MapReduce实战项目——芝加哥的犯罪数据分析，互联网架构师前景如何

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, Text>{

Text dis=new Text();

Text cnumber =new Text();

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

String line = value.toString();

String[] l = line.split(",");

dis.set(l[11]);

cnumber.set(l[1]);

context.write(dis, cnumber);

}

}

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

private int sum=0;

public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException{

for(Text t : values){

sum=sum+1;

}

context.write(new Text(key),new IntWritable(sum));

}

}

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

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);

}

}