一.Version:
1.MapReduce(v1.0):
2.MapReduce(v2.0):
二.Code:
Example:
1.Counting the data of phone (partition):
FlowBean.java:
package com.bsr.bigdata.mapreduce.part_pd;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class FlowBean implements Writable{
private long upFlow;
private long dFlow;
private long sumFlow;
//反序列化时,需要反射调用空参构造函数,所以要显示定义一个
public FlowBean(){}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getdFlow() {
return dFlow;
}
public void setdFlow(long dFlow) {
this.dFlow = dFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
public FlowBean(long upFlow, long dFlow) {
super();
this.upFlow = upFlow;
this.dFlow = dFlow;
this.sumFlow = upFlow + dFlow;
}
/**
* 序列化方法
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(dFlow);
out.writeLong(sumFlow);
}
/**
* 反序列化方法
* 注:反序列化的顺序跟序列化的顺序完全一致
*/
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
dFlow = in.readLong();
sumFlow = in.readLong();
}
@Override
public String toString() {
return upFlow + "\t" + dFlow + "\t" + sumFlow;
}
}
PhonePartitioner.java:
package com.bsr.bigdata.mapreduce.part_pd;
import java.util.HashMap;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
import com.bsr.bigdata.mapreduce.part.FlowBean;
public class PhonePartitioner extends Partitioner<Text, FlowBean>{
public static HashMap<String, Integer> phoneDict = new HashMap<String, Integer>();
static{
phoneDict.put("0431", 0);
phoneDict.put("0451", 1);
phoneDict.put("0461", 2);
phoneDict.put("0471", 3);
}
@Override
public int getPartition(Text key, FlowBean value, int numPartitions) {
String prefix = key.toString().substring(0, 4);
Integer phoneId = phoneDict.get(prefix);
return phoneId == null?4:phoneId;
}
}
FlowCount.java:
package com.bsr.bigdata.mapreduce.part_pd;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 FlowCount {
static class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException{
//将一行数据转成String
String line = value.toString();
//切分字符
String[] fields = line.split("\t");
//手机号
String phoneNbr = fields[1];
//取出上行流量
long upFlow = Long.parseLong(fields[fields.length-3]);
//取出下行流量
long dFlow = Long.parseLong(fields[fields.length-2]);
context.write(new Text(phoneNbr), new FlowBean(upFlow, dFlow));
}
}
static class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean>{
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException{
long sum_upFlow = 0;
long sum_dFlow = 0;
//遍历所有的bean 将上行流量和下行流量分别累加
for(FlowBean bean:values){
sum_upFlow += bean.getUpFlow();
sum_dFlow += bean.getdFlow();
}
//将所有流量进行汇总
FlowBean resultBean = new FlowBean(sum_upFlow, sum_dFlow);
context.write(key, resultBean);
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//指定本程序的jar包所在的本地路径
job.setJarByClass(FlowCount.class);
//指定本业务job要是用的Mapper/Reducer业务类
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
//指定我们自定义的数据分区器
job.setPartitionerClass(PhonePartitioner.class);
//同时制定相应“分区”数量的reducetask
job.setNumReduceTasks(5);
//指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path("D:\\flow\\in"));
//指定job的输出结果所在目录
FileOutputFormat.setOutputPath(job, new Path("D\\flow\\in"));
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}
2.WordCountContainer:
package com.bsr.bigdata.mapreduce.combiner;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;
/**
* 问:为什么使用Combiner?
* 答:Combiner发生在Map端,对数据进行规约处理,数据量变小了,传送到reduce端的数据量变小了,传输时间变短,作业的整体时间变短。
*
* 问:为什么Combiner不作为MR运行的标配,而是可选步骤哪?
* 答:因为不是所有的算法都适合使用Combiner处理,例如求平均数。
*
* 问:Combiner本身已经执行了reduce操作,为什么在Reducer阶段还要执行reduce操作哪?
* 答:combiner操作发生在map端的,处理一个任务所接收的文件中的数据,不能跨map任务执行;只有reduce可以接收多个map任务处理的数据。
*
*/
public class WordCountCombiner {
/**
* KEYIN 即k1 表示行的偏移量
* VALUEIN 即v1 表示行文本内容
* KEYOUT 即k2 表示行中出现的单词
* VALUEOUT 即v2 表示行中出现的单词的次数,固定值1
*/
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
final String[] splited = v1.toString().split(" ");
for (String word : splited) {
context.write(new Text(word), new LongWritable(1));
System.out.println("Mapper输出<"+word+","+1+">");
}
};
}
/**
* KEYIN 即k2 表示行中出现的单词
* VALUEIN 即v2 表示行中出现的单词的次数
* KEYOUT 即k3 表示文本中出现的不同单词
* VALUEOUT 即v3 表示文本中出现的不同单词的总次数
*
*/
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException {
//显示次数表示redcue函数被调用了多少次,表示k2有多少个分组
System.out.println("MyReducer输入分组<"+k2.toString()+",...>");
long times = 0L;
for (LongWritable count : v2s) {
times += count.get();
//显示次数表示输入的k2,v2的键值对数量
System.out.println("MyReducer输入键值对<"+k2.toString()+","+count.get()+">");
}
ctx.write(k2, new LongWritable(times));
};
}
static class MyCombiner extends Reducer<Text, LongWritable, Text, LongWritable>{
protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2s, Context ctx) throws java.io.IOException ,InterruptedException {
//显示次数表示redcue函数被调用了多少次,表示k2有多少个分组
System.out.println("Combiner输入分组<"+k2.toString()+",...>");
long times = 0L;
for (LongWritable count : v2s) {
times += count.get();
//显示次数表示输入的k2,v2的键值对数量
System.out.println("Combiner输入键值对<"+k2.toString()+","+count.get()+">");
}
ctx.write(k2, new LongWritable(times));
//显示次数表示输出的k2,v2的键值对数量
System.out.println("Combiner输出键值对<"+k2.toString()+","+times+">");
};
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//指定如何对输入文件进行格式化,把输入文件每一行解析成键值对
//job.setInputFormatClass(TextInputFormat.class);
//1.2 指定自定义的map类
job.setMapperClass(MyMapper.class);
//map输出的<k,v>类型。如果<k3,v3>的类型与<k2,v2>类型一致,则可以省略
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//1.5 规约
job.setCombinerClass(MyCombiner.class);
//2.2 指定自定义reduce类
job.setReducerClass(MyReducer.class);
//指定reduce的输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
//指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path("D:\\word\\in"));
//指定job的输出结果所在目录
Path outPath = new Path("D:\\word\\out");
FileOutputFormat.setOutputPath(job, outPath);
FileSystem fs = FileSystem.get(conf);
if(fs.exists(outPath)){
fs.delete(outPath, true);
}
//将job中配置的相关参数,以及job所用的java类所在的jar包,提交给yarn去运行
/*job.submit();*/
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}