mapreduce编程（二）－ 大象书中求每一年的最高温度

书上的例子是为了取出一年当中气温最高的值，那么将年份和气温做了一个复合的key. 

1 通过设置了partitioner来进行分区。因为分区是按照年份来进行，所以同年的数据就可以分区到一个reducer中。

2 自定义key比较器，按照年份升序，温度值降序。这样map输出的所有kv对就是按照年份升序，温度值降序排列的。

3 自定义分组比较器，所有同一年的数据属于同一个组，那么在reduce输出的时候，只需要取第一个value就能达到输出一年最高气温的目的。 

代码：

package temperature; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.WritableComparable; import org.apache.hadoop.io.WritableComparator; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Partitioner; 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.output.TextOutputFormat; public class Temperature { // 自己定义的key类应该实现WritableComparable接口 public static class IntPair implements WritableComparable { int first; int second; /** * Set the left and right values. */ public void set(int left, int right) { first = left; second = right; } public int getFirst() { return first; } public int getSecond() { return second; } @Override // 反序列化 public void readFields(DataInput in) throws IOException { // TODO Auto-generated method stub first = in.readInt(); second = in.readInt(); } @Override // 序列化 public void write(DataOutput out) throws IOException { // TODO Auto-generated method stub out.writeInt(first); out.writeInt(second); } @Override // key的比较 public int compareTo(IntPair o) { // TODO Auto-generated method stub if (first != o.first) { return first < o.first ? -1 : 1; } else if (second != o.second) { return second < o.second ? -1 : 1; } else { return 0; } } // 新定义类应该重写的两个方法 @Override public int hashCode() { return first * 157 + second; } @Override public boolean equals(Object right) { if (right == null) return false; if (this == right) return true; if (right instanceof IntPair) { IntPair r = (IntPair) right; return r.first == first && r.second == second; } else { return false; } } } /** * 分区函数类。根据first确定Partition。 */ public static class FirstPartitioner extends Partitioner { @Override public int getPartition(IntPair key, NullWritable value, int numPartitions) { return Math.abs(key.getFirst() * 127) % numPartitions; } } /** * key比较函数类。first升序，second降序。 */ public static class KeyComparator extends WritableComparator { protected KeyComparator() { super(IntPair.class, true); } @Override public int compare(WritableComparable w1, WritableComparable w2) { IntPair ip1 = (IntPair) w1; IntPair ip2 = (IntPair) w2; int l = ip1.getFirst(); int r = ip2.getFirst(); int cmp = (l == r ? 0 : (l < r ? -1 : 1)); if (cmp != 0) { return cmp; } l = ip1.getSecond(); r = ip2.getSecond(); return l == r ? 0 : (l < r ? 1 : -1); // reverse } } /** * 分组函数类。属于同一个组的value会放到同一个迭代器中，而比较是否是同一组需要使用GroupingComparator比较器。 */ // 第二种方法，继承WritableComparator public static class GroupingComparator extends WritableComparator { protected GroupingComparator() { super(IntPair.class, true); } @Override // Compare two WritableComparables. public int compare(WritableComparable w1, WritableComparable w2) { IntPair ip1 = (IntPair) w1; IntPair ip2 = (IntPair) w2; int l = ip1.getFirst(); int r = ip2.getFirst(); return l == r ? 0 : (l < r ? -1 : 1); } } // 自定义map public static class Map extends Mapper { private final IntPair intkey = new IntPair(); public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); StringTokenizer tokenizer = new StringTokenizer(line); int left = 0; int right = 0; if (tokenizer.hasMoreTokens()) { left = Integer.parseInt(tokenizer.nextToken()); if (tokenizer.hasMoreTokens()) right = Integer.parseInt(tokenizer.nextToken()); intkey.set(left, right); context.write(intkey, NullWritable.get()); } } } // 自定义reduce // public static class Reduce extends Reducer { private final IntWritable left = new IntWritable(); private final IntWritable right = new IntWritable(); public void reduce(IntPair key, Iterable values, Context context) throws IOException, InterruptedException { left.set(key.getFirst()); right.set(key.getSecond()); context.write(left, right); } } /** * @param args */ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { // TODO Auto-generated method stub // 读取hadoop配置 Configuration conf = new Configuration(); // 实例化一道作业 Job job = new Job(conf, "temperature"); job.setJarByClass(Temperature.class); // Mapper类型 job.setMapperClass(Map.class); // 不再需要Combiner类型，因为Combiner的输出类型对Reduce的输入类型不适用 // job.setCombinerClass(Reduce.class); // Reducer类型 job.setReducerClass(Reduce.class); // 分区函数 job.setPartitionerClass(FirstPartitioner.class); // key比较函数 job.setSortComparatorClass(KeyComparator.class); // 分组函数 job.setGroupingComparatorClass(GroupingComparator.class); // map 输出Key的类型 job.setMapOutputKeyClass(IntPair.class); // map输出Value的类型 job.setMapOutputValueClass(NullWritable.class); // rduce输出Key的类型，是Text，因为使用的OutputFormatClass是TextOutputFormat job.setOutputKeyClass(IntWritable.class); // rduce输出Value的类型 job.setOutputValueClass(IntWritable.class); // 将输入的数据集分割成小数据块splites，同时提供一个RecordReder的实现。 job.setInputFormatClass(TextInputFormat.class); // 提供一个RecordWriter的实现，负责数据输出。 job.setOutputFormatClass(TextOutputFormat.class); // 输入hdfs路径 FileInputFormat.setInputPaths(job, new Path(args[0])); // 输出hdfs路径 FileOutputFormat.setOutputPath(job, new Path(args[1])); // 提交job System.exit(job.waitForCompletion(true) ? 0 : 1); } }