Hadoop은 서로 다른 인용 횟수의 특허 수를 통계한다(3)

3066 단어 hadoop
1. (二)의 기초 위에서 수정하고 코드는 다음과 같다.
 
import java.io.IOException;

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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 *              
 * 
 * @author liuhongbo
 * 
 */
public class PatentCiteCount extends Configured implements Tool {

	public static class PatentCiteCountMapper extends
			Mapper<Text, Text, Text, IntWritable> {

		private final IntWritable one = new IntWritable(1);

		@Override
		protected void map(Text key, Text value, Context context)
				throws IOException, InterruptedException {
			context.write(value, one);
		}
	}

	public static class PatentCiteCountReducer extends
			Reducer<Text, IntWritable, Text, LongWritable> {
		private final LongWritable result = new LongWritable();

		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,
				Context context) throws IOException, InterruptedException {
			int sum = 0;
			for (IntWritable value : values) {
				sum += value.get();
			}
			result.set(sum);
			context.write(key, result);
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		Job job = new Job(getConf());
		job.setJarByClass(getClass());
		job.setJobName("patentcitecount");

		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);

		job.setMapperClass(PatentCiteCountMapper.class);
		job.setReducerClass(PatentCiteCountReducer.class);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);

		FileInputFormat.setInputPaths(job, new Path(
				"/patent/test/input/patentcitecount.txt"));
		FileOutputFormat.setOutputPath(job, new Path("/patent/test/outnput"));

		boolean success = job.waitForCompletion(true);

		return success ? 0 : 1;

	}

	public static void main(String[] args) throws Exception {
		int result = ToolRunner.run(new PatentCiteCount(), args);
		System.exit(result);
	}

}

좋은 웹페이지 즐겨찾기