一、实验目的
- 通过实验掌握基本的MapReduce编程方法;
- 掌握用MapReduce解决一些常见的数据处理问题,包括数据去重计数、数据排序。
二、实验平台
- 操作系统:Linux
- Hadoop版本:2.6.0
三、实验步骤
(一)对访问同一个网站的用户去重计数。
注:文件userurl_20150911中,数据以”\t”隔开,用户手机号为第三列,网站主域为第17列
这个是记录用户访问了一个网站多少次。。。
将用户手机号同用户访问网站两个属性合在一起作为 key 值,其余和 wordcount 差不多,改改即可,不再赘述
import com.amazonaws.services.dynamodbv2.xspec.S;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
public class mr {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String str = value.toString();
if (str != null && !str.equals("")) {
String[] fa = str.split("\t");
String per = fa[2], web = fa[16];
context.write(new Text(per+'\t'+web),new IntWritable(1));
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
public static HashMap<String, Integer> mp;
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum=0;
for(IntWritable t:values)
sum++;
context.write(key,new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
FileSystem fs = FileSystem.get(conf);
Job job = Job.getInstance(conf, "merge and duplicate removal");
job.setJarByClass(mr.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/input4/userurl_20150911"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output4"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
正解:先将网站同用户一起作为主键map后,在reduce拆分获取用户访问网站去重后的数据,再次编写另一个程序进行计数即可
import com.amazonaws.services.dynamodbv2.xspec.S;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
public class mr {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String str = value.toString();
if (str != null && !str.equals("")) {
String[] fa = str.split("\t");
String per = fa[2], web = fa[16];
context.write(new Text(per+'\t'+web),new IntWritable(1));
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, Text> {
public static HashMap<String, Integer> mp;
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
String[] tmp = key.toString().split("\t");
String per = tmp[0], web = tmp[1];
// 此处主要存在有用户多次访问同一网站,需要再执行一边mapreduce
context.write(new Text(per+'\t'+web),new Text(""));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
FileSystem fs = FileSystem.get(conf);
Job job = Job.getInstance(conf, "merge and duplicate removal");
job.setJarByClass(mr.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/input4/userurl_20150911"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output4"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
接着第二道程序,这里就和wordcount一样了
import com.amazonaws.services.dynamodbv2.xspec.S;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
public class mr {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String str = value.toString();
if (str != null && !str.equals("")) {
String[] fa = str.split("\t");
String web = fa[1];
context.write(new Text(web), new IntWritable(1));
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
public static HashMap<String, Integer> mp;
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable t : values) sum += t.get();
context.write(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
FileSystem fs = FileSystem.get(conf);
Job job = Job.getInstance(conf, "merge and duplicate removal");
job.setJarByClass(mr.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/output4/part-r-00000"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output4/outnext"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
(二)对同一个用户不同记录产生的上下行流量求和后进行排序输出。
注:上行流量位于第25列,下行流量位于第26列
此处认为同一个用户不同记录为:同一用户访问的同一个网站的一条记录
import com.amazonaws.services.dynamodbv2.xspec.S;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.io.IntWritable.Comparator;
import org.apache.hadoop.io.WritableComparable;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
public class mr {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String str = value.toString();
if (str != null && !str.equals("")) {
String[] fa = str.split("\t");
String per = fa[2], web = fa[16], up = fa[24], down = fa[25];
int use = Integer.parseInt(up) + Integer.parseInt(down);
context.write(new Text(per + '\t' + web), new IntWritable(use));
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable t : values) {
sum = t.get();
context.write(key, new IntWritable(sum));
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
FileSystem fs = FileSystem.get(conf);
Job job = Job.getInstance(conf, "merge and duplicate removal");
job.setJarByClass(mr.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/input4/userurl_20150911"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/output5"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
四、实验总结及问题
- 学会使用什么做什么事情
MapReduce 模式设计,深入掌握 MapReduce 编程设计。
- 实验过程中遇到了什么问题?是如何解决的?
暂无
- 还有什么问题尚未解决?可能是什么原因导致的。
关于 Map 函数与 Reduce 函数之间数据传输,想通过自行创建一种数据类进行数据传输尚未成功。