MapReduce经典样例
@
mapreduce核心思想是分治
以下样例只涉及基础学习和少量数据，并不需要连接虚拟机
以下样例均可在系统创建的文件夹的part-r-0000中查看结果
MapReduce 经典样例 词频统计
在文件输入一定数量单词，统计各个单词出现次数
代码
package qfnu;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
// mapper组件
class WordCountMapper extends Mapper<LongWritable, Text,
Text, IntWritable>{
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String line = value.toString();
String[] words = line.split(" ");
for(String word : words) {
context.write(new Text(word), new IntWritable(1));
}
}
}
// reducer 组件
class WordCountReducer extends Reducer<Text, IntWritable,
Text, IntWritable>{
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
// TODO Auto-generated method stub
int count = 0;
for(IntWritable value : values) {
count += value.get();
}
context.write(key, new IntWritable(count));
}
}
public class WordCountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance();
job.setJarByClass(WordCountDriver.class);
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 读取数据
FileInputFormat.setInputPaths(job, "D:/hadooptest/count.txt");
// 读入到指定位置，若文件不存在，自动创建
FileOutputFormat.setOutputPath(job, new Path("D:/hadooptest/ansofcount"));
job.waitForCompletion(true);
}
}
我们可以在D:/hadooptest/ansofcount的part-r-0000看到
MapReduce 经典样例 倒排索引
倒排索引是为了更加方便的搜索
代码
package qfnu;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
class InvertedIndexMapper extends Mapper<LongWritable, Text,
Text, Text>{
private static Text keyInfo = new Text();
private static Text valueInfo = new Text("1");
@Override
protected void map(LongWritable key, Text value, Mapper<
LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String line = value.toString();
String[] words = line.split(" ");
FileSplit fileSplit = (FileSplit)context.getInputSplit();
String fileName = fileSplit.getPath().getName();
for(String word : words) {
keyInfo.set(word + ":" + fileName);
context.write(keyInfo, valueInfo);
}
}
}
class InvertedIndexCombiner extends Reducer<
Text, Text, Text, Text>{
private static Text keyInfo = new Text();
private static Text valueInfo = new Text();
@Override
protected void reduce(Text key, Iterable<Text> values,
Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
int count = 0;
for(Text value : values) {
count += Integer.parseInt(value.toString());
}
int splitIndex = key.toString().indexOf(":");
keyInfo.set(key.toString().substring(0, splitIndex));
valueInfo.set(key.toString().substring(splitIndex+1) + ":" + count);
context.write(keyInfo, valueInfo);
}
}
class InvertedIndexReducer extends Reducer<Text, Text, Text, Text>{
private static Text valueInfo = new Text();
@Override
protected void reduce(Text key, Iterable<Text> values,
Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String fileList = "";
for(Text value : values) {
fileList += value.toString() + ";";
}
valueInfo.set(fileList);
context.write(key, valueInfo);
}
}
public class InvertedIndexDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance();
job.setJarByClass(InvertedIndexDriver.class);
job.setMapperClass(InvertedIndexMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setCombinerClass(InvertedIndexCombiner.class);
job.setReducerClass(InvertedIndexReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path("D:/hadooptest/InvertedIndexReducer.txt"));
FileOutputFormat.setOutputPath(job, new Path("D:/hadooptest/ansofInvertedIndexReducer"));
job.waitForCompletion(true);
}
}
MapReduce 经典样例 数据去重
package qfnu;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
class DeDupMapper extends Mapper<LongWritable, Text, Text, Text>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
context.write(value, new Text(""));
}
}
class DeDupReducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text key, Iterable<Text> values,
Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
context.write(key, new Text(""));
}
}
public class DeDupDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance();
job.setJarByClass(DeDupDriver.class);
job.setMapperClass(DeDupMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setReducerClass(DeDupReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path("D:/hadooptest/dedup.txt"));
FileOutputFormat.setOutputPath(job, new Path("D:/hadooptest/ansdedup"));
job.waitForCompletion(true);
}
}
MapReduce 经典样例 TOPN排序
package qfnu;
import java.io.IOException;
import java.util.Comparator;
import java.util.TreeMap;
import org.apache.hadoop.conf.Configuration;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
class TopNMapper extends Mapper<LongWritable, Text,
Text, IntWritable>{
private TreeMap<Integer, String> treeMap =
new TreeMap<Integer, String>();
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String line = value.toString();
String[] values = line.split(" ");
for(String v : values) {
treeMap.put(Integer.parseInt(v), "");
if(treeMap.size() > 5) {
treeMap.remove(treeMap.firstKey());
}
}
}
@Override
protected void cleanup(Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
for(Integer key : treeMap.keySet()) {
context.write(new Text("value"), new IntWritable(key));
}
}
}
class TopNReducer extends Reducer<Text, IntWritable,
IntWritable, Text>{
private TreeMap<Integer, String> treeMap = new TreeMap<Integer, String>(
new Comparator<Integer>() {
public int compare(Integer a, Integer b) {
return b-a;
}
});
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Reducer<Text, IntWritable, IntWritable, Text>.Context context) throws IOException, InterruptedException {
// TODO Auto-generated method stub
for(IntWritable value : values) {
treeMap.put(value.get(), "");
if(treeMap.size() > 5) {
Integer firstKey = treeMap.firstKey();
Integer lastKey = treeMap.lastKey();
treeMap.remove(treeMap.firstKey());
}
}
for(Integer i : treeMap.keySet()) {
context.write(new IntWritable(i), new Text(""));
}
}
}
public class TopNDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("mapreduce.framework.name", "local");
Job job = Job.getInstance();
job.setJarByClass(TopNDriver.class);
job.setMapperClass(TopNMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setReducerClass(TopNReducer.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path("D:/hadooptest/TopN.txt"));
FileOutputFormat.setOutputPath(job, new Path("D:/hadooptest/ansofTopN"));
job.waitForCompletion(true);
}
}
浙公网安备 33010602011771号