mapreduce案例二

练习题：求每个平均消费,如果遇到异常数据，money异常，就回填为10
数据：
张三,12月3号,20
张三,12月3号,10
李四,12月3号,12
王五,12月3号,10
王五,12月2号
王五,12月2号,30
王二麻,12月2号,0
王二麻,12月2号,,
王二麻,12月2号, ,

代码

package com.shujia.avgmoney;

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.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;

/*
李四,12月3号,12
王五,12月3号,10
王五,12月2号
王五,12月2号,30
王二麻,12月2号,0
王二麻,12月2号,,
王二麻,12月2号, ,
 */
class AvgMapper extends Mapper<LongWritable,Text,Text,LongWritable>{
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String s = line.replaceAll("[,|,,|, ,]", "\t");
        String[] split = s.split("\t");
        if(split.length!=3) {
            String[] strings = new String[3];
            strings[0]=split[0];
            strings[1]=split[1];
            strings[2]="10";
            Text name = new Text(strings[0]);
            LongWritable res = new LongWritable(new Long(strings[2]));
            context.write(name,res);
        }else{
            Text name = new Text(split[0]);
            LongWritable res = new LongWritable(new Long(split[2]));
            context.write(name,res);
        }
    }
}

class AvgReducer extends Reducer<Text,LongWritable,Text,LongWritable> {
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
        long sum=0;
        long count=0;
        for (LongWritable value : values) {
            long l = value.get();
            sum+=l;
            count++;
        }
        long avg=sum / count;
        context.write(key,new LongWritable(avg));
    }
}

public class AvgDemo {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(AvgDemo.class);
        job.setMapperClass(AvgMapper.class);
        job.setReducerClass(AvgReducer.class);

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

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

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        job.waitForCompletion(true);
    }
}

注意的点：需要数据清洗，替换

结果：