学号:2120011013
(一)编程实现文件合并和去重操作
对于两个输入文件,即文件A和文件B,编写MapReduce程序,对两个文件进行合并,并剔除其中重复的内容,得到一个新的输出文件C。下面是输入文件和输出文件的一个样例供参考。
输入文件A的样例如下:
|
输入文件B的样例如下:
|
根据输入文件A和B合并得到的输出文件C的样例如下:
|
package shiyan4;
import java.io.IOException;
public class Merge {
//重载map函数,直接将输入中的value复制到输出数据的key上
public static class Map extends Mapper<Object, Text, Text, Text>{
private static Text text = new Text();
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
text = value;
context.write(text, new Text(""));
}
}
//重载reduce函数,直接将输入中的key复制到输出数据的key上
public static class Reduce extends Reducer<Text, Text, Text, Text>{
public void reduce(Text key, Iterable<Text> values, Context context ) throws IOException,InterruptedException{
context.write(key, new Text(""));
}
}
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and duplicate removal");
job.setJarByClass(Merge.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
(二)编写程序实现对输入文件的排序
现在有多个输入文件,每个文件中的每行内容均为一个整数。要求读取所有文件中的整数,进行升序排序后,输出到一个新的文件中,输出的数据格式为每行两个整数,第一个数字为第二个整数的排序位次,第二个整数为原待排列的整数。下面是输入文件和输出文件的一个样例供参考。
输入文件1的样例如下:
33 37 12 40 |
输入文件2的样例如下:
4 16 39 5 |
输入文件3的样例如下:
1 45 25 |
根据输入文件1、2和3得到的输出文件如下:
|
package shiyan4;
import java.io.IOException;
public class MergeSort {
//map函数读取输入中的value,将其转化成IntWritable类型,最后作为输出key
public static class Map extends Mapper<Object, Text, IntWritable, IntWritable>{
private static IntWritable data = new IntWritable();
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
String text = value.toString();
data.set(Integer.parseInt(text));
context.write(data, new IntWritable(1));
}
}
//reduce函数将map输入的key复制到输出的value上,然后根据输入的value-list中元素的个数决定key的输出次数,定义一个全局变量line_num来代表key的位次
public static class Reduce extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{
private static IntWritable line_num = new IntWritable(1);
public void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException,InterruptedException{
for(IntWritable val : values){
context.write(line_num, key);
line_num = new IntWritable(line_num.get() + 1);
}
}
}
//自定义Partition函数,此函数根据输入数据的最大值和MapReduce框架中Partition的数量获取将输入数据按照大小分块的边界,然后根据输入数值和边界的关系返回对应的Partiton ID
public static class Partition extends Partitioner<IntWritable, IntWritable>{
public int getPartition(IntWritable key, IntWritable value, int num_Partition){
int Maxnumber = 65223;//int型的最大数值
int bound = Maxnumber/num_Partition+1;
int keynumber = key.get();
for (int i = 0; i<num_Partition; i++){
if(keynumber<bound * (i+1) && keynumber>=bound * i){
return i;
}
}
return -1;
}
}
public static void main(String[] args) throws Exception{
// TODO Auto-generated method stub
Configuration conf = new Configuration();
conf.set("fs.default.name","hdfs://localhost:9000");
String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in><out>");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and sort");
job.setJarByClass(MergeSort.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setPartitionerClass(Partition.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
(三)对指定的表格进行信息挖掘
下面给出一个child-parent的表格,要求挖掘其中的父子辈关系,给出祖孙辈关系的表格。
输入文件内容如下
|
输出文件内容如下:
|
package shiyan4;
import java.io.IOException;
import java.util.*;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class Child2Parent {
public static class Mymapper extends Mapper<Object, Text, Text, Text>{
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
String[] cap=value.toString().split("[\\s|\\t]+");//分割数据
if (!"child".equals(cap[0])) {
String cName = cap[0];
String pName = cap[1];
context.write(new Text(pName), new Text("r#"+cName));//打标签
context.write(new Text(cName), new Text("l#"+pName));
}
}
}
public static class Myreduce extends Reducer<Text, Text, Text, Text>{
public static int runtime = 0;
public void reduce(Text key, Iterable<Text> values,Context context) throws IOException,InterruptedException{
if (runtime == 0) {
context.write(new Text("grandchild"), new Text("grandparent"));
runtime++;
}
List<String> grandChild = new ArrayList<>();
List<String> grandParent = new ArrayList<>();
for (Text text : values) {
String[] relation = text.toString().split("#");
if ("l".equals(relation[0])) {
grandChild.add(relation[1]);
} else {
grandParent.add(relation[1]);
}
}
for (String l:grandChild) {
for (String r:grandParent) {
context.write(new Text(r), new Text(l));
}
}
}
}
public static void main(String[] args) throws Exception{
Configuration conf = new Configuration();
Job job = Job.getInstance(conf,"TableJoin");
job.setJarByClass(Child2Parent.class);
job.setMapperClass(Child2Parent.Mymapper.class);
job.setReducerClass(Child2Parent.Myreduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path("hdfs://localhost:9000/user/hadoop/input"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/user/hadoop/output"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}