MapReduce序列化及分割槽的java程式碼示例
需求
統計每一個使用者（手機號）所耗費的總上行流量、下行流量，總流量，將統計結果按照總流量倒序排序
hadoop jar wordcount.jar cn.itcast.bigdata.mr.flowsum.FlowCount /wordcount/input /wordcount/output8
public class FlowCount {
static class FlowCountMapper extends Mapper<LongWritable, Text, FlowBean, Text>{
//FlowBean k = new FlowBean();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//將一行內容轉成string
String line = value.toString();
//切分欄位
String[] fields = line.split("\t");
//取出手機號
String phoneNbr = fields[1];
//取出上行流量下行流量
long upFlow = Long.parseLong(fields[fields.length-3]);
long dFlow = Long.parseLong(fields[fields.length-2]);
context.write(new FlowBean(upFlow,dFlow), new Text(phoneNbr));
}
}
static class FlowCountReducer extends Reducer<FlowBean, Text, Text, FlowBean>{
@Override
protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
Text phoNum = values.iterator().next();//iterator中只有一個值
context.write(phoNum,key);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
/*conf.set("mapreduce.framework.name", "yarn");
conf.set("yarn.resoucemanager.hostname", "mini1");*/
Job job = Job.getInstance(conf);
/*job.setJar("/home/hadoop/wc.jar");*/
//指定本程式的jar包所在的本地路徑
job.setJarByClass(FlowCount.class);
//指定本業務job要使用的mapper/Reducer業務類
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
//指定mapper輸出資料的kv型別
job.setMapOutputKeyClass(FlowBean.class);
job.setMapOutputValueClass(Text.class);
//指定最終輸出的資料的kv型別
job.setOutputKeyClass(FlowBean.class);
job.setOutputValueClass(Text.class);
//指定job的輸入原始檔案所在目錄
FileInputFormat.setInputPaths(job, new Path(args[0]));
//指定job的輸出結果所在目錄
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//將job中配置的相關引數，以及job所用的java類所在的jar包，提交給yarn去執行
/*job.submit();*/
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}
public class FlowBean implements WritableComparable<FlowBean>{
private long upFlow;
private long dFlow;
private long sumFlow;
//反序列化時，需要反射呼叫空參建構函式，所以要顯示定義一個
public FlowBean(){}
public FlowBean(long upFlow, long dFlow) {
this.upFlow = upFlow;
this.dFlow = dFlow;
this.sumFlow = upFlow + dFlow;
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getdFlow() {
return dFlow;
}
public void setdFlow(long dFlow) {
this.dFlow = dFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
/**
* 序列化方法
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(dFlow);
out.writeLong(sumFlow);
}
/**
* 反序列化方法
* 注意：反序列化的順序跟序列化的順序完全一致
*/
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
dFlow = in.readLong();
sumFlow = in.readLong();
}
@Override
public String toString() {
return upFlow + "\t" + dFlow + "\t" + sumFlow;
}
@Override
public int compareTo(FlowBean o) {
return this.getSumFlow() > o.getSumFlow() ? -1 : 1 ;//按照指定的總流量的倒序排序
}
}
測試內容
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 視訊網站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 資訊保安 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站點統計 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜尋引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站點統計 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 綜合門戶 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 綜合門戶 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜尋引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜尋引擎 69 63 11058 48243 200