hadoop对专利数据进行处理，输出引用次数以及该引用次数的专利总数

这个结果需要引用我上篇文章的实验结果，结果如下：

将这个输出结果作为输入，输出为引用次数以及该引用次数的专利总数

代码如下：

package com.hadoop.test;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * 对专利数据进行处理，输出引用次数以及该引用次数的专利总数
 * 
 * @author root 2014-12-28
 */
public class CitationHistorgram extends Configured implements Tool {

	public static class MapClass extends MapReduceBase implements
			Mapper<Text, Text, IntWritable, IntWritable> {
		private final static IntWritable uno = new IntWritable(1);
		private IntWritable citationCount = new IntWritable();

		@Override
		public void map(Text key, Text value,
				OutputCollector<IntWritable, IntWritable> output,
				Reporter reporter) throws IOException {
			// TODO Auto-generated method stub
			// 只对value进行收集处理
			citationCount.set(Integer.parseInt(value.toString()));
			output.collect(citationCount, uno);
		}

	}

	public static class Reduce extends MapReduceBase implements
			Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {

		@Override
		public void reduce(IntWritable key, Iterator<IntWritable> values,
				OutputCollector<IntWritable, IntWritable> output,
				Reporter reporter) throws IOException {
			// TODO Auto-generated method stub
			int count = 0;
			while (values.hasNext()) {
				count += values.next().get();
			}
			output.collect(key, new IntWritable(count));
		}

	}

	@Override
	public int run(String[] arg0) throws Exception {
		// TODO Auto-generated method stub
		Configuration conf = getConf();
		JobConf job = new JobConf(conf, CitationHistorgram.class);

		Path in = new Path(arg0[0]);
		Path out = new Path(arg0[1]);

		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setJobName("CitationHistorgram");
		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);

		job.setInputFormat(KeyValueTextInputFormat.class);
		job.setOutputFormat(TextOutputFormat.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(IntWritable.class);

		JobClient.runJob(job);

		return 0;
	}

	public static void main(String[] args) throws Exception {
		// 定义本地输入文件路径
		String inputPath = "hdfs://znb:9000/output/CountPatent/";
		// 定义输出的HDFS文件路径
		String outputPath = "hdfs://znb:9000/output/CitationHistorgram/";
		String[] args1 = { inputPath, outputPath };
		int res = ToolRunner.run(new Configuration(), new CitationHistorgram(), args1);
		System.exit(res);
	}
}

输出结果为：