环境大数据MapReduce

Posted 2021-09-04 Gendan

mapper
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 MavgaqiMapper extends Mapper<LongWritable, Text,Text,IntWritable> {

@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
    //忽略首行
    //用key判断，第一行的key一定是0
    if (key.get()==0) {
        return;
    }
    //字符串类型转成java类型
    String data = value.toString();
    //切片成数组，一共有9个元素
    String[] msgs = data.split(",");

    if (!(msgs[6].equals("N/A"))){
        context.write(new Text(msgs[0]),new IntWritable(Integer.parseInt(msgs[6])));
    }
}

}
reducer
import org.apache.hadoop.io.FloatWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class MavgaqiReducer extends Reducer<Text, IntWritable,Text, IntWritable> {

@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
    //把处理的每一个201601的value值都加起来
    int total = 0;
    int count = 0;
    int avg = 0;
    for (IntWritable v:values){
        //把IntWritable类型转化为int型
        count++;
        total += v.get();
    }
    avg = total/count;
    //total由int类型变为FloatWritable类型
    context.write(key,new IntWritable(avg));
}

}
main
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.FloatWritable;
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 MavgaqiMain {

public static void main(String[] args) throws Exception {
    Job job = Job.getInstance(new Configuration());
    //程序主类
    job.setJarByClass(MavgaqiMain.class);
    //Mapper类的相关设置
    job.setMapperClass(MavgaqiMapper.class);
    //Map输出key，[PerfectMoney下载](https://www.gendan5.com/wallet/PerfectMoney.html)value类型
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    //Reducer类的相关设置
    job.setReducerClass(MavgaqiReducer.class);
    //程序运行输出key,value类型
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    //设置输入，输出路径
    FileInputFormat.setInputPaths(job,new Path(args[0]));
    FileOutputFormat.setOutputPath(job,new Path(args[1]));
    //提交任务，并等待任务运行完成
    job.waitForCompletion(true);
}

}