大数据wordcount代码。要理解代码就要配合图形理解

Posted 喷气背包

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了大数据wordcount代码。要理解代码就要配合图形理解相关的知识,希望对你有一定的参考价值。

package cn.itcast.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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountDriver {
    public WordCountDriver() {
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        //conf.set("mapreduce.app-submission.cross-platform", "true");  // 跨平台,保证在 Windows 下可以提交 mr job
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCountDriver.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path("/home/node-1/zhouriyue/input/"));
        FileOutputFormat.setOutputPath(job, new Path("/home/node-1/zhouriyue/output/"));
        /*FileInputFormat.setInputPaths(job, "/wordcount/input");
        FileOutputFormat.setOutputPath(job, new Path("/wordcount/output"));*/
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

 

package cn.itcast.hadoop.mr;

import java.io.IOException;
import java.util.Arrays;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    public WordCountMapper() {
    }

    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        String[] var9 = words;
        int var8 = words.length;
        for(int var7 = 0; var7 < var8; ++var7) {
            String word = var9[var7];
            System.out.println(word+","+1);
            context.write(new Text(word), new IntWritable(1));
        }

    }
}

 

package cn.itcast.hadoop.mr;

import java.io.IOException;
import java.util.Arrays;
import java.util.Iterator;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    public WordCountReducer() {
    }

    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        int count = 0;
        IntWritable value;
        System.out.println(key+","+count);
        for(Iterator var6 = values.iterator(); var6.hasNext();) {
            System.out.println("count:"+count+"var6:"+var6);
            value = (IntWritable)var6.next();
            count += value.get();
        }
        context.write(key, new IntWritable(count));
    }
}

举一反三,借鉴别人的写出自己的才是真的好。

问题:求4.txt,5.txt,6.txt文件里所有数字的最大值。代码如下

package com.gxuwz.MaxValue;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.fs.Path;
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 java.io.IOException;

public class MaxValueDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(MaxValueDriver.class);
        job.setMapperClass(MaxValueMapper.class);
        job.setReducerClass(MaxValueReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.setInputPaths(job,"/home/node-1/zhouriyue/data/");
        FileOutputFormat.setOutputPath(job,new Path("/home/node-1/zhouriyue/maxvalue/"));
        Boolean b = job.waitForCompletion(true);
        System.exit(b?0:1);
    }
}

package com.gxuwz.MaxValue;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class MaxValueMapper extends Mapper<LongWritable, Text,Text, Text> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String data = value.toString();
        String[] values = data.split(" ");
        for(int i = 0;i < values.length;i++) {
            context.write(new Text("maxValue"),new Text(values[i]));
        }
    }
}

package com.gxuwz.MaxValue;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class MaxValueReducer extends Reducer<Text, Text,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        int maxValue = 0;
        Iterator datas = values.iterator();
        Text v = null;
        while (datas.hasNext()) {
            v = (Text)datas.next();
            System.out.println("v:"+v.toString());
            int s = Integer.parseInt(""+v.toString());
            if(s > maxValue) {
                maxValue = s;
            }
        }
        context.write(new Text("maxValue"),new IntWritable(maxValue));
    }
}

 

以上是关于大数据wordcount代码。要理解代码就要配合图形理解的主要内容,如果未能解决你的问题,请参考以下文章

hadoop之WordCount源代码分析

PySpark理解wordcount.py

彻底解密WordCount运行原理(DT大数据梦工厂)

MapReduce简单实例:wordcount--大数据纪录片第五记

Apache Beam WordCount编程实战及源代码解读

WordCount 分析