Examples of edu.umd.cloud9.collection.line.NumberTextDocuments

edu.umd.cloud9.io.map.HMapSFW

Program that builds the mapping from docids (String identifiers) to docnos (sequentially-numbered ints) for regular text documents. The program takes four command-line arguments:
@author Ferhan Ture

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(enwikiEn + "/test_wt-term-doc-vectors/part-00000")));
    reader.next(key, value);
    verifyTermDocVector(enTermDocVector1, value);

View Full Code Here

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(dewikiEn + "/test_wt-term-doc-vectors/part-00000")));
    reader.next(key, value);
    verifyTermDocVector(deTermDocVector1, value);

View Full Code Here

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(enwikiEn + "/test_wt-term-doc-vectors/part-00000")));
    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(enTermDocVector1, value);


    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(enTermDocVector2, value);
    reader.close();
  }

View Full Code Here

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(dewikiEn + "/test_wt-term-doc-vectors/part-00000")));
    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(deTermDocVector1, value);


    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(deTermDocVector2, value);
    reader.close();
  }

View Full Code Here

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(galagoIndex + "/test_wt-term-doc-vectors/part-00000")));


    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(galagoTermDocVector1, value);


    reader.next(key, value);


    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }


    verifyTermDocVector(galagoTermDocVector2, value);
    reader.close();

View Full Code Here

    Configuration conf = IntegrationUtils.getBespinConfiguration();
    FileSystem fs = FileSystem.get(conf);


    SequenceFile.Reader reader;
    IntWritable key = new IntWritable();
    HMapSFW value = new HMapSFW();


    reader = new SequenceFile.Reader(fs.getConf(),
        SequenceFile.Reader.file(new Path(opennlpIndex + "/test_wt-term-doc-vectors/part-00000")));


    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(opennlpTermDocVector1, value);


    reader.next(key, value);
    System.out.println("*** top 10 terms ***");
    for (MapKF.Entry<String> entry : value.getEntriesSortedByValue(10)) {
      System.out.println(entry.getKey() + ": " + entry.getValue());
    }
    verifyTermDocVector(opennlpTermDocVector2, value);
    reader.close();
  }

View Full Code Here

      sLogger = logger;
    }


    //sLogger.setLevel(Level.DEBUG);


    HMapSFW v = new HMapSFW();
    float normalization=0;
    for(int e : tfTable.keySet()){
      // retrieve term string, tf and df
      String eTerm = eVocab.get(e);
      float tf = tfTable.get(e);
      float df = dfTable.get(e);


      // compute score via scoring model
      float score = ((Bm25) scoringModel).computeDocumentWeight(tf, df, docLen);


      sLogger.debug(eTerm+" "+tf+" "+df+" "+score);
      if(score>0){
        v.put(eTerm, score);
        if(isNormalize){
          normalization+=Math.pow(score, 2);
        }    
      }
    }


    // length-normalize doc vector
    if(isNormalize){
      normalization = (float) Math.sqrt(normalization);
      for(Entry<String> e : v.entrySet()){
        v.put(e.getKey(), e.getValue()/normalization);
      }
    }
    return v;
  }

View Full Code Here

      sLogger = logger;
    }


    //sLogger.setLevel(Level.DEBUG);


    HMapSFW v = new HMapSFW();
    float normalization=0;
    for(int e : tfTable.keySet()){
      // retrieve term string, tf and df
      String eTerm = eVocab.get(e);
      float tf = tfTable.get(e);
      float df = dfTable.get(eTerm);


      // compute score via scoring model
      float score = ((Bm25) scoringModel).computeDocumentWeight(tf, df, docLen);


      sLogger.debug(eTerm+" "+tf+" "+df+" "+score);
      if(score>0){
        v.put(eTerm, score);
        if(isNormalize){
          normalization+=Math.pow(score, 2);
        }   
      }
    }


    // length-normalize doc vector
    if(isNormalize){
      normalization = (float) Math.sqrt(normalization);
      for(Entry<String> e : v.entrySet()){
        v.put(e.getKey(), e.getValue()/normalization);
      }
    }
    return v;
  }

View Full Code Here

      sLogger = logger;
    }


    //    sLogger.setLevel(Level.DEBUG);


    HMapSFW v = new HMapSFW();
    float normalization=0;
    for(edu.umd.cloud9.util.map.MapIF.Entry entry : tfTable.entrySet()){
      // retrieve term string, tf and df
      String eTerm = eVocab.get(entry.getKey());
      float tf = entry.getValue();
      int eId = dict.getId(eTerm);
      if(eId < 1){    //OOV
        continue;
      }
      int df = dfTable.getDf(eId);
      // compute score via scoring model
      float score = ((Bm25) scoringModel).computeDocumentWeight(tf, df, docLen);
      if(df<1){
        sLogger.warn("Suspicious DF WARNING = "+eTerm+" "+tf+" "+df+" "+score);
      }


      sLogger.debug(eTerm+" "+tf+" "+df+" "+score);


      if(score>0){
        v.put(eTerm, score);
        if(isNormalize){
          normalization+=Math.pow(score, 2);
        }    
      }
    }


    // length-normalize doc vector
    if(isNormalize){
      normalization = (float) Math.sqrt(normalization);
      for(Entry<String> e : v.entrySet()){
        v.put(e.getKey(), e.getValue()/normalization);
      }
    }
    return v;
  }

View Full Code Here

      sLogger = logger;
    }


    //    sLogger.setLevel(Level.DEBUG);


    HMapSFW v = new HMapSFW();
    float normalization=0;
    for(edu.umd.cloud9.util.map.MapKI.Entry<String> entry : tfTable.entrySet()){
      // retrieve term string, tf and df
      String eTerm = entry.getKey();
      float tf = entry.getValue();
      int eId = dict.getId(eTerm);
      if(eId < 1){    //OOV
        continue;
      }
      int df = dfTable.getDf(eId);
      // compute score via scoring model
      float score = ((Bm25) scoringModel).computeDocumentWeight(tf, df, docLen);
      if(df<1){
        sLogger.warn("Suspicious DF WARNING = "+eTerm+" "+tf+" "+df+" "+score);
      }


      sLogger.debug(eTerm+" "+tf+" "+df+" "+score);


      if(score>0){
        v.put(eTerm, score);
        if(isNormalize){
          normalization+=Math.pow(score, 2);
        }   
      }
    }


    // length-normalize doc vector
    if(isNormalize){
      normalization = (float) Math.sqrt(normalization);
      for(Entry<String> e : v.entrySet()){
        v.put(e.getKey(), e.getValue()/normalization);
      }
    }
    return v;
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of edu.umd.cloud9.collection.line.NumberTextDocuments

bak.pcj.IntIterator

edu.umd.cloud9.example.bfs.BfsNodeTest

edu.umd.cloud9.example.pagerank.PageRankNodeTest

edu.umd.cloud9.io.array.ArrayListOfIntsWritable

edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest

edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest

edu.umd.cloud9.io.map.HMapIDW

edu.umd.cloud9.io.map.HMapIDWTest

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.