MapReduce的API实现词频统计

MapReduce的API操作

---

MapReduce的工作流程

参考文章：MapReduce工作流程

词频统计API实现

一、环境准备：参考HDFS的API操作
二、编码实现：
创建3个类：Mapper、Reducer、Driver

1. 创建Map阶段的WordCountMapper
   WordCountMapper代码;

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;

/**
 * KEYIN,map阶段输入的kek类型：LongWritable
 * VALUEIN，map阶段输入的value类型：Text
 * KEYOUT,map阶段输出的key类型：Text
 * VALUEOUT，map阶段输出value类型：IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    //在最外层分配输出key、value对象，这样比写在循环里面更节省空间
    Text outK = new Text();
    IntWritable outV = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        super.map(key, value, context);
        // 1 获取一行
        String line = value.toString();

        // 2 切割
        String[] words = line.split(" ");

        // 3 循环写出
        for (String word : words) {
            //封装
            outK.set(word);

            //写出
            context.write(outK, outV);
        }

    }
}

2. 创建Reduce阶段的WordCountReducer
   WordCountReducer代码：

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

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outV = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {

        int sum = 0;
        //执行结果格式为 abc(1,1)
        for (IntWritable value : values) {
            sum += value.get();
        }

        outV.set(sum);

        //写出
        context.write(key,outV);
    }
}

3. 编写运行时的Driver类WordCountDriver
   WordCountDriver代码：

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;
import java.io.IOException;

public class WordCountDriver {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入路径
        FileInputFormat.setInputPaths(job, new Path("F:\\hello.txt"));
        FileOutputFormat.setOutputPath(job, new Path("F:\\hdfs\\output1"));

        // 7 提交job,成功返回0，否则返回1
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

这里的输入文本为

运行结果在指定目录下的part-r-00000