實驗3-MapReduce編程初級實踐

1、實驗3 MapReduce編程初級實踐1. 實驗目的1.通過實驗掌握基本的MapReduce編程方法；2.掌握用MapReduce解決一些常見的數(shù)據(jù)處理問題，包括數(shù)據(jù)去重、數(shù)據(jù)排序和數(shù)據(jù)挖掘等。2. 實驗平臺已經(jīng)配置完成的Hadoop偽分布式環(huán)境。3. 實驗內(nèi)容和要求1.編程實現(xiàn)文件合并和去重操作對于兩個輸入文件，即文件A和文件B，請編寫MapReduce程序，對兩個文件進行合并，并剔除其中重復的內(nèi)容，得到一個新的輸出文件C。下面是輸入文件和輸出文件的一個樣例供參考。實驗最終結(jié)果（合并的文件）：代碼如下：package com.Merge;import java.io.IOException;

2、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;impor

3、t 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, new Text(); p

4、ublic 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.defaultFS, hdfs

5、:/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); job.setRed

6、ucerClass(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. 編寫程序?qū)崿F(xiàn)對輸入文件的排序現(xiàn)在有多個輸入文件，每個文件中的每行內(nèi)容均為

7、一個整數(shù)。要求讀取所有文件中的整數(shù)，進行升序排序后，輸出到一個新的文件中，輸出的數(shù)據(jù)格式為每行兩個整數(shù)，第一個數(shù)字為第二個整數(shù)的排序位次，第二個整數(shù)為原待排列的整數(shù)。下面是輸入文件和輸出文件的一個樣例供參考。實驗結(jié)果截圖：代碼如下：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;import org.apache.

8、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 public static

9、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 static class

10、 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.get() + 1); pu

11、blic static void main(String args) throws Exception Configuration conf = new Configuration(); conf.set(fs.defaultFS, hdfs:/localhost:9000); String otherArgs = new String input2, output2 ; /* 直接設置輸入?yún)?shù) */ if (otherArgs.length != 2) System.err.println(Usage: mergesort ); System.exit(2); Job job = Job.g

12、etInstance(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); FileOutputFormat.setOutputP

13、ath(job, new Path(otherArgs1); System.exit(job.waitForCompletion(true) ? 0 : 1); 3. 對給定的表格進行信息挖掘下面給出一個child-parent的表格，要求挖掘其中的父子輩關(guān)系，給出祖孫輩關(guān)系的表格。實驗最后結(jié)果截圖如下：代碼如下：package com.join;import java.io.IOException;import java.util.*;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;im

14、port 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 p

15、ublic 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 = value.toString()

16、; 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); re

17、lation_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(grand_

18、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 (len

19、 = 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 Te

21、xt( 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); Job job = Job.getInstance(conf, Single table join ); job.se