实验-MapReduce编程初级实践 作者： 日期：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.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.FileInputFormat;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, 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.defaultFS, 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); 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，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;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 MergeSort public 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 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.get() + 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); 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(otherArgs0); FileOutputFormat.setOutputPath(job, new Path(otherArgs1); System.exit(job.waitForCompletion(true) ? 0 : 1); 3. 对给定的表格进行信