MapReduce Design Patterns-chapter 3

CHAPTER 3：Filtering Patterns

There are a couple of reasons why map-only jobs are efficient.
• Since no reducers are needed, data never has to be transmitted between the map
and reduce phase. Most of the map tasks pull data off of their locally attached disks
and then write back out to that node.
• Since there are no reducers, both the sort phase and the reduce phase are cut out.
This usually doesn’t take very long, but every little bit helps.

Distributed grep

public static class GrepMapper
        extends Mapper {
    private String mapRegex = null;
    public void setup(Context context) throws IOException,
        InterruptedException {
       
        mapRegex = context.getConfiguration().get("mapregex");
    } 
    
    public void map(Object key, Text value, Context context)
        throws IOException, InterruptedException {
        if (value.toString().matches(mapRegex)) {
           context.write(NullWritable.get(), value);
        }
    }
}

Simple Random Sampling

public static class SRSMapper
        extends Mapper {
	private Random rands = new Random();
    private Double percentage;
    protected void setup(Context context) throws IOException,
          InterruptedException {
        // Retrieve the percentage that is passed in via the configuration
        //    like this: conf.set("filter_percentage", .5);
        //         for .5%
        String strPercentage = context.getConfiguration()
                .get("filter_percentage");
        percentage = Double.parseDouble(strPercentage) / 100.0;
    }
    public void map(Object key, Text value, Context context)
          throws IOException, InterruptedException {
        if (rands.nextDouble() < percentage) {
            context.write(NullWritable.get(), value);
        }
    }
}

Bloom Filtering

Bloom filter training.

public class BloomFilterDriver {
    public static void main(String[] args) throws Exception {
        // Parse command line arguments
        Path inputFile = new Path(args[0]);
        int numMembers = Integer.parseInt(args[1]);
        float falsePosRate = Float.parseFloat(args[2]);
        Path bfFile = new Path(args[3]);
        // Calculate our vector size and optimal K value based on approximations
        int vectorSize = getOptimalBloomFilterSize(numMembers, falsePosRate);
        int nbHash = getOptimalK(numMembers, vectorSize);
        // Create new Bloom filter
	BloomFilter filter = new BloomFilter(vectorSize, nbHash,
                Hash.MURMUR_HASH);
        System.out.println("Training Bloom filter of size " + vectorSize
                + " with " + nbHash + " hash functions, " + numMembers
                + " approximate number of records, and " + falsePosRate
                + " false positive rate");
        // Open file for read
        String line = null;
        int numElements = 0;
        FileSystem fs = FileSystem.get(new Configuration());
        for (FileStatus status : fs.listStatus(inputFile)) {
            BufferedReader rdr = new BufferedReader(new InputStreamReader(
                    new GZIPInputStream(fs.open(status.getPath()))));
            System.out.println("Reading " + status.getPath());
            while ((line = rdr.readLine()) != null) {
                filter.add(new Key(line.getBytes()));
                ++numElements;
            }
            rdr.close();
        }
        System.out.println("Trained Bloom filter with " + numElements
            + " entries.");
            
        System.out.println("Serializing Bloom filter to HDFS at " + bfFile);
        FSDataOutputStream strm = fs.create(bfFile);
        filter.write(strm);
        strm.flush();
        strm.close();
        
        System.exit(0);
    }
}

public static class BloomFilteringMapper extends
    Mapper {
  private BloomFilter filter = new BloomFilter();
  protected void setup(Context context) throws IOException,
      InterruptedException {
    // Get file from the DistributedCache
    URI[] files = DistributedCache.getCacheFiles(context
        .getConfiguration());
    System.out.println("Reading Bloom filter from: "
        + files[0].getPath());
    // Open local file for read.
    DataInputStream strm = new DataInputStream(new FileInputStream(
        files[0].getPath()));
    // Read into our Bloom filter.
    filter.readFields(strm);
    strm.close();
  }
  public void map(Object key, Text value, Context context)
      throws IOException, InterruptedException {
    	Map parsed = transformXmlToMap(value.toString());
    // Get the value for the comment
    String comment = parsed.get("Text");
    StringTokenizer tokenizer = new StringTokenizer(comment);
    // For each word in the comment
    while (tokenizer.hasMoreTokens()) {
      // If the word is in the filter, output the record and break
      String word = tokenizer.nextToken();
      if (filter.membershipTest(new Key(word.getBytes()))) {
        context.write(value, NullWritable.get());
        break;
      }
    }
  }
}

This Bloom filter was trained with all user IDs that have a reputation of at least 1,500.

