//思路根据hadoop原理归并相同人名,以人名为key,以各科成绩为value容器元素,计算容器值的和,除以科目数。
public class AverageScore {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
private Text word = new Text();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
//按照行分割
StringTokenizer line = new StringTokenizer(value.toString(),"\n");
while (line.hasMoreElements()) {
//按照空格分割
StringTokenizer lineBlock = new StringTokenizer(line.nextToken());
String stuName = lineBlock.nextToken();
int stuScore = Integer.parseInt(lineBlock.nextToken());
word.set(stuName);
context.write(word, new IntWritable(stuScore));
}
}
}
public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
int count =0;
while(values.iterator().hasNext()){
sum+=values.iterator().next().get();
count++;
}
int average = sum/count;
result.set(average);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(AverageScore.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.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);
}
}