MapReduce02——删除有缺失值的记录

最新推荐文章于 2024-04-30 11:17:05 发布

yeyu_xing

最新推荐文章于 2024-04-30 11:17:05 发布

阅读量1.7k

点赞数 1

分类专栏：大数据

本文链接：https://blog.csdn.net/yeyu_xing/article/details/113890736

版权

Hadoop MapReduce map阶段 reduce阶段文本处理

关键词由CSDN通过智能技术生成

大数据专栏收录该内容

7 篇文章 0 订阅

订阅专栏

1、有words.txt文件内容如下，其中以制表符分割

1	xiaoming	18
2	xiaohong	17
3	xiaoli
4	xiaowang	20

2、分析
map阶段
（1）、mapreduce逐行读取文件，得到每行的值
（2）、首先判断该行不是空字符串
（3）、满足以制表符分割后，长度必须大于3
（4）、将整行当做key输出
reduce阶段
（1）、map阶段将相同的key聚合在一起，但value为空
（2）、直接输出key即可
3、创建maven工程后，添加如下依赖

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.9.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.9.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.9.2</version>
        </dependency>
    </dependencies>

4、编写mapreduce程序

package com.qujiuge.handle_lackval;

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.NullWritable;
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 java.io.IOException;

public class Driver {
    static class LackMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] fields = line.split("\t");
            if (fields.length == 3) {
                context.write(value, NullWritable.get());
            }
        }
    }

    static class LackReducer extends Reducer<Text, NullWritable, Text, NullWritable> {
        @Override
        protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            context.write(key, values.iterator().next());
        }
    }

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

        job.setJarByClass(Driver.class);

        job.setMapperClass(LackMapper.class);
        job.setReducerClass(LackReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileSystem fs = FileSystem.get(config);
        Path outPath = new Path(args[1]);
        if (fs.exists(outPath)) {
            fs.delete(outPath, true);
        }
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, outPath);

        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}