【Hadoop】MapReduce练习：分科目等级并按分区统计学生以及人数

需求

背景：学校的学生的是一个非常大的生成数据的集体，比如每次考试的成绩
现有一个班级的学生一个月的考试成绩数据。
科目姓名分数
需求：求出每门成绩中属于甲级的学生人数和总人数
乙级的学生人数和总人数
丙级的学生人数和总人数
甲级（90及以上）乙级（80到89）丙级（0到79）
处理数据结果：

                    甲级分区

课程\t甲级\t学生1,学生2,...\t总人数

                    乙级分区

课程\t乙级\t学生1,学生2,...\t总人数

                    丙级分区

课程\t丙级\t学生1,学生2,...\t总人数

文档格式

English,liudehua,80
English,lijing,79
English,nezha,85
English,jinzha,60
English,muzha,71
English,houzi,99
English,libai,88
English,hanxin,66
English,zhugeliang,95
Math,liudehua,74
Math,lijing,72
Math,nezha,95
Math,jinzha,61
Math,muzha,37
Math,houzi,37
Math,libai,84
Math,hanxin,89
Math,zhugeliang,93
Computer,liudehua,54
Computer,lijing,73
Computer,nezha,86
Computer,jinzha,96
Computer,muzha,76
Computer,houzi,92
Computer,libai,73
Computer,hanxin,82
Computer,zhugeliang,100

代码示例

StuDriver

import org.apache.hadoop.io.Text;
import stuScore.JobUtils;

public class StuDriver {
    public static void main(String[] args) {
        String[] paths = {"F:/stu_score.txt", "F:/output"};

        JobUtils.commit(paths, true, 3, false, StuDriver.class,
                StuMapper.class, Text.class, Text.class, null, StuPartitioner.class, StuReduce.class,
                Text.class, Text.class);

    }
}

JobUtils

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.File;
import java.io.IOException;

public class JobUtils {
    private static Configuration conf;

    static {
        conf = new Configuration();
    }

    /**
     * 提交job
     *
     * @param paths        输入输出路径数组
     * @param isPartition  是否包含自定义分区类
     * @param reduceNumber reduce数量(若自定义分区为true，则此项必须>=自定义分区数)
     * @param isGroup  是否分组
     * @param params       可变参数
     */
    public static void commit(String[] paths, boolean isPartition, int reduceNumber, boolean isGroup, Class... params) {
        try {
            Job job = Job.getInstance(conf);
            job.setJarByClass(params[0]);

            job.setMapperClass(params[1]);
            job.setMapOutputKeyClass(params[2]);
            job.setMapOutputValueClass(params[3]);

            if(isGroup) {
                job.setGroupingComparatorClass(params[4]);
            }

            if (isPartition) {
                job.setPartitionerClass(params[5]);//设置自定义分区；
            }

            if (reduceNumber > 0) {
                job.setNumReduceTasks(reduceNumber);
                job.setReducerClass(params[6]);
                job.setOutputKeyClass(params[7]);
                job.setOutputValueClass(params[8]);
            } else {
                job.setNumReduceTasks(0);
            }
            FileInputFormat.setInputPaths(job, new Path(paths[0]));
            FileOutputFormat.setOutputPath(job, new Path(paths[1]));
            job.waitForCompletion(true);
        } catch (InterruptedException | ClassNotFoundException | IOException e) {
            e.printStackTrace();
        }
    }
}

StuMapper

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

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

    Text k = new Text();
    Text v = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] splits = line.split(",");
        int score = Integer.parseInt(splits[2]);
        String level;
        if (score >= 90) {
            level = "甲级";
        } else if (score < 90 && score >= 80) {
            level = "乙级";
        } else {
            level = "丙级";
        }
        k.set(splits[0] + "\t" + level);
        v.set(splits[1]);
        context.write(k, v);
    }
}

StuReduce

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class StuReduce extends Reducer<Text,Text,Text, Text> {
    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        StringBuilder builder = new StringBuilder();
        int count =0;
        for (Text v : values) {
            builder.append(v+",");
            count++;
        }
        builder.replace(builder.length()-1,builder.length(),"\t");
        builder.append(count);
        context.write(key,new Text(builder.toString()));
    }
}

StuPartitioner

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class StuPartitioner extends Partitioner<Text, Text> {
    @Override
    public int getPartition(Text text, Text text2, int i) {
        String line = text.toString();
        if(line.contains("甲级")){
            return 0;
        }else if(line.contains("乙级")){
            return 1;
        }else{
            return 2;
        }
    }
}