来源吴超7天视频
1.求最大K个值
import java.io.IOException;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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;
public class TopKnum {
static final String INPUT_PATH = "hdfs://hadoop0:9000/input";
static final String OUT_PATH = "hdfs://hadoop0:9000/out";
static final int K=100;
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
final Path outPath = new Path(OUT_PATH);
if(fileSystem.exists(outPath)){
fileSystem.delete(outPath, true);
}
final Job job = new Job(conf , TopKnum.class.getSimpleName());
FileInputFormat.setInputPaths(job, INPUT_PATH);
job.setMapperClass(MyMapper.class);
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(LongWritable.class);
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(LongWritable.class);
job.setOutputValueClass(NullWritable.class);
FileOutputFormat.setOutputPath(job, outPath);
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, LongWritable, LongWritable>{
private Long[] top = new Long[K];
{
for(int j=0;j<100;j++)
top[j]=0L;
}
@Override
protected void map(LongWritable k1, Text v1,
org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, LongWritable, LongWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
Long temp=Long.parseLong(v1.toString());
if(temp>top[0]){
top[0]=temp;
int i=0;
for(;i<99&&temp>top[i+1];i++){
top[i]=top[i+1];
}
top[i]=temp;
}
}
@Override
protected void cleanup(
org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, LongWritable, LongWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
for(int i=0;i<100;i++){
context.write(new LongWritable(top[i]),new LongWritable(top[i]));
}
}
}
static class MyReducer extends Reducer<LongWritable, LongWritable, LongWritable, NullWritable>{
private Long[] top = new Long[K];
{
for(int j=0;j<100;j++)
top[j]=0L;
}
@Override
protected void reduce(LongWritable k2, Iterable<LongWritable> v2s,
org.apache.hadoop.mapreduce.Reducer<LongWritable, LongWritable, LongWritable, NullWritable>.Context arg2)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
for (LongWritable v2 : v2s) {
Long temp=v2.get();
if(temp>top[0])
{
int i=0;
for(;i<99&&temp>top[i+1];i++){
top[i]=top[i+1];
}
top[i]=temp;
}
}
}
@Override
protected void cleanup(
org.apache.hadoop.mapreduce.Reducer<LongWritable, LongWritable, LongWritable, NullWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
for(int i=0;i<100;i++){
context.write(new LongWritable(top[i]), NullWritable.get());
}
}
}
}
2.求最大值
import java.net.URI;
import mapreduce.WordCountApp;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
* 作业:求最大的100个值
*/
public class TopKApp {
static final String INPUT_PATH = "hdfs://hadoop0:9000/input";
static final String OUT_PATH = "hdfs://hadoop0:9000/out";
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
final Path outPath = new Path(OUT_PATH);
if(fileSystem.exists(outPath)){
fileSystem.delete(outPath, true);
}
final Job job = new Job(conf , TopKApp.class.getSimpleName());
FileInputFormat.setInputPaths(job, INPUT_PATH);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(LongWritable.class);
job.setOutputValueClass(NullWritable.class);
FileOutputFormat.setOutputPath(job, outPath);
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, LongWritable, NullWritable>{
long max = Long.MIN_VALUE;
protected void map(LongWritable k1, Text v1, Context context) throws java.io.IOException ,InterruptedException {
final long temp = Long.parseLong(v1.toString());
if(temp>max){
max = temp;
}
};
protected void cleanup(org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,LongWritable, NullWritable>.Context context) throws java.io.IOException ,InterruptedException {
context.write(new LongWritable(max), NullWritable.get());
};
}
static class MyReducer extends Reducer<LongWritable, NullWritable, LongWritable, NullWritable>{
long max = Long.MIN_VALUE;
protected void reduce(LongWritable k2, java.lang.Iterable<NullWritable> arg1, org.apache.hadoop.mapreduce.Reducer<LongWritable,NullWritable,LongWritable,NullWritable>.Context arg2) throws java.io.IOException ,InterruptedException {
final long temp = k2.get();
if(temp>max){
max = temp;
}
};
protected void cleanup(org.apache.hadoop.mapreduce.Reducer<LongWritable,NullWritable,LongWritable,NullWritable>.Context context) throws java.io.IOException ,InterruptedException {
context.write(new LongWritable(max), NullWritable.get());
};
}
}