hadoop电影评分排序

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/weixin_45526489/article/details/100656400

package Use.Rates;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class UseRatesSum  implements WritableComparable<UseRatesSum> {
    private String movie;
    private String timeStamp;
    private Integer rate;
    private String uid;
    private Integer rateSum;

    public String getMovie() {
        return movie;
    }

    public void setMovie(String movie) {
        this.movie = movie;
    }

    public String getTimeStamp() {
        return timeStamp;
    }

    public void setTimeStamp(String timeStamp) {
        this.timeStamp = timeStamp;
    }

    public Integer getRate() {
        return rate;
    }

    public void setRate(Integer rate) {
        this.rate = rate;
    }

    public String getUid() {
        return uid;
    }

    public void setUid(String uid) {
        this.uid = uid;
    }

    public Integer getRateSum() {
        return rateSum;
    }

    public void setRateSum(Integer rateSum) {
        this.rateSum = rateSum;
    }

    @Override
    public String toString() {
        return "movie:" + movie + ";" + "rateSum:" + rateSum;
    }

    @Override
    public int compareTo(UseRatesSum other) {
        Integer other_rateSum = other.getRateSum();
        Integer my_rateSum = this.rateSum;
        Integer cha = other_rateSum - my_rateSum;
        return cha;

    }
    //序列化
    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(this.movie);
        dataOutput.writeInt(this.rate);

    }
    //反序列化
    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.movie = dataInput.readUTF();
        this.rateSum = dataInput.readInt();

    }
}

package Use.Rates;

import com.doit.sumrate.UserRateDriver;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 org.codehaus.jackson.map.ObjectMapper;

import java.io.IOException;

class UserRateSumDriver {
    //定义一个map类
    public static class UserRateSumMap extends Mapper<LongWritable, Text,Text, IntWritable>{
        ObjectMapper objectMapper = new ObjectMapper();
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException,InterruptedException{

            //将json数据转换成Java对象
            String line = value.toString();
            UseRatesSum useRatesSum = objectMapper.readValue(line,UseRatesSum.class);
            //获取需要的数据
            String movie = useRatesSum.getMovie();
            Integer rate = useRatesSum.getRate();
            context.write(new Text(movie),new IntWritable(rate));

        }
        //定义一个reduce类
    public static class UserRateSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            Integer count = 0;
            for(IntWritable v : values ){
                count = count + v.get();
            }
            context.write(key, new IntWritable(count));
        }
    }


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

        //需要执行的jar包
        job.setJarByClass(UserRateSumDriver.class);

        //需要的map，reduce类
        job.setMapperClass(UserRateSumMap.class);
        job.setReducerClass(UserRateSumReducer.class);

        //
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

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

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



    }
    }
}