Examples of WordFrequencyMap

edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap
A map that keeps a track of word frequencies. It can also be queried with patterns. Does not need a reference to the original TokenList (though see constructor) @author will

Examples of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

    
    /**
     * Compute or recompute off our tokens
     */
    protected void computeWordFrequencyMap(){
      map = new WordFrequencyMap(this);
    }

View Full Code Here

Examples of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
      vocab.addAll(map.getVocabularyList());
    }
    List<String> list = new ArrayList<String>();
    list.addAll(vocab);
    return list;
  }

View Full Code Here

Examples of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
      writer.write( FileUtil.escapeForCsv(doc.getTitle()) );
      for (String vocabWord: vocab) {
        Integer count = map.getWordCount(vocabWord);
        if (count == null)
          writer.write(",0");
        else
          writer.write("," + count.toString());
      }
      writer.write("," + map.getTotal() + "\n");
    }
    // something else should close the file
  }

View Full Code Here

Examples of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

      TokenList tl = tcache.getTokenList(doc);
      if (tl == null){
        tl = TokenizationService.getTokenizationService().tokenize(doc);
        tcache.putTokenList(doc, tl);
      }
      WordFrequencyMap map = new WordFrequencyMap(tl);
      
      row = sheet.createRow((short)rowNumber);
      cell = row.createCell((short)0);
            cell.setEncoding(HSSFCell.ENCODING_UTF_16);
            cell.setCellValue(doc.getTitle());
      
            for (int ii = 0; ii < vocab.size(); ii++) {
            cell = row.createCell((short)(ii+1));
              Integer count = map.getWordCount(vocab.get(ii));
        if (count == null)
          cell.setCellValue((double)0);
        else
          cell.setCellValue((double)count.doubleValue());
      }  
      cell = row.createCell((short)(vocab.size()+1));
      cell.setCellValue((double)map.getTotal());
      
      rowNumber++;
    }
    wb.write(stream);
    // something else should close the file

View Full Code Here

Examples of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

                if (tl == null){
                    tl = TokenizationService.getTokenizationService().tokenize(doc);
                    tcache.putTokenList(doc, tl);
                }
                
                WordFrequencyMap map = new WordFrequencyMap(tl);
                DocumentFrequencyReport report = 
                    new DocumentFrequencyReport("Word Frequency Report", 
                            "Frequencies of each word in " + doc.getTitle(), 
                            yoshikoder.getDