你的位置:首页 > 数据库

[数据库]七、统计网站中不同省份用户的访问数


一、需求

针对log日志中给定的信息,统计网站中不同省份用户的访问数

二、编程代码

 

package org.apache.hadoop.studyhdfs.mapreduce;import java.io.IOException;import org.apache.commons.lang.StringUtils;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.conf.Configured;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Mapper.Context;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.util.Tool;import org.apache.hadoop.util.ToolRunner;import org.jboss.netty.util.internal.StringUtil;public class ProvinceCountMapReduce extends Configured implements Tool {  //1.map  /*   * <KEYIN,VALUEIN,KEYOUT,VALUEOUT>   */  public static class WordCountMapper extends Mapper<LongWritable,Text,IntWritable,IntWritable>{    private IntWritable mapOutputKey =new IntWritable();    private IntWritable mapOutputValue =new IntWritable(1);    @Override    public void map(LongWritable key, Text value, Context context)        throws IOException, InterruptedException {      //get lineValue      String lineValue =value.toString();      //split      String[] strs =lineValue.split("\t");      //line blank      String url=strs[1];      String provinceIdValue =strs[23];            //guolv      if(strs.length < 30 || StringUtils.isBlank(provinceIdValue) || StringUtils.isBlank(url)){        return;        }            int provinceId =Integer.MAX_VALUE;      try {        provinceId=Integer.valueOf(provinceIdValue);      } catch (Exception e) {        return;      }      if(provinceId == Integer.MAX_VALUE){        return;      }      mapOutputKey.set(provinceId);      context.write(mapOutputKey, mapOutputValue);    }      }    //2.reduce  public static class WordCountReduce extends Reducer<IntWritable,IntWritable,IntWritable,IntWritable>{    private IntWritable outputValue =new IntWritable();    @Override    public void reduce(IntWritable key, Iterable<IntWritable> values,Context context)        throws IOException, InterruptedException {      //to do      int sum = 0;      for(IntWritable value:values){        sum +=value.get();      }      outputValue.set(sum);      context.write(key, outputValue);    }          }    public int run(String[] args) throws Exception{    //1.get Configuration    Configuration conf =super.getConf();    //2.create job    Job job =Job.getInstance(conf, this.getClass().getSimpleName());    job.setJarByClass(ProvinceCountMapReduce.class);    //3.set job    //3.1 set input    Path inputPath =new Path(args[0]);    FileInputFormat.addInputPath(job, inputPath);    //3.2 set mapper    job.setMapperClass(WordCountMapper.class);    job.setMapOutputKeyClass(IntWritable.class);    job.setMapOutputValueClass(IntWritable.class);            //3.3 set reduce    job.setReducerClass(WordCountReduce.class);    job.setOutputKeyClass(IntWritable.class);    job.setOutputValueClass(IntWritable.class);    //3.4 set input    Path outputPath =new Path(args[1]);    FileOutputFormat.setOutputPath(job, outputPath);        //4.submmit    boolean isSuccess =job.waitForCompletion(true);    return isSuccess?0:1;  }    public static void main(String[] args) throws Exception {    args =new String[]{        "hdfs://Hadoop-senior02.beifeng.com:8020/input/2015082818",        "hdfs://Hadoop-senior02.beifeng.com:8020/output15/"    };    Configuration conf =new Configuration();    conf.set("mapreduce.map.output.compress", "true");    int status=ToolRunner.run(conf, new ProvinceCountMapReduce() , args);    System.exit(status);  }  }

 

3、运行结果

1)运行代码:bin/hdfs dfs -text /output15/par*

2)运行结果:

1 3527
2 1672
3 511
4 325
5 776
6 661
7 95
8 80
9 183
10 93
11 135
12 289
13 264
14 374
15 163
16 419
17 306
18 272
19 226
20 2861
21 124
22 38
23 96
24 100
25 20
26 157
27 49
28 21
29 85
30 42
32 173