public static class BloomFilteringMapper extends
    Mapper {
private BloomFilter filter = new BloomFilter();
  private HTable table = null;
  protected void setup(Context context) throws IOException,
      InterruptedException {
    // Get file from the Distributed Cache
    URI[] files = DistributedCache.getCacheFiles(context
          .getConfiguration());
    System.out.println("Reading Bloom filter from: "
        + files[0].getPath());
    // Open local file for read.
    DataInputStream strm = new DataInputStream(new FileInputStream(
        files[0].getPath()));
    // Read into our Bloom filter.
    filter.readFields(strm);
    strm.close();
    // Get HBase table of user info
    Configuration hconf = HBaseConfiguration.create();
    table = new HTable(hconf, "user_table");
  }
  public void map(Object key, Text value, Context context)
      throws IOException, InterruptedException {
    Map parsed = transformXmlToMap(value.toString());
    // Get the value for the comment
    String userid = parsed.get("UserId");
    // If this user ID is in the set
      if (filter.membershipTest(new Key(userid.getBytes()))) {
        // Get the reputation from the HBase table
        Result r = table.get(new Get(userid.getBytes()));
        int reputation = Integer.parseInt(new String(r.getValue(
            "attr".getBytes(), "Reputation".getBytes())));
        // If the reputation is at least 1500,
        // write the record to the file system
        if (reputation >= 1500) {
          context.write(value, NullWritable.get());
      }
    }
  }
}

Top Ten

class mapper:
   setup():
      initialize top ten sorted list
   map(key, record):
      insert record into top ten sorted list
      if length of array is greater-than 10 then
         truncate list to a length of 10
   cleanup():
      for record in top sorted ten list:
         emit null,record
class reducer:
   setup():
      initialize top ten sorted list
   reduce(key, records):
      sort records
      truncate records to top 10
      for record in records:

         emit record

Top Ten

map用于产生一个数据块的top ten，利用treeSet进行排序，大于十个时，移除最小的，在cleanup阶段，写出treeSet中的value

public static class TopTenMapper extends
    Mapper {
  // Stores a map of user reputation to the record
  private TreeMap repToRecordMap = new TreeMap();
  public void map(Object key, Text value, Context context)
      throws IOException, InterruptedException {
    Map parsed = transformXmlToMap(value.toString());
    String userId = parsed.get("Id");
    String reputation = parsed.get("Reputation");
    // Add this record to our map with the reputation as the key
    repToRecordMap.put(Integer.parseInt(reputation), new Text(value));
    // If we have more than ten records, remove the one with the lowest rep
    // As this tree map is sorted in descending order, the user with
    // the lowest reputation is the last key.
    if (repToRecordMap.size() > 10) {
	repToRecordMap.remove(repToRecordMap.firstKey());
    }
  }
  protected void cleanup(Context context) throws IOException,
      InterruptedException {
    // Output our ten records to the reducers with a null key
    for (Text t : repToRecordMap.values()) {
      context.write(NullWritable.get(), t);
    }
  }
}

reduce阶段通过values获取得分，然后利用treeSet，与reduce类似

private TreeMap repToRecordMap = new TreeMap();
  public void reduce(NullWritable key, Iterable values,
      Context context) throws IOException, InterruptedException {
    for (Text value : values) {
      Map parsed = transformXmlToMap(value.toString());
      repToRecordMap.put(Integer.parseInt(parsed.get("Reputation")),
          new Text(value));
      // If we have more than ten records, remove the one with the lowest rep
      // As this tree map is sorted in descending order, the user with
      // the lowest reputation is the last key.
      if (repToRecordMap.size() > 10) {
        repToRecordMap.remove(repToRecordMap.firstKey());
      }
    }
    for (Text t : repToRecordMap.descendingMap().values()) {
      // Output our ten records to the file system with a null key
	context.write(NullWritable.get(), t);
    }
  }
}

Distinct

map(key, record):
   emit record,null
reduce(key, records):
   emit key

The mapper takes each record and extracts the data fields for which we want unique values.In our HTTP logs example, this means extracting the user, the web browser,and the device values. The mapper outputs the record as the key, and null as the value.

public static class DistinctUserMapper extends
      Mapper {
  private Text outUserId = new Text();
  public void map(Object key, Text value, Context context)
      throws IOException, InterruptedException {
      
    Map parsed = transformXmlToMap(value.toString());
    // Get the value for the UserId attribute
    String userId = parsed.get("UserId");
    // Set our output key to the user's id
    outUserId.set(userId);
    // Write the user's id with a null value
    context.write(outUserId, NullWritable.get());
  }
}
public static class DistinctUserReducer extends
      Reducer {
  public void reduce(Text key, Iterable values,
      Context context) throws IOException, InterruptedException {
    // Write the user's id with a null value
    context.write(key, NullWritable.get());
  }
}

Combiner optimization.   A combiner can and should be used in the distinct pattern. Duplicate keys will be removed from each local map’s output, thus reducing the amount ofnetwork I/O required. The same code for the reducer can be used in the combiner.