标题
提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档
一、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。
二、实验平台
已经配置完成的Hadoop伪分布式环境。
三. 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。 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
需要首先删除HDFS中与当前Linux用户hadoop对应的input和output目录(即HDFS中的“/user/hadoop/input”和“/user/hadoop/output”目录),这样确保后面程序运行不会出现问题
cd /usr/local/hadoop
./bin/hdfs dfs -rm -r input
./bin/hdfs dfs -rm -r output
然后,再在HDFS中新建与当前Linux用户hadoop对应的input目录,即“/user/hadoop/input”目录
cd /usr/local/hadoop
./bin/hdfs dfs -mkdir input
创建A.txt B.txt,输入上述内容
vi A.txt
vi B.txt
将A,B上传到HDFS中
cd /usr/local/hadoop
./bin/hdfs dfs -put ./A.txt input
./bin/hdfs dfs -put ./B.txt input
运行代码:
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 {
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(""));
}
}
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{
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"};
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);
}
}
编译运行: 查看实验结果:
cd /usr/local/hadoop
./bin/hdfs dfs -cat output/*
(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。 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 需要首先删除HDFS中与当前Linux用户hadoop对应的input和output目录(即HDFS中的“/user/hadoop/input”和“/user/hadoop/output”目录),这样确保后面程序运行不会出现问题
cd /usr/local/hadoop
./bin/hdfs dfs -rm -r input
./bin/hdfs dfs -rm -r output
然后,再在HDFS中新建与当前Linux用户hadoop对应的input目录,即“/user/hadoop/input”目录
cd /usr/local/hadoop
./bin/hdfs dfs -mkdir input
创建test1.txt test2.txt test3,输入上述内容
vi test1.txt
vi test2.txt
vi test3.txt
将test1,test2,test3上传到HDFS中
cd /usr/local/hadoop
./bin/hdfs dfs -put ./test1.txt input
./bin/hdfs dfs -put ./test2.txt input
./bin/hdfs dfs -put ./test3.txt input
运行代码:
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.Partitioner;
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 {
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 text = value.toString();
data.set(Integer.parseInt(text));
context.write(data, new IntWritable(1));
}
}
public static class Reduce extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{
private static IntWritable line_num = new IntWritable(1);
public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException,InterruptedException{
for(IntWritable val : values){
context.write(line_num, key);
line_num = new IntWritable(line_num.get() + 1);
}
}
}
public static class Partition extends Partitioner<IntWritable, IntWritable>{
public int getPartition(IntWritable key, IntWritable value, int num_Partition){
int Maxnumber = 65223;
int bound = Maxnumber/num_Partition+1;
int keynumber = key.get();
for (int i = 0; i<num_Partition; i++){
if(keynumber<bound * (i+1) && keynumber>=bound * i){
return i;
}
}
return -1;
}
}
public static void main(String[] args) throws Exception{
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"};
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and sort");
job.setJarByClass(Merge.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setPartitionerClass(Partition.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);
}
}
编译运行: 查看实验结果:
cd /usr/local/hadoop
./bin/hdfs dfs -cat output/*
(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。 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
输出文件内容如下: grandchild grandparent Mark Jesse Mark Alice Philip Jesse Philip Alice Jone Jesse Jone Alice Steven Jesse Steven Alice Steven Frank Steven Mary Jone Frank Jone Mary 需要首先删除HDFS中与当前Linux用户hadoop对应的input和output目录(即HDFS中的“/user/hadoop/input”和“/user/hadoop/output”目录),这样确保后面程序运行不会出现问题
cd /usr/local/hadoop
./bin/hdfs dfs -rm -r input
./bin/hdfs dfs -rm -r output
然后,再在HDFS中新建与当前Linux用户hadoop对应的input目录,即“/user/hadoop/input”目录
cd /usr/local/hadoop
./bin/hdfs dfs -mkdir input
创建test1.txt,输入上述内容
vi test1.txt
将test1上传到HDFS中
cd /usr/local/hadoop
./bin/hdfs dfs -put ./test1.txt input
运行代码:
import java.io.IOException;
import java.util.*;
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{
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<Text> 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.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"};
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Single table join ");
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(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
编译运行:
查看实验结果:
cd /usr/local/hadoop
./bin/hdfs dfs -cat output/*
四、实验遇到的问题
问题1: 解决方法:引入hdfs包
问题2: 解决方法:hdfs的output目录已经存在,删除即可 问题三: 解决方法:引入yarn包
|