数据文件格式
根据上述数据文件编写的mapreduce代码
package first.first_maven;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/*
* 模仿hive的rank功能,选择第一个
*/
public class AllocateLog {
public static class MyMapper extends Mapper<LongWritable, Text, IntWritable, IntWritable>{
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String words[]=value.toString().split(",");
// 获取customer_id和分配的id
context.write(new IntWritable(Integer.parseInt(words[2])), new IntWritable(Integer.parseInt(words[0])));
}
}
public static class MyReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{
@Override
protected void reduce(IntWritable key, Iterable<IntWritable> value,Context context)
throws IOException, InterruptedException {
//选取每个customer_id的首次分配id
int tmp=99999999;
for(IntWritable v:value){
if(tmp>v.get()){
tmp=v.get();
}
}
context.write(key, new IntWritable(tmp));
}
}
public static void main(String[] args) throws Exception {
Configuration conf=new Configuration();
Job job = Job.getInstance(conf, "myjob");
job.setJarByClass(WordCount.class);
job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(IntWritable.class);
job.setMapOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job,new Path(args[0]));
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(IntWritable.class);
FileOutputFormat.setOutputPath(job,new Path(args[1]));
int isok=job.waitForCompletion(true)?0:1;
System.exit(isok);
}
}