07．Mapreduce实例——二次排序
实验原理
在Map阶段，使用job.setInputFormatClass定义的InputFormat将输入的数据集分割成小数据块splites，同时InputFormat提供一个RecordReder的实现。本实验中使用的是TextInputFormat，他提供的RecordReder会将文本的字节偏移量作为key，这一行的文本作为value。这就是自定义Map的输入是<LongWritable, Text>的原因。然后调用自定义Map的map方法，将一个个<LongWritable, Text>键值对输入给Map的map方法。注意输出应该符合自定义Map中定义的输出<IntPair, IntWritable>。最终是生成一个List<IntPair, IntWritable>。在map阶段的最后，会先调用job.setPartitionerClass对这个List进行分区，每个分区映射到一个reducer。每个分区内又调用job.setSortComparatorClass设置的key比较函数类排序。可以看到，这本身就是一个二次排序。 如果没有通过job.setSortComparatorClass设置key比较函数类，则可以使用key实现的compareTo方法进行排序。 在本实验中，就使用了IntPair实现的compareTo方法。
在Reduce阶段，reducer接收到所有映射到这个reducer的map输出后，也是会调用job.setSortComparatorClass设置的key比较函数类对所有数据对排序。然后开始构造一个key对应的value迭代器。这时就要用到分组，使用job.setGroupingComparatorClass设置的分组函数类。只要这个比较器比较的两个key相同，他们就属于同一个组，它们的value放在一个value迭代器，而这个迭代器的key使用属于同一个组的所有key的第一个key。最后就是进入Reducer的reduce方法，reduce方法的输入是所有的（key和它的value迭代器）。同样注意输入与输出的类型必须与自定义的Reducer中声明的一致。
实验步骤
1.建一个文本文档，用逗号分隔开，数据如下
goods_visit2表
goods_id click_num
1010037 100
1010102 100
1010152 97
1010178 96
1010280 104
1010320 103
1010510 104
1010603 96
1010637 97虚拟机中启动Hadoop
2.本地新建/data/mapreduce8目录。
mkdir -p /data/mapreduce8
3.将表上传到虚拟机中
4.上传并解压hadoop2lib文件
5.在HDFS上新建/mymapreduce8/in目录，然后将Linux本地/data/mapreduce8目录下的goods_visit2文件导入到HDFS的/mymapreduce8/in目录中。
hadoop fs -mkdir -p /mymapreduce8/in
hadoop fs -put /data/mapreduce8/goods_visit2 /mymapreduce8/in
6.IDEA中编写Java代码
package mapreduce7;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class SecondarySort
{
public static class IntPair implements WritableComparable<IntPair>
{
int first;
int second;
public void set(int left, int right)
{
first = left;
second = right;
}
public int getFirst()
{
return first;
}
public int getSecond()
{
return second;
}
@Override
public void readFields(DataInput in) throws IOException
{
// TODO Auto-generated method stub
first = in.readInt();
second = in.readInt();
}
@Override
public void write(DataOutput out) throws IOException
{
// TODO Auto-generated method stub
out.writeInt(first);
out.writeInt(second);
}
@Override
public int compareTo(IntPair o)
{
// TODO Auto-generated method stub
if (first != o.first)
{
return first < o.first ? 1 : -1;
}
else if (second != o.second)
{
return second < o.second ? -1 : 1;
}
else
{
return 0;
}
}
@Override
public int hashCode()
{
return first * 157 + second;
}
@Override
public boolean equals(Object right)
{
if (right == null)
return false;
if (this == right)
return true;
if (right instanceof IntPair)
{
IntPair r = (IntPair)
right;
return r.first == first && r.second ==
second;
}
else
{
return false;
}
}
}
public static class FirstPartitioner extends Partitioner<IntPair, IntWritable>
{
@Override
public int getPartition(IntPair key, IntWritable value,int numPartitions)
{
return Math.abs(key.getFirst() * 127) % numPartitions;
}
}
public static class GroupingComparator extends WritableComparator
{
protected GroupingComparator()
{
super(IntPair.class, true);
}
@Override
//Compare two WritableComparables.
public int compare(WritableComparable w1, WritableComparable w2)
{
IntPair ip1 = (IntPair) w1;
IntPair ip2 = (IntPair) w2;
int l = ip1.getFirst();
int r = ip2.getFirst();
return l == r ? 0 : (l < r ? -1 : 1);
}
}
public static class Map extends Mapper<LongWritable, Text, IntPair, IntWritable>
{
private final IntPair intkey = new IntPair();
private final IntWritable intvalue = new IntWritable();
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
{
String line =
value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
int left = 0;
int right = 0;
if (tokenizer.hasMoreTokens())
{
left =
Integer.parseInt(tokenizer.nextToken());
if (tokenizer.hasMoreTokens())
right =
Integer.parseInt(tokenizer.nextToken());
intkey.set(right, left);
intvalue.set(left);
context.write(intkey, intvalue);
}
}
}
public static class Reduce extends Reducer<IntPair, IntWritable, Text, IntWritable>
{
private final Text left = new Text();
private static final Text SEPARATOR = new Text("------------------------------------------------");
public void reduce(IntPair key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException
{
context.write(SEPARATOR, null);
left.set(Integer.toString(key.getFirst()));
System.out.println(left);
for (IntWritable val : values)
{
context.write(left, val);
//System.out.println(val);
}
}
}
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException
{
Configuration conf = new Configuration();
Job job = new Job(conf, "secondarysort");
job.setJarByClass(SecondarySort.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setPartitionerClass(FirstPartitioner.class);
job.setGroupingComparatorClass(GroupingComparator.class);
job.setMapOutputKeyClass(IntPair.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
String[] otherArgs=new String[2];
otherArgs[0]="hdfs://192.168.149.10:9000/mymapreduce8/in/goods_visit2";
otherArgs[1]="hdfs://192.168.149.10:9000/mymapreduce8/out";
FileInputFormat.setInputPaths(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
7.将hadoop2lib目录中的jar包，拷贝到hadoop2lib目录下。
8.拷贝log4j.properties文件
9.运行结果
PS:本次表不用把空格替换成逗号，数据之间使用一个空格隔开