大数据相关博客的目录
数据集
以TAB为分隔符
- 第一列：序号
- 第二列：手机号
- 第三列：网络IP
- 第四列：访问的域名
- 第五列：上行流量
- 第六列：下行流量
- 第七列：HTTP状态码
1 13736230513 192.196.100.1 www.atguigu.com 2481 24681 200
2 13846544121 192.196.100.2 264 0 200
3 13956435636 192.196.100.3 132 1512 200
4 13966251146 192.168.100.1 240 0 404
5 18271575951 192.168.100.2 www.atguigu.com 1527 2106 200
6 84188413 192.168.100.3 www.atguigu.com 4116 1432 200
7 13590439668 192.168.100.4 1116 954 200
8 15910133277 192.168.100.5 www.hao123.com 3156 2936 200
9 13729199489 192.168.100.6 240 0 200
10 13630577991 192.168.100.7 www.shouhu.com 6960 690 200
11 15043685818 192.168.100.8 www.baidu.com 3659 3538 200
12 15959002129 192.168.100.9 www.atguigu.com 1938 180 500
13 13560439638 192.168.100.10 918 4938 200
14 13470253144 192.168.100.11 180 180 200
15 13682846555 192.168.100.12 www.qq.com 1938 2910 200
16 13992314666 192.168.100.13 www.gaga.com 3008 3720 200
17 13509468723 192.168.100.14 www.qinghua.com 7335 110349 404
18 18390173782 192.168.100.15 www.sogou.com 9531 2412 200
19 13975057813 192.168.100.16 www.baidu.com 11058 48243 200
20 13768778790 192.168.100.17 120 120 200
21 13568436656 192.168.100.18 www.alibaba.com 2481 24681 200
22 13568436656 192.168.100.19 1116 954 200需求
统计每个手机号的总上行流量、总下行流量、总流量
编程
实体类
package club.kwcoder.flowsum;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class FlowWritable implements Writable {
private Integer upFlow;
private Integer downFlow;
private Integer sumFlow;
// 省略空参构造、满参构造、getter/setter、equals、hashCode
@Override
public void write(DataOutput out) throws IOException {
out.writeInt(upFlow);
out.writeInt(downFlow);
out.writeInt(sumFlow);
}
@Override
public void readFields(DataInput in) throws IOException {
this.upFlow = in.readInt();
this.downFlow = in.readInt();
this.sumFlow = in.readInt();
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
}Mapper类
package club.kwcoder.flowsum;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class FlowMapper extends Mapper {
private final Text outKey = new Text();
private final FlowWritable outVal = new FlowWritable();
@Override
protected void map(LongWritable key, Text value, Mapper.Context context) throws IOException, InterruptedException {
String valueStr = value.toString();
if (StringUtils.isBlank(valueStr)) {
return;
}
String[] records = valueStr.split("\t");
String phone = records[1];
int upFlow = Integer.parseInt(StringUtils.isBlank(records[4]) ? "0" : records[4]);
int downFlow = Integer.parseInt(StringUtils.isBlank(records[5]) ? "0" : records[5]);
int sumFlow = upFlow + downFlow;
outKey.set(phone);
outVal.setUpFlow(upFlow);
outVal.setDownFlow(downFlow);
outVal.setSumFlow(sumFlow);
context.write(outKey, outVal);
}
} Reducer类
package club.kwcoder.flowsum;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class FlowReducer extends Reducer {
private final FlowWritable outVal = new FlowWritable();
@Override
protected void reduce(Text key, Iterable values, Reducer.Context context) throws IOException, InterruptedException {
int upFlow = 0, downFlow = 0, sumFlow = 0;
for (FlowWritable value : values) {
upFlow += value.getUpFlow();
downFlow += value.getDownFlow();
sumFlow += value.getSumFlow();
}
outVal.setUpFlow(upFlow);
outVal.setDownFlow(downFlow);
outVal.setSumFlow(sumFlow);
context.write(key, outVal);
}
} Runner类
package club.kwcoder.flowsum;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import java.io.IOException;
public class FlowRunner {
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
FileSystem hdfs = FileSystem.get(conf);
Path input = new Path("/flow/flow.log");
Path output = new Path("/flow_result");
if (hdfs.exists(output)) {
hdfs.delete(output, true);
}
Job job = Job.getInstance(conf, "flowSum");
// 配置运行类
job.setJarByClass(FlowRunner.class);
// 配置输入
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.setInputPaths(job, input);
// 配置Mapper
job.setMapperClass(FlowMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowWritable.class);
// 配置Reducer
job.setReducerClass(FlowReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowWritable.class);
// 配置输出
job.setOutputFormatClass(TextOutputFormat.class);
FileOutputFormat.setOutputPath(job, output);
// 运行
boolean flag = job.waitForCompletion(true);
if (flag) {
System.out.println("flow sum success");
}
hdfs.close();
}
}大数据相关博客的目录