MapReduce实战项目——芝加哥的犯罪数据分析

Configuration conf=new Configuration();

Job job=Job.getInstance(conf,“crime1”);

job.setJobName(“crime1”);

job.setJarByClass(Crime.class);

job.setMapperClass(CMapper.class);

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(Text.class);

job.setReducerClass(CReduce.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);

FileInputFormat.addInputPath(job, new Path(args[0]));

FileOutputFormat.setOutputPath(job,new Path(args[1]));

job.waitForCompletion(true);

}

}

这里是按从小到大的顺序进行警区的排序，由此看出犯罪数量最少的警区是警区1，犯罪数量最多的是警区934，判断出来警区1 的治安比较好。

2.这里是按警区进行分组，然后统计每一组的逮捕数量，逮捕数量即为警察在案件发生后，成功抓捕犯罪人员的次数。逮捕数量高，说明这个警区的警察抓捕成功率更高，更容易抓到犯罪人员。

//这里的代码实现的是按地区District进行分组，然后统计逮捕数

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;

import org.apache.hadoop.mapreduce.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.Mapper.Context;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Crime {

private static class CMapper extends Mapper<LongWritable , Text, Text, IntWritable>{

Text dis=new Text();

//private final static IntWritable one = new IntWritable();

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

String line = value.toString();

String[] l = line.split(“,”);

dis.set(l[11]);

String arr=l[8];

String a =“FALSE”;

int b=0;

if (arr.equals(a)){

b=1;

}

else {

b=0;

}

if(b==0){

context.write(dis, new IntWritable(1));

}

}

}

public static class CReduce extends Reducer<Text, IntWritable, Text, IntWritable>{

public