hadoop MapReduce工资统计代码

以下是一个使用Hadoop MapReduce框架来统计工资数据的简单示例代码：

Mapper部分：

public class SalaryMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] fields = line.split(",");
        int salary = Integer.parseInt(fields[2]);

        // 将薪资范围映射为对应的key
        if (salary < 10000) {
            word.set("<10000");
        } else if (salary < 20000) {
            word.set("10000-20000");
        } else if (salary < 30000) {
            word.set("20000-30000");
        } else {
            word.set(">30000");
        }

        context.write(word, one);
    }
}

Reducer部分：

public class SalaryReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, Context context)
            throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

Driver部分：

public class SalaryCount {

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "Salary Count");

        job.setJarByClass(SalaryCount.class);
        job.setMapperClass(SalaryMapper.class);
        job.setCombinerClass(SalaryReducer.class);
        job.setReducerClass(SalaryReducer.class);

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

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

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

以上代码用于统计薪资范围在<10000, 10000-20000, 20000-30000, >30000之间的员工数量。输入文件为CSV格式的员工信息文件，每行为一个员工的id、姓名和薪资。输出文件为每个薪资范围对应的员工数量。