Hadoop学习--Mapper Reduce--day08
mapper类的代码:
实现Mapper类的方法
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class MyMapper extends Mapper
// constant
private static final int MISSING = 9999;
// map function
@Override
protected void map(LongWritable key, Text value, Mapper
throws IOException, InterruptedException {
// per line
String line = value.toString();
// get year
String year = line.substring(15, 19);
// get airtemp
int airTemperature;
if (line.charAt(87) == '+') {
airTemperature = Integer.parseInt(line.substring(88, 92));
} else {
airTemperature = Integer.parseInt(line.substring(87, 92));
}
// valid air temp data
String quality = line.substring(92, 93);
if (airTemperature != MISSING && quality.matches("[01459]")) {
context.write(new Text(year), new IntWritable(airTemperature));
}
}
}
Reduce类的代码:
实现Reducer类的方法
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class MyReducer extends Reducer
@Override
protected void reduce(Text key, Iterable
throws IOException, InterruptedException {
// max
int maxValue = Integer.MIN_VALUE;
// for
for (IntWritable value : values) {
maxValue = Math.max(maxValue, value.get());
}
// output
context.write(key, new IntWritable(maxValue));
}
}
主方法的代码:
import mapper类实现.MyMapper;
import reducer类实现.MyReducer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class MyMapperApp {
/**
* @param args
* @throws Exception
* @throws IllegalArgumentException
*/
public static void main(String[] args) throws IllegalArgumentException, Exception {
// new job
Job job = Job.getInstance();
// find jar by ClassName
job.setJarByClass(MyMapper.class);
// job name
job.setJobName("Max temperature");
FileInputFormat.addInputPath(job, new Path("file:///mnt/hgfs/test-ncdc-data"));
FileOutputFormat.setOutputPath(job, new Path("file:///home/hadoop/mr/"));
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}