数据清洗 处理有字段缺失的数据

将有字段缺失的数据删除掉

分析

将清洗后的数据导入数据库表中

筛选出新增确诊人数最多的前三天的数据

map代码

效果

还有一种思路 把缺失的数据注释
map代码

package test7;

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

import java.io.IOException;

public class test11 extends Mapper <LongWritable, Text,Text, NullWritable>{
     Text  k=new Text();
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line=value.toString();
        String[] word=line.split(",");
        String end = "";

        int i = 0;
        if (word.length==5){
            for ( i=0;i<=4;i++ ){
                if(word[i].equals("")){
                  word[0]= "--"+word[0];
                }
            }
        }
        else if(word.length<5){
            word[0]="--"+word[0];
        }

        for (String item: word){
                end = end + item + ",";
        }
        end=end.substring(0,end.length()-1);

        k.set(end);
        context.write(k,NullWritable.get());

    }
}

效果