Java 코드 통계 사이트의 성별 사용자 접근 수

수요
log 로그에서 지정한 정보에 대해 웹 사이트의 서로 다른 성 사용자의 방문 수를 통계합니다
2. 프로그래밍 코드

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. 실행 결과
1) 실행 코드:bin/hdfs dfs -text/output15/par*
2) 실행 결과:
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
위에서 말한 것은 여러분이 소개해 드린 자바 코드 통계 사이트에서 서로 다른 성 사용자의 방문수에 대한 소개입니다. 여러분께 도움이 되었으면 합니다. 이 편집에서도 저희 사이트에 대한 지지에 감사드립니다!