Hadoop | 数据清洗

# 数据清洗概念

通常情况下，大数据平台获得原始数据文件中，存在大量无效数据和缺失数据，需要再第一时间，对数据进行清洗，获得符合后续处理需求的数据内容和格式

# 需求

对手机流量原始数据，将其中的手机号为"null"和不完整的数据去除

数据格式说明

# 源数据

id       手机号   手机mac         ip地址   上传 下载 HTTP状态码

1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 24 27 2481 24681 200 1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200 1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200 1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200 1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 24 27 2481 24681 200 1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200 1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200 1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200 1363157995052 13826544109 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0

1363157995052 null 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 240 0 200 1363157991076 13926435659 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 null nullnull

# 期望结果

1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 24 27 2481 24681 200 1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200 1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200 1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200 1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 24 27 2481 24681 200 1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200 1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200 1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200

 思路分析

1.将数据上传到hdfs

命令：hdfs dfs -put /mapreduce /

2.Idea代码

package demo4;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.IOException;

public class CleanDataJob {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://hadoop10:8020");

        Job job = Job.getInstance(conf);
        job.setJarByClass(CleanDataJob.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        TextInputFormat.addInputPath(job,new Path("/mapreduce/demo3/dataclean.log"));
        TextOutputFormat.setOutputPath(job,new Path("/mapreduce/demo3/out"));
        job.setNumReduceTasks(0);
        job.setMapperClass(CleanDataMapper.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        boolean b = job.waitForCompletion(true);
        System.out.println(b);
    }

    static class CleanDataMapper extends Mapper<LongWritable, Text,Text, NullWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            context.getCounter("我的计数器","全部数据共计").increment(1L);
            String[] s = value.toString().split("\t");
            if(s.length != 9){
                return;
            }
            if("".equals(s[1]) || "null".equals(s[1])){
                return;
            }
            if("".equals(s[6]) || "null".equals(s[6])){
                return;
            }
            if("".equals(s[7]) || "null".equals(s[7])){
                return;
            }
            if("".equals(s[8]) || "null".equals(s[8])){
                return;
            }
            context.getCounter("我的计数器","数据清洗后的数据").increment(1L);
            context.write(value,NullWritable.get());
        }
    }
}

3.结果

希望今天的你，开开心心~    喜欢我就关注我叭~