Hadoop 学习笔记 (十一) MapReduce 求平均成绩

china:
张三 78
李四 89
王五 96
赵六 67
english
张三 80
李四 82
王五    84
赵六 86
math
张三 88
李四 99
王五 66
赵六 77 import java.io.IOException; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.FloatWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer; public class MyAverage { public static class FormatMapper extends Mapper<Object, Text, Text, IntWritable>{ private IntWritable val = new IntWritable(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
String line[] = value.toString().split("\\s");
val.set(Integer.parseInt(line[]));
context.write(new Text(line[]), val);
}
} public static class AverageReducer extends Reducer<Text, IntWritable, Text, FloatWritable>{
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException{
int count = ;
int sum = ;
for (IntWritable val : values) {
sum += val.get();
count ++;
}
float ave = (float)sum / count;
context.write(key, new FloatWritable(ave));
}
} public static void main(String[] args) throws Exception {
String dir_in = "hdfs://localhost:9000/in_average";
String dir_out = "hdfs://localhost:9000/out_average"; Path in = new Path(dir_in);
Path out = new Path(dir_out); Configuration conf = new Configuration();
Job averageJob = new Job(conf, "my_average"); averageJob.setJarByClass(MyAverage.class); averageJob.setInputFormatClass(TextInputFormat.class);
averageJob.setMapperClass(FormatMapper.class);
averageJob.setCombinerClass(IntSumReducer.class);
//countJob.setPartitionerClass(HashPartitioner.class);
averageJob.setMapOutputKeyClass(Text.class);
averageJob.setMapOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(averageJob, in); averageJob.setReducerClass(AverageReducer.class);
//averageJob.setNumReduceTasks(1);
averageJob.setOutputKeyClass(Text.class);
averageJob.setOutputValueClass(FloatWritable.class);
//countJob.setOutputFormatClass(SequenceFileOutputFormat.class); FileOutputFormat.setOutputPath(averageJob, out); averageJob.waitForCompletion(true); } }
张三    82.0
李四 90.0
王五 82.0
赵六 76.666664

 
上一篇:Hadoop学习记录(4)|MapReduce原理|API操作使用


下一篇:drf源码系列