Mapreduce例項——二次排序
阿新 • • 發佈：2021-11-19
在電商網站中，使用者進入頁面瀏覽商品時會產生訪問日誌，記錄使用者對商品的訪問情況，現有goods_visit2表，包含（goods_id,click_num）兩個欄位，資料內容如下：
goods_id click_num
1010037 100
1010102 100
1010152 97
1010178 96
1010280 104
1010320 103
1010510 104
1010603 96
1010637 97
goods_visit2
編寫MapReduce程式碼，功能為根據商品的點選次數(click_num)進行降序排序，再根據goods_id升序排序，並輸出所有商品：
packagemapreduce8; 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.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; //07.Mapreduce例項——二次排序 public class SecondarySort { public static class IntPair implements WritableComparable<IntPair> { int first; int second; public void set(int left, int right) { first = left; second = right; } public int getFirst() { return first; } public int getSecond() { return second; } @Override public void readFields(DataInput in) throws IOException { // TODO Auto-generated method stub first = in.readInt(); second = in.readInt(); } @Override public void write(DataOutput out) throws IOException { // TODO Auto-generated method stub out.writeInt(first); out.writeInt(second); } @Override 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; } } @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; } } } public static class FirstPartitioner extends Partitioner<IntPair, IntWritable> { @Override public int getPartition(IntPair key, IntWritable value,int numPartitions) { return Math.abs(key.getFirst() * 127) % numPartitions; } } 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); } } public static class Map extends Mapper<LongWritable, Text, IntPair, IntWritable> { private final IntPair intkey = new IntPair(); private final IntWritable intvalue = new IntWritable(); 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(right, left); intvalue.set(left); context.write(intkey, intvalue); } } } public static class Reduce extends Reducer<IntPair, IntWritable, Text, IntWritable> { private final Text left = new Text(); private static final Text SEPARATOR = new Text("------------------------------------------------"); public void reduce(IntPair key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException { context.write(SEPARATOR, null); left.set(Integer.toString(key.getFirst())); System.out.println(left); for (IntWritable val : values) { context.write(left, val); //System.out.println(val); } } } public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = new Job(conf, "secondarysort"); job.setJarByClass(SecondarySort.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); job.setPartitionerClass(FirstPartitioner.class); job.setGroupingComparatorClass(GroupingComparator.class); job.setMapOutputKeyClass(IntPair.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); String[] otherArgs=new String[2]; otherArgs[0]="hdfs://192.168.51.100:8020/mymapreduce8/in/goods_visit2"; otherArgs[1]="hdfs://192.168.51.100:8020/mymapreduce8/out"; FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
結果：
原理：
在Map階段，使用job.setInputFormatClass定義的InputFormat將輸入的資料集分割成小資料塊splites，同時InputFormat提供一個RecordReder的實現。本實驗中使用的是TextInputFormat，他提供的RecordReder會將文字的位元組偏移量作為key，這一行的文字作為value。這就是自定義Map的輸入是<LongWritable, Text>的原因。然後呼叫自定義Map的map方法，將一個個<LongWritable, Text>鍵值對輸入給Map的map方法。注意輸出應該符合自定義Map中定義的輸出<IntPair, IntWritable>。最終是生成一個List<IntPair, IntWritable>。在map階段的最後，會先呼叫job.setPartitionerClass對這個List進行分割槽，每個分割槽對映到一個reducer。每個分割槽內又呼叫job.setSortComparatorClass設定的key比較函式類排序。可以看到，這本身就是一個二次排序。 如果沒有通過job.setSortComparatorClass設定key比較函式類，則可以使用key實現的compareTo方法進行排序。 在本實驗中，就使用了IntPair實現的compareTo方法。
在Reduce階段，reducer接收到所有對映到這個reducer的map輸出後，也是會呼叫job.setSortComparatorClass設定的key比較函式類對所有資料對排序。然後開始構造一個key對應的value迭代器。這時就要用到分組，使用job.setGroupingComparatorClass設定的分組函式類。只要這個比較器比較的兩個key相同，他們就屬於同一個組，它們的value放在一個value迭代器，而這個迭代器的key使用屬於同一個組的所有key的第一個key。最後就是進入Reducer的reduce方法，reduce方法的輸入是所有的（key和它的value迭代器）。同樣注意輸入與輸出的型別必須與自定義的Reducer中宣告的一致。