hadoop-MapReduce-计数器应用-数据清洗(ETL)

——尚硅谷课程笔记


计数器应用

        Hadoop为每个作业维护若干内置计数器,以描述多项指标。例如,某些计数器记录已处理的字节数和记录数,使用户可监控已处理的输入数据量和已产生的输出数据量。

       1.计数器API

             (1)采用枚举的方式统计计数

                 enum MyCounter{MALFORORMED,NORMAL}

    //对枚举定义的自定义计数器加1

   context.getCounter(MyCounter.MALFORORMED).increment(1);

2)采用计数器组、计数器名称的方式统计

   context.getCounter("counterGroup", "counter").increment(1);

   组名和计数器名称随便起,但最好有意义。

3)计数结果在程序运行后的控制台上查看。

数据清洗(ETL)

在运行核心业务MapReduce程序之前,往往要先对数据进行清洗,清理掉不符合用户要求的数据。清理的过程往往只需要运行Mapper程序,不需要运行Reduce程序。

数据清洗案例实操-简单解析版

1.需求

去除日志中字段长度小于等于11的日志。

(1)输入数据

web.log

194.237.142.21 - - [18/Sep/2013:06:49:18 +0000] "GET /wp-content/uploads/2013/07/rstudio-git3.png HTTP/1.1" 304 0 "-" "Mozilla/4.0 (compatible;)"

(2)期望输出数据

每行字段长度都大于11。

2.需求分析

       需要在Map阶段对输入的数据根据规则进行过滤清洗。

3.实现代码

(1)编写LogMapper类

package com.liun.mr.log;

import java.io.IOException;

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

public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable>{

	@Override
	protected void map(LongWritable key, Text value,Context context)
			throws IOException, InterruptedException {
		
		//获取一行
		String line = value.toString();
		
		//解析数据
		boolean result = parseLog(line,context);
		
		if (!result) {
			return;
		}
		
		// 解析通过 写出
		context.write(value, NullWritable.get());
	}

	private boolean parseLog(String line, Context context) {
		// 切割
		String[] fields = line.split(" ");
		
		if (fields.length > 11) {
			
			//计数器统计true
			context.getCounter("map", "true").increment(1);
			return true;
		}else {
			
			//计数器统计false
			context.getCounter("map", "false").increment(1);
			return false;
		}
	}
}

(2)编写LogDriver类

package com.liun.mr.log;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class LogDriver {

	public static void main(String[] args) throws Exception, IOException {

		// 1 获取job信息
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);

		// 2 加载jar包
		job.setJarByClass(LogDriver.class);

		// 3 关联map
		job.setMapperClass(LogMapper.class);

		// 4 设置最终输出类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(NullWritable.class);

		// 设置reducetask个数为0
		job.setNumReduceTasks(0);

		// 5 设置输入和输出路径
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		// 6 提交
		job.waitForCompletion(true);

	}
}

数据清洗案例实操-复杂解析版

1.需求

对Web访问日志中的各字段识别切分,去除日志中不合法的记录。根据清洗规则,输出过滤后的数据。

(1)输入数据

web.log

194.237.142.21 - - [18/Sep/2013:06:49:18 +0000] "GET /wp-content/uploads/2013/07/rstudio-git3.png HTTP/1.1" 304 0 "-" "Mozilla/4.0 (compatible;)"

(2)期望输出数据

都是合法的数据

2.实现代码

(1)定义一个bean,用来记录日志数据中的各数据字段

package com.liun.mr.log;

public class LogBean {

	private String remote_addr;// 记录客户端的ip地址
	private String remote_user;// 记录客户端用户名称,忽略属性"-"
	private String time_local;// 记录访问时间与时区
	private String request;// 记录请求的url与http协议
	private String status;// 记录请求状态;成功是200
	private String body_bytes_sent;// 记录发送给客户端文件主体内容大小
	private String http_referer;// 用来记录从那个页面链接访问过来的
	private String http_user_agent;// 记录客户浏览器的相关信息

	private boolean valid = true;// 判断数据是否合法

	public String getRemote_addr() {
		return remote_addr;
	}

	public void setRemote_addr(String remote_addr) {
		this.remote_addr = remote_addr;
	}

	public String getRemote_user() {
		return remote_user;
	}

	public void setRemote_user(String remote_user) {
		this.remote_user = remote_user;
	}

	public String getTime_local() {
		return time_local;
	}

	public void setTime_local(String time_local) {
		this.time_local = time_local;
	}

	public String getRequest() {
		return request;
	}

	public void setRequest(String request) {
		this.request = request;
	}

	public String getStatus() {
		return status;
	}

	public void setStatus(String status) {
		this.status = status;
	}

	public String getBody_bytes_sent() {
		return body_bytes_sent;
	}

	public void setBody_bytes_sent(String body_bytes_sent) {
		this.body_bytes_sent = body_bytes_sent;
	}

	public String getHttp_referer() {
		return http_referer;
	}

	public void setHttp_referer(String http_referer) {
		this.http_referer = http_referer;
	}

	public String getHttp_user_agent() {
		return http_user_agent;
	}

	public void setHttp_user_agent(String http_user_agent) {
		this.http_user_agent = http_user_agent;
	}

	public boolean isValid() {
		return valid;
	}

	public void setValid(boolean valid) {
		this.valid = valid;
	}

	@Override
	public String toString() {
		
		StringBuilder sb = new StringBuilder();
		
		sb.append(this.valid);
		sb.append("\001").append(this.remote_addr);
		sb.append("\001").append(this.remote_user);
		sb.append("\001").append(this.time_local);
		sb.append("\001").append(this.request);
		sb.append("\001").append(this.status);
		sb.append("\001").append(this.body_bytes_sent);
		sb.append("\001").append(this.http_referer);
		sb.append("\001").append(this.http_user_agent);
		
		return sb.toString();
	}
}

(2)编写LogMapper类

package com.liun.mr.log;

import java.io.IOException;

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

public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

	Text k = new Text();

	@Override
	protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

		// 获取一行
		String line = value.toString();

		// 解析数据
		LogBean bean = parseLog(line, context);

		if (!bean.isValid()) {
			return;
		}

		k.set(bean.toString());
		// 解析通过 写出
		context.write(k, NullWritable.get());
	}

	private LogBean parseLog(String line, Context context) {

		LogBean logBean = new LogBean();

		// 切割
		String[] fields = line.split(" ");

		if (fields.length > 11) {

			// 2封装数据
			logBean.setRemote_addr(fields[0]);
			logBean.setRemote_user(fields[1]);
			logBean.setTime_local(fields[3].substring(1));
			logBean.setRequest(fields[6]);
			logBean.setStatus(fields[8]);
			logBean.setBody_bytes_sent(fields[9]);
			logBean.setHttp_referer(fields[10]);

			// 大于400,HTTP错误
			if (Integer.parseInt(logBean.getStatus()) >= 400) {

				context.getCounter("map", "false").increment(1);
				logBean.setValid(false);
			} else if (fields.length > 12) {

				context.getCounter("map", "true").increment(1);
				logBean.setHttp_user_agent(fields[11] + " " + fields[12]);
			} else {
				context.getCounter("map", "true").increment(1);
				logBean.setHttp_user_agent(fields[11]);
			}
		} else {
			context.getCounter("map", "false").increment(1);
			logBean.setValid(false);
		}
		return logBean;
	}
}

 

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值