = new String();

            String line = value.toString();

            int i = 0;

            while (line.charAt(i) != ' ') {

                i++;

            }

            String[] values = { line.substring(0, i), line.substring(i + 1) };

            if (values[0].compareTo("child") != 0) {

                child_name = values[0];

                parent_name = values[1];

                relation_type = "1";

                context.write(new Text(values[1]), new Text(relation_type + "+"   + child_name + "+" + parent_name));

                relation_type = "2";

                context.write(new Text(values[0]), new Text(relation_type + "+"

                        + child_name + "+" + parent_name));

            }}}

    public static class Reduce extends Reducer<Text, Text, Text,Text> {

        public void reduce(Text key, Iterable values, Context context)

                throws IOException, InterruptedException {

            if (time == 0) {

                context.write(new Text("grand_child"), new Text("grand_parent"));

                time++;

            }

            int grand_child_num = 0;

            String grand_child[] = new String[10];

            int grand_parent_num = 0;

            String grand_parent[] = new String[10];

            Iterator ite = values.iterator();

            while (ite.hasNext()) {

                String record = ite.next().toString();

                int len = record.length();

                int i = 2;

                if (len == 0)

                    continue;

                char relation_type = record.charAt(0);

                String child_name = new String();

                String parent_name = new String();

                while (record.charAt(i) != '+') {

                    child_name = child_name + record.charAt(i);

                    i++;

                }

                i = i + 1;

                while (i < len) {

                    parent_name = parent_name + record.charAt(i);

                    i++;

                }

                if (relation_type == '1') {

                    grand_child[grand_child_num] = child_name;

                    grand_child_num++;

                } else {

                    grand_parent[grand_parent_num] = parent_name;

                    grand_parent_num++;

                }}

            if (grand_parent_num != 0 && grand_child_num != 0) {

                for (int m = 0; m < grand_child_num; m++) {

                    for (int n = 0; n < grand_parent_num; n++) {

                        context.write(new Text(grand_child[m]), new Text(grand_parent[n]));

                    }

                }

            } }}

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();

        conf.set("fs.defaultFS", "hdfs://localhost:9000");

        String[] otherArgs = new String[] { "input", "output" };

        if (otherArgs.length != 2) {

          System.err.println("Usage: Single Table Join  ");

             System.exit(2);}

         Job job = Job.getInstance(conf, "Single table join ");

         job.setJarByClass(STjoin.class);

         job.setMapperClass(Map.class);

         job.setReducerClass(Reduce.class);

         job.setOutputKeyClass(Text.class);

         job.setOutputValueClass(Text.class);

         FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

         FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

         System.exit(job.waitForCompletion(true) ? 0 : 1);

     }

}