本身求平均數很簡單的，必須用到combine的話我在兩個地方廢了很多時間，

一是combine的輸入不僅僅是map的輸出，還有可能是combine的輸出，所以對value的處理得分兩種情況吧；

二是結果要保留4位有效數字。。。噗，注意保留4位有效數字不等于小數點后面有四位，第二不能用parse！它只能轉成整形。

第三，代碼寫的實在比較挫，哎。

import java.io.IOException;

import java.math.BigDecimal;

import java.math.MathContext;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.DoubleWritable;

import org.apache.hadoop.io.LongWritable;

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;

public class Avg {

public static class Map extends

Mapper

{

protected void map(LongWritable

key, Text value, Context context)

throws

IOException, InterruptedException {

String line =

value.toString();

StringTokenizer

words = new StringTokenizer(line, "\n");

//

對每一行進行分割

while

(words.hasMoreElements()) {

StringTokenizer

tokenizerLine = new StringTokenizer(

words.nextToken());

String

strAlp = tokenizerLine.nextToken();

String

strData = tokenizerLine.nextToken();

Text

alphabet = new Text(strAlp);

Text

score = new Text(strData);

context.write(alphabet,

score);

}

}

}

public static class Combine extends

Reducer

{

//將部分和以及出現次數共同作為value

private Text tmp = new

Text();

public void reduce(Text key,

Iterable values, Context context)

throws

IOException, InterruptedException {

//

統計某字母出現次數和部分和

int sum =

0;

int count =

0;

String[]

val_input = null;

for (Text val

: values) {

if((val_input=val.toString().split(":")).length==2){

sum

+= Integer.parseInt(val_input[0].toString());

count

+=

Integer.parseInt(val_input[1].toString());?}

else{

sum

+= Integer.parseInt(val.toString());

count++;

}

}?// 設置value值為部分和以及出現次數

tmp.set(sum +

":" + count);

context.write(key, tmp);

}

}

public static class Reduce extends Reducer

{

private String tmp_sum = new

String();

private String tmp_count = new

String();

public void reduce(Text key,

Iterable values, Context context)

throws IOException, InterruptedException {

int sum_all =

0;

int count_all

=

0;?for (Text val

: values) {

String

str_tmp=val.toString();

//將部分和以及出現次數分割，分別求和

int

splitIndex = str_tmp.indexOf(":");

tmp_sum

= str_tmp.substring(0, splitIndex);

tmp_count

= str_tmp.substring(splitIndex+1);

int

int_sum = Integer.parseInt(tmp_sum);

int

int_count =

Integer.parseInt(tmp_count);?sum_all

+= int_sum;

count_all += int_count;

}?double average = (sum_all * 1.0) / (count_all *

1.0);?MathContext mathContext = new MathContext(4);

BigDecimal c = new BigDecimal(average);

BigDecimal aver_final = c.round(mathContext);

double aver_4 = aver_final.doubleValue();

String str_aver = String.valueOf(aver_4);

Text aver = new Text();

aver.set(str_aver);

context.write(key, aver);

}

}

public static void main(String[] args) throws

Exception {

Configuration conf = new

Configuration();

Job job = new Job(conf,

"Avg_use_combine");

job.setJarByClass(Avg.class);

job.setMapperClass(Map.class);

job.setCombinerClass(Combine.class);

job.setReducerClass(Reduce.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(Text.class);

FileInputFormat.addInputPath(job,

new Path(args[0]));

FileOutputFormat.setOutputPath(job,

new Path(args[1]));

System.exit(job.waitForCompletion(true)

? 0 : 1);

}

}

總結

以上是生活随笔為你收集整理的bigdecimal 平均数_MapReduce实例-必须用Combine--求平均数的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。