我目前刚接触Hadoop。所以我在MapReduce中找到了这个已解决的代码片段,它找出了“每年最多'数据工程师'工作的国家/地区”(例如,如果格式为 的数据(年份,地区) ,计数(工作)) 是 “2016,'XYZ',35” 和 “2016,'ABC ',25“ 和 ”2015,'sdf',14“ ,答案是”2016,'XYZ' ,35“和”2015,'sdf',14“),但我无法理解减速器中的部件如下: -
if (Top5DataEngineer.size() > 1)
Top5DataEngineer.remove(Top5DataEngineer.firstKey());
}//Ignore this bracket for the time being.
protected void cleanup(Context context) throws IOException,
InterruptedException {
for (Text t : Top5DataEngineer.descendingMap().values())
context.write(NullWritable.get(), t);
}
这是完整的代码: -
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Partitioner;
import java.util.TreeMap;
import org.apache.hadoop.mapreduce.Reducer;
public class Q_002a {
public static class Q_002a_Mapper extends
Mapper<LongWritable, Text, Text, LongWritable> {
LongWritable one = new LongWritable(1);
public void map(LongWritable key, Text values, Context context)
throws IOException, InterruptedException {
try {
if (key.get() > 0)
{
String[] token = values.toString().split("\t");
if (token[4].equals("DATA ENGINEER")) {
Text answer = new Text(token[8] + "\t" + token[7]);
context.write(answer, one);
}
}
} catch (ArrayIndexOutOfBoundsException e) {
System.out.println(e.getMessage());
} catch (ArithmeticException e1) {
System.out.println(e1.getMessage());
}
}
}
public static class Q_002a_Partitioner extends Partitioner<Text, LongWritable> {
@Override
public int getPartition(Text key, LongWritable value, int numReduceTasks) {
String[] str = key.toString().split("\t");
if (str[1].equals("2011"))
return 0;
if (str[1].equals("2012"))
return 1;
if (str[1].equals("2013"))
return 2;
if (str[1].equals("2014"))
return 3;
if (str[1].equals("2015"))
return 4;
if (str[1].equals("2016"))
return 5;
else
return 6;
}
}
public static class Q_002a_Reducer extends
Reducer<Text, LongWritable, NullWritable, Text> {
private TreeMap<LongWritable, Text> Top5DataEngineer = new TreeMap<LongWritable, Text>();
long sum = 0;
public void reduce(Text key, Iterable<LongWritable> values,
Context context) throws IOException, InterruptedException {
sum = 0;
for (LongWritable val : values) {
sum += val.get();
}
Top5DataEngineer.put(new LongWritable(sum), new Text(key + ","
+ sum));
if (Top5DataEngineer.size() > 1)
Top5DataEngineer.remove(Top5DataEngineer.firstKey());
}
protected void cleanup(Context context) throws IOException,
InterruptedException {
for (Text t : Top5DataEngineer.descendingMap().values())
context.write(NullWritable.get(), t);
}
}
public static void main(String args[]) throws IOException,
InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "Top 5 Data Engineer in a worksite");
job.setJarByClass(Q_002a.class);
job.setMapperClass(Q_002a_Mapper.class);
job.setPartitionerClass(Q_002a_Partitioner.class);
job.setReducerClass(Q_002a_Reducer.class);
job.setNumReduceTasks(6);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
这是我得到的输出: -
编辑: - 我尝试在reduce()方法中运行cleanup()方法中的代码,但它没有按预期工作。它只在cleanup()方法中运行正常。任何有关这方面的帮助将不胜感激。
答案 0 :(得分:1)
cleanup()
方法。它只会被调用一次。
在您的示例中reduce()
方法是&#34;搜索&#34;数据工程师在城市中划分的最大数量。 Top5DataEngineer
TreeMap以排序(升序)顺序存储密钥,并且在每次迭代时,如果它具有多个密钥,它只删除第一个密钥(较小密钥)。换句话说,在处理Iterable<LongWritable>
值后,您将获得每个&#39;年中工作次数最多的城市。分区。
当reducer阶段结束时,cleanup()
方法只会写入每个已处理分区的结果(Top5DataEngineer
映射中的单个/最大kv对)。
cleanup()
方法会在每个&#39;年内被调用一次。划分。
希望它会对你有所帮助。