1.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，请编写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：
| 20150101 x 20150102 y 20150103 x 20150104 y 20150105 z 20150106 x |
输入文件B的样例如下：
| 20150101 y 20150102 y 20150103 x 20150104 z 20150105 y |
根据输入文件A和B合并得到的输出文件C的样例如下：
| 20150101 x 20150101 y 20150102 y 20150103 x 20150104 y 20150104 z 20150105 y 20150105 z 20150106 x |
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.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 MergeSort {
//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{
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{
public void reduce(Text key, Iterable 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"};
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount ");
System.exit(2);
}
Job job = Job.getInstance(conf,"Merge and duplicate removal");
job.setJarByClass(MergeSort.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);
}
}
2.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：
| 1 1 2 4 3 5 4 12 5 16 6 25 7 33 8 37 9 39 10 40 11 45 |
package Mersort;
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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
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 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{
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{
private static IntWritable line_num = new IntWritable(1);
public void reduce(IntWritable key, Iterable 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{
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=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"};
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount ");
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);
} }
3.对给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：
| child parent Steven Lucy Steven Jack Jone Lucy Jone Jack Lucy Mary Lucy Frank Jack Alice Jack Jesse David Alice David Jesse Philip David Philip Alma Mark David Mark Alma |
输出文件内容如下：
| grandchild grandparent Steven Alice Steven Jesse Jone Alice Jone Jesse Steven Mary Steven Frank Jone Mary Jone Frank Philip Alice Philip Jesse Mark Alice Mark Jesse |
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 MergeSort{
public static int time = 0;
//Map将输入文件按照空格分割成child和parent，然后正序输出一次作为右表，反序输出一次作为左表，需要注意的是在输出的value中必须加上左右表区别标志
public static class Map extends Mapper{
public void map(Object key, Text value, Context context) throws IOException,InterruptedException{
String child_name = new String();
String parent_name = new String();
String relation_type = new String();
String line = value.toString();
int i = 0;
while(line.charAt(i) != ' '){
i++;
}
String[] values = {line.substring(0,i),line.substring(i+1)};
if(values[0].compareTo("child") != 0){
child_name = values[0];
parent_name = values[1];
relation_type = "1";//左右表区分标志
context.write(new Text(values[1]), new Text(relation_type+"+"+child_name+"+"+parent_name));
//左表
relation_type = "2";
context.write(new Text(values[0]), new Text(relation_type+"+"+child_name+"+"+parent_name));
//右表
}
}
}
public static class Reduce extends Reducer{
public void reduce(Text key, Iterable values,Context context) throws IOException,InterruptedException{
if(time == 0){ //输出表头
context.write(new Text("grand_child"), new Text("grand_parent"));
time++;
}
int grand_child_num = 0;
String grand_child[] = new String[10];
int grand_parent_num = 0;
String grand_parent[]= new String[10];
Iterator ite = values.iterator();
while(ite.hasNext()){
String record = ite.next().toString();
int len = record.length();
int i = 2;
if(len == 0) continue;
char relation_type = record.charAt(0);
String child_name = new String();
String parent_name = new String();
//获取value-list中value的child
while(record.charAt(i) != '+'){
child_name = child_name + record.charAt(i);
i++;
}
i=i+1;
//获取value-list中value的parent
while(i");
System.exit(2);
}
Job job = Job.getInstance(conf,"Single table join");
job.setJarByClass(MergeSort.class);
job.setMapperClass(Map.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);
}
}
