本文主要包含mapreduce数据去重,mapreduce数据倾斜,mapreduce数据清洗,mapreduce过滤数据,mapreduce数据流图等服务器相关知识,网友希望可以进行参考
MapReduce编程之数据去重，mapreduce编程数据
数据去重主要是为了掌握和利用并行化思想来对数据进行有意义的筛选。统计大数据集上的数据种类个数、从网站日志中计算访问地等这些看似庞杂的任务都会涉及数据去重。下面就进入这个实例的MapReduce程序设计。package com.hadoop.mr;
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 Dedup {
//map将输入中的value复制到输出数据的key上，并直接输出
public static class Map extends Mapper<Object,Text,Text,Text>{
private static Text line=new Text();//每行数据
//实现map函数
public void map(Object key,Text value,Context context)
throws IOException,InterruptedException{
line=value;
context.write(line, new Text(""));[/indent]
}
}
//reduce将输入中的key复制到输出数据的key上，并直接输出
public static class Reduce extends Reducer<Text,Text,Text,Text>{
//实现reduce函数
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();
//这句话很关键
conf.set("mapred.job.tracker", "192.168.1.2:9001");
String[] ioArgs=new String[]{"dedup_in","dedup_out"};
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: Data Deduplication <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Data Deduplication");
job.setJarByClass(Dedup.class);
//设置Map、Combine和Reduce处理类
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
//设置输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
//设置输入和输出目录
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}