MapReduce编程之统计二手房数目
要求:统计出上海各个地区二手房的数目,其中将浦东的二手房单独由一个Reduce计算
分析:由于浦东区的二手房数目需要单独统计,因此需要设置分区器,同时设置ReduceTask为2
代码实现:
package com.miao.secondhouse;
import com.miao.partition.UserPartition;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import java.io.IOException;
/**
* @ClassName SecondHouseNum
* @Description TODO 统