MapReduce are included partitioning HashPartitioner
principle : first find hash key map output value, and then reduce the number of mold Task, based on the results of this decision for kv output, reduce task matched removed.
Custom partitioning points need to inherit Partitioner
, replication getpariton()
method
custom partitioning class:
Note : output map is <K, V> key-value pair
where int partitionIndex = dict.get(text.toString())
, partitionIndex
is to obtain the value of K
Appendix: Calculation of the text
Dear Dear Bear Bear River Car Dear Dear Bear Rive
Dear Dear Bear Bear River Car Dear Dear Bear Rive
In the main function to set, specify a custom class partition
custom partitions classes:
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
import java.util.HashMap;
public class CustomPartitioner extends Partitioner<Text, IntWritable> {
public static HashMap<String, Integer> dict = new HashMap<String, Integer>();
//Text代表着map阶段输出的key,IntWritable代表着输出的值
static{
dict.put("Dear", 0);
dict.put("Bear", 1);
dict.put("River", 2);
dict.put("Car", 3);
}
public int getPartition(Text text, IntWritable intWritable, int i) {
//
int partitionIndex = dict.get(text.toString());
return partitionIndex;
}
}
Note : map the output of the key-value <K, V>, int partitionIndex = dict.get(text.toString());
in partitionIndex
that the output value of the key map on the key, i.e. the value of K.
Maper categories:
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String[] words = value.toString().split("\t");
for (String word : words) {
// 每个单词出现1次,作为中间结果输出
context.write(new Text(word), new IntWritable(1));
}
}
}
Reducer categories:
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String[] words = value.toString().split("\t");
for (String word : words) {
// 每个单词出现1次,作为中间结果输出
context.write(new Text(word), new IntWritable(1));
}
}
}
main functions:
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class WordCountMain {
public static void main(String[] args) throws IOException,
ClassNotFoundException, InterruptedException {
if (args.length != 2 || args == null) {
System.out.println("please input Path!");
System.exit(0);
}
Configuration configuration = new Configuration();
configuration.set("mapreduce.job.jar","/home/bruce/project/kkbhdp01/target/com.kaikeba.hadoop-1.0-SNAPSHOT.jar");
Job job = Job.getInstance(configuration, WordCountMain.class.getSimpleName());
// 打jar包
job.setJarByClass(WordCountMain.class);
// 通过job设置输入/输出格式
//job.setInputFormatClass(TextInputFormat.class);
//job.setOutputFormatClass(TextOutputFormat.class);
// 设置输入/输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 设置处理Map/Reduce阶段的类
job.setMapperClass(WordCountMap.class);
//map combine
//job.setCombinerClass(WordCountReduce.class);
job.setReducerClass(WordCountReduce.class);
//如果map、reduce的输出的kv对类型一致,直接设置reduce的输出的kv对就行;如果不一样,需要分别设置map, reduce的输出的kv类型
//job.setMapOutputKeyClass(.class)
// 设置最终输出key/value的类型m
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setPartitionerClass(CustomPartitioner.class);
job.setNumReduceTasks(4);
// 提交作业
job.waitForCompletion(true);
}
}
the main function parameters: