接着Hadoop2.4.1 简单的用户手机流量统计的MapReduce程序(二) 现在我们又有了新的需求,我们需要根据用户的手机号码所属的不同省份用不同的reduce来进行处理。
1.环境:Centos 6.5 32位, 在linux环境中开发。
2.核心代码如下:
2.1 Mapper类。package com.npf.hadoop.partition;
import java.io.IOException;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import com.npf.hadoop.FlowBean;
public class FlowCountPartitionMapper extends Mapper<LongWritable, Text, Text, FlowBean>{
private FlowBean flowBean = new FlowBean();
private Text phoneNumKey = new Text();
@Override
protected void map(LongWritable key, Text value,Context context)throws IOException, InterruptedException {
String line = value.toString();
String[] fields = StringUtils.split(line, "\t");
String phoneNumber = fields[1];
long upFlow = Long.valueOf(fields[fields.length - 3]);
long downFlow = Long.valueOf(fields[fields.length - 2]);
flowBean.setPhoneNumber(phoneNumber);
flowBean.setUpFlow(upFlow);
flowBean.setDownFlow(downFlow);
flowBean.setSumFlow(upFlow + downFlow);
phoneNumKey.set(phoneNumber);
context.write(phoneNumKey, flowBean);
}
}
2.2 Reducer类。
package com.npf.hadoop.partition;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import com.npf.hadoop.FlowBean;
public class FlowCountPartitionReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
private FlowBean flowBean = new FlowBean();
@Override
protected void reduce(Text key, Iterable<FlowBean> iterable,Context context)throws IOException, InterruptedException {
long upFlow = 0L;
long downFlow = 0L;
long sumFlow = 0L;
for(FlowBean bean : iterable){
upFlow = upFlow + bean.getUpFlow();
downFlow = downFlow + bean.getDownFlow();
}
sumFlow = upFlow + downFlow;
flowBean.setPhoneNumber(key.toString());
flowBean.setDownFlow(downFlow);
flowBean.setUpFlow(upFlow);
flowBean.setSumFlow(sumFlow);
context.write(key, flowBean);
}
}
2.3 MyPartition类。
136开头的号码存储到0号reduce中,137开头的号码存储到1号reduce中,138开头的号码存储到2号reduce中,139开头的号码存储到3号reduce中,其他的存储在第4号reduce中。
package com.npf.hadoop.partition;
import java.util.HashMap;
import java.util.Map;
import org.apache.hadoop.mapreduce.Partitioner;
public class MyPartition<KEY,VALUE> extends Partitioner<KEY,VALUE>{
private static Map<String,Integer> areaMap = new HashMap<String, Integer>();
static {
areaMap.put("136", 0);
areaMap.put("137", 1);
areaMap.put("138", 2);
areaMap.put("139", 3);
}
@Override
public int getPartition(KEY key, VALUE value, int numPartitions) {
Integer code = areaMap.get(key.toString().substring(0, 3));
return code == null ? 4 : code;
}
}
2.3FlowCountPartitionRunner类。
package com.npf.hadoop.partition;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import com.npf.hadoop.FlowBean;
public class FlowCountPartitionRunner {
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
job.setJarByClass(FlowCountPartitionRunner.class);
job.setMapperClass(FlowCountPartitionMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setReducerClass(FlowCountPartitionReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setPartitionerClass(MyPartition.class);
job.setNumReduceTasks(5);
FileInputFormat.setInputPaths(job, new Path("hdfs://devcitibank:9000/flowCountJob/srcdata"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://devcitibank:9000/flowCountJob/outputdatapar"));
job.waitForCompletion(true);
}
}
3. 我们通过Eclipse将我们的程序打成一个Jar包,打到/root目录下面。Jar包的名字我们命名为flowpartitioncount.jar。
4. ok, 我们来验证下在/root/目录下是否存在我们的Jar包。
5. 验证hadoop集群是否启动。
6. 验证我们在集群中的/flowCountJob/srcdata目录下面是否有我们需要处理的文件。
7.提交flowpartitioncount.jar到hadoop集群中去处理。
8. 执行成功后,我们去hadoop集群中去查看结果。我们有5个Reducer实例,所以产生0~4个处理文件。
分别查看这个5个文件。
part-r-00000
part-r-00001
part-r-00002
part-r-00003
part-r-00004
9. 源代码已托管到GitHub上面: https://github.com/HadoopOrganization/HadoopMapReducerFlowCount