Group+Count+Sum

2019独角兽企业重金招聘Python工程师标准>>>

GroupOpration

字段依次为：
_编号No
姓名Name
学科Subject
分数Score _

功能：按用户获取count(1)和sum(分数)

SQL表示：
_select Name,count(1),sum(score)
from table
where Name in ('zyl','lyy')
group by Name
_

输入input：
_1 zyl English 80
2 zyl Math 50
3 lyy English 90
4 lyy Chinese 80 _

输出output：
_zyl 2 130
lyy 2 170 _

import java.io.IOException;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class GroupOpration {
	public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

		private String[] FilterStrings = { "zyl", "lyy" };
		private List<String> FilterList = Arrays.asList(FilterStrings);
		private Text name = new Text();
		private IntWritable score= new IntWritable();

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
			StringTokenizer StringTokenLine = new StringTokenizer(value.toString(), " ");
			
			while (StringTokenLine.hasMoreTokens()) {
				String No = StringTokenLine.nextToken();
				String Name = StringTokenLine.nextToken();
				if (FilterList.contains(Name)) {
					String Subject = StringTokenLine.nextToken();
					String Score = StringTokenLine.nextToken();
					name.set(Name);
					score.set(Integer.parseInt(Score));
					context.write(name,score);
				} else
					continue;

			}
		}
	}

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

		public void reduce(Text key, Iterable<IntWritable> values, Context context)
				throws IOException, InterruptedException {
			int sum = 0;
			int count = 0;
			for (IntWritable val : values) {
				sum += val.get();
				count++;
			}
			context.write(key, new Text(Integer.toString(count) + " " + Integer.toString(sum)));
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		String HADOOP_HOME = System.getenv("HADOOP_HOME");
		String HADOOP_CONF_DIR = HADOOP_HOME + "/etc/hadoop";
		conf.addResource(new Path(HADOOP_CONF_DIR + "/core-site.xml"));
		conf.addResource(new Path(HADOOP_CONF_DIR + "/hdfs-site.xml"));
		conf.addResource(new Path(HADOOP_CONF_DIR + "/yarn-site.xml"));
		conf.set("mapreduce.job.ubertask.enable", "true");
		conf.set("mapred.textoutputformat.separator", " ");
		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		if (otherArgs.length < 2) {
			System.err.println("Usage: GroupOpration <in> [<in>...] <out>");
			System.exit(2);
		}
		Job job = Job.getInstance(conf, "GroupOpration");
		job.setJarByClass(GroupOpration.class);
		job.setMapperClass(TokenizerMapper.class);
		//job.setCombinerClass(GroupReducer.class);
		job.setReducerClass(GroupReducer.class);
		job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(IntWritable.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		for (int i = 0; i < otherArgs.length - 1; ++i) {
			FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
		}
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

转载于:https://my.oschina.net/yulongblog/blog/741074