【大数据实训日记】Day2 电商日志数据分析项目

一、项目要求

根据电商日志文件，分析： 

1.  统计页面浏览量（每行记录就是一次浏览）

2.  统计各个省份的浏览量 （需要解析IP）

3.  日志的ETL操作（ETL：数据从来源端经过抽取（Extract）、转换（Transform）、加载（Load）至目的端的过程）

   为什么要ETL：没有必要解析出所有数据，只需要解析出有价值的字段即可。本项目中需要解析出：ip、url、pageId（topicId对应的页面Id）、country、province、city

二、问题一分析

       Map阶段，对于每一条数据，设置一个默认键（只用于标记该行），值设置为1。Reduce阶段，获得所有的值的和即可。

三、代码实现

1.Map阶段

package org.dianshang;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(new Text("line"), new IntWritable(1));

    }
}

2.Reduce阶段

package org.dianshang;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
public class DSReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable result = new IntWritable();
    @Override
    protected 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);
    }
}

3.运行文件

package org.dianshang;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import java.net.URI;


public class DSDriver {

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

        job.setJarByClass(DSDriver.class);//设置作业的Jar包
        job.setMapperClass(DSMapper.class);
        job.setCombinerClass(DSReducer.class);
        job.setReducerClass(DSReducer.class);//设置Combiner类

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

        FileInputFormat.addInputPath(job, new Path("hdfs://192.168.10.131:9000/wj/input/trackinfo.txt"));
        FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.10.131:9000/wj/output1"));

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