MR之词频统计
前言
本文讲的是大数据入门程序词频统计。
一、Driver类编写
package com.hadoop.mapreduce.wordcount;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* Driver类,程序的入口
*/
public class WordCountDriver extends Configured implements Tool {
private Configuration conf = new Configuration();
@Override
public int run(String[] args