Mapreduce统计每个年月下，温度最高的前两天

需求分析:统计每个年月下，温度最高的前两天.

1. 按年月分组
2. 再按温度排序取前两个

测试数据

2020-01-02 10:22:22	1c
2020-01-03 10:22:22	2c
2020-01-04 10:22:22	100c
2020-01-04 10:22:22	4c
2020-02-01 10:22:22	7c
2020-02-02 10:22:22	9c
2020-02-03 10:22:22	11c
2020-02-04 10:22:22	1c
2019-01-02 10:22:22	1c
2019-01-03 10:22:22	2c
2019-01-04 10:22:22	4c
2019-02-01 10:22:22	7c
2019-02-04 10:22:22	72c
2019-02-02 10:22:22	9c
2018-02-03 10:22:22	111c
2018-02-04 10:22:22	1c

mapper类

public static class MyMapper extends Mapper<LongWritable, Text, Text, Text> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] split = value.toString().split("\t");      //分为两个   split[1]为 1c
            String s =split[0];
            int i = s.lastIndexOf("-");
            String substring = s.substring(0,i);    //取年月，自动分组
            context.write(new Text(substring),new Text(split[0]+"       "+split[1]));
        }
    }

reduce类

public static class MyReducer extends Reducer<Text, Text, Text,Text> {
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            Map<String,Integer> map=new HashMap<>();
            Iterator<Text> iterator = values.iterator();
            while (iterator.hasNext()){
                String[] split = iterator.next().toString().split("\\s+");//分为3个
                int index = split[2].lastIndexOf("c");  //取到c的index
                int temp = Integer.parseInt(split[2].substring(0,index));   //取出数并转为int
                map.put(split[0]+split[1],temp);
            }
            //这里将map.entrySet()转换成list，里面存到是相同年月的map
            List<Map.Entry<String,Integer>> list=new LinkedList<Map.Entry<String,Integer>>(map.entrySet());
            Collections.sort(list,new Comparator<Map.Entry<String, Integer>>() {    //排序
                @Override
                public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) {
                    return (int)(o2.getValue()-o1.getValue());  //降序排
                }
            });
            for (int i=0;i<2;i++){//排好序后输出最大的两个值
                context.write(new Text(list.get(i).getKey()),new Text(list.get(i).getValue()+"c"));
            }

        }
    }

出现的问题:reduce分割空格时split(“\t”)失效，换了个正则的。
执行

 public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        Configuration conf = new Configuration();//配置运行的配置
        Job job = Job.getInstance(conf, "number wendu");
        job.setJarByClass(MapReduce_wendu.class);     //运行的jar包

        job.setMapperClass(MyMapper.class);     //mapper操作
        job.setReducerClass(MyReducer.class);      //只要合并一次就行

        job.setOutputKeyClass(Text.class);          //输出的键类型        与reduce的key保持一直
        job.setOutputValueClass(Text.class);     //输出的值类型           与reduce的result保持一直

        FileInputFormat.addInputPath(job,new Path("C:\\Users\\q'q'w\\Desktop\\MapReduce\\input"));//提前存在的
        Util_lgy.deleteFile(Util_lgy.file);         //删output
        FileOutputFormat.setOutputPath(job,new Path("C:\\Users\\q'q'w\\Desktop\\MapReduce\\output"));//不存在，运行后要删了output才能执行

//        FileInputFormat.addInputPath(job, new Path(args[0]));
//        Path path=new Path(args[1]);
//        Util_lgy.delete(path);                      //删hdfs里的
//        FileOutputFormat.setOutputPath(job, path);

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

输出结果:
2018-02-0310:22:22 111c
2018-02-0410:22:22 1c
2019-01-0410:22:22 4c
2019-01-0310:22:22 2c
2019-02-0410:22:22 72c
2019-02-0210:22:22 9c
2020-01-0410:22:22 100c
2020-01-0310:22:22 2c
2020-02-0310:22:22 11c
2020-02-0210:22:22 9c