|
int len = 40000;
int hotel = 1000;
int LM = 1000;
Random ran = new Random();
int type = 0; // 0酒店 1地标
String hdfs_path = "/tmp/hotel";
Configuration hadoopconf = new Configuration();
hadoopconf.set("fs.default.name", "hdfs://m04.ct1.r01.hdp:9000");
FileSystem myFS = FileSystem.get(hadoopconf);
OutputStream out = myFS.create(new Path(hdfs_path));
for (int i = 0; i < hotel; i++) { // 用两个for循环嵌套，打乱酒店/地标数据
// 类型(酒店/地标) id(酒店id/地标id) 纬度 经度
int hx = ran.nextInt(len);
int hy = ran.nextInt(len);
type = 0;
StringBuilder str = new StringBuilder();
str.append(type); // 类型(酒店/地标)
str.append("\t");
str.append(i * 10000); // id(酒店id/地标id)
str.append("\t");
str.append(hx); // 酒店 X
str.append("\t");
str.append(hy);// 酒店 Y
str.append("\r\n");
type = 1;
for (int k = 0; k < LM; k++) {
int lmx = ran.nextInt(len);
int lmy = ran.nextInt(len);
str.append(type); // 类型(酒店/地标)
str.append("\t");
str.append(i * 10000 + k + 1); // id(酒店id/地标id)
str.append("\t");
str.append(lmx); // 地标 X
str.append("\t");
str.append(lmy);// 地标 Y
str.append("\r\n");
}
byte[] midbytes1 = (str.toString()).getBytes("UTF8");
out.write(midbytes1);
System.out.println(i * 1000);
}
out.close();
}
}
MapReduce 找出所有酒店1公里内的所有地标
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.ArrayList;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
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.FileOutputF
上一页 [1] [2] [3] [4] [5] [6] 下一页
| 