MapReduce编程初级实践(共7页).docx

《MapReduce编程初级实践(共7页).docx》由会员分享，可在线阅读，更多相关《MapReduce编程初级实践(共7页).docx（7页珍藏版）》请在淘文阁 - 分享文档赚钱的网站上搜索。

1、精选优质文档-倾情为你奉上实验3 MapReduce编程初级实践1. 实验目的1.通过实验掌握基本的MapReduce编程方法；2.掌握用MapReduce解决一些常见的数据处理问题，包括数据去重、数据排序和数据挖掘等。2. 实验平台已经配置完成的Hadoop伪分布式环境。3. 实验内容和要求1.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。实验最终结果（合并的文件）：代码如下：package com.Merge;import java.io

2、.IOException;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.FileInpu

3、tFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;public class Merge public static class Map extends Mapper private static Text text = new Text(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException text = value; context.write(text,

4、new Text(); public static class Reduce extends Reducer public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException context.write(key, new Text(); public static void main(String args) throws Exception Configuration conf = new Configuration(); conf.set(fs.de

5、faultFS, hdfs:/localhost:9000); String otherArgs = new String input, output ; if (otherArgs.length != 2) System.err.println(Usage: Merge and duplicate removal ); System.exit(2); Job job = Job.getInstance(conf, Merge and duplicate removal); job.setJarByClass(Merge.class); job.setMapperClass(Map.class

6、); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs0); FileOutputFormat.setOutputPath(job, new Path(otherArgs1); System.exit(job.waitForCompletion(true) ? 0 : 1); 2. 编写程序实现对输入文件的排序现在有多个输入文件

7、，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。实验结果截图：代码如下：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;impor

8、t 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 MergeSort p

9、ublic static class Map extends Mapper 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

10、 static class Reduce extends Reducer private static IntWritable linenum = new IntWritable(1); public void reduce(IntWritable key, Iterable values, Context context) throws IOException, InterruptedException for (IntWritable val : values) context.write(linenum, key); linenum = new IntWritable(linenum.g

11、et() + 1); public static void main(String args) throws Exception Configuration conf = new Configuration(); conf.set(fs.defaultFS, hdfs:/localhost:9000); String otherArgs = new String input2, output2 ; /* 直接设置输入参数 */ if (otherArgs.length != 2) System.err.println(Usage: mergesort ); System.exit(2); Jo

12、b 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(otherArgs0); FileOutputForm

13、at.setOutputPath(job, new Path(otherArgs1); System.exit(job.waitForCompletion(true) ? 0 : 1); 3. 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。实验最后结果截图如下：代码如下：package com.join;import java.io.IOException;import java.util.*;import org.apache.hadoop.conf.Configuration;import org.apache.hado

14、op.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 c

15、lass STjoin public static int time = 0; public static class Map extends Mapper 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 = val

16、ue.toString(); int i = 0; while (line.charAt(i) != ) i+; String values = line.substring(0, i), line.substring(i + 1) ; if (pareTo(child) != 0) child_name = values0; parent_name = values1; relation_type = 1; context.write(new Text(values1), new Text(relation_type + + + child_name + + + parent_name);

17、relation_type = 2; context.write(new Text(values0), new Text(relation_type + + + child_name + + + parent_name); public static class Reduce extends Reducer public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException if (time = 0) context.write(new Text(gran

18、d_child), new Text(grand_parent); time+; int grand_child_num = 0; String grand_child = new String10; int grand_parent_num = 0; String grand_parent = new String10; Iterator ite = values.iterator(); while (ite.hasNext() String record = ite.next().toString(); int len = record.length(); int i = 2; if (l

19、en = 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

20、) grand_childgrand_child_num = child_name; grand_child_num+; else grand_parentgrand_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_childm), new

21、Text( grand_parentn); public static void main(String args) throws Exception Configuration conf = new Configuration(); conf.set(fs.defaultFS, hdfs:/localhost:9000); String otherArgs = new String input3, output3 ; if (otherArgs.length != 2) System.err.println(Usage: Single Table Join ); System.exit(2)

22、; 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(otherArgs0); FileOutputFormat.s

23、etOutputPath(job, new Path(otherArgs1); System.exit(job.waitForCompletion(true) ? 0 : 1); 4. 实验报告云计算 实验报告题目：MapReduce编程初级实践姓名包生友日期：2016/12/20实验环境：机房的虚拟机上配置好的环境解决问题的思路：根据老师给的代码进行操作实验内容与完成情况：已完成，与同学商量后仍有部分代码尚未知道其作用所在出现的问题：执行之后，出现未找到main函数情况，再次执行会报错，说文件已经存在。解决方案（列出遇到的问题和解决办法，列出没有解决的问题）：问题：1.执行之后，出现未找到main函数情况 2. 再次执行会报错，说文件已经存在。解决办法：删除输出文件即可（程序执行时输出文件不能存在）5. 实验总结通过本次实验，使我掌握基本的MapReduce编程方法；掌握用MapReduce解决一些常见的数据处理问题，包括数据去重、数据排序和数据挖掘等。短暂的云计算课程实验到此结束，到我知道对云计算的学习是没有尽头的。专心-专注-专业