如何数据清洗

创建Mapper类输入代码

package org.example;
import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

// 继承Mapper

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

    @Override

    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 获取一行数据，用空格拆分为一个个单词

        String[] words = value.toString().split(" ");

        // 遍历单词，设置键值对，值为1

        for (String word : words) {

            context.write(new Text(word), new LongWritable(1));

        }

    }

}

创建Driver类输入代码

package org.example;

import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;
public class WordCountDriver {
    // mapreduce的Driver
    // 提交job
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        // 1. 获取配置信息以及获取job对象
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);
        // 2. 关联本地的jar
        job.setJarByClass(WordCountDriver.class);

        // 3. 关联Mapper和Reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4. 设置Mapper输出的KV类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //5.设置最终输出的kv的类型
        //设置reduceTask的数量为0
        job.setOutputKeyClass(0);
        //6.设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path("input"));
        FileOutputFormat.setOutputPath(job, new Path("output"));
        // 7. 提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}
.class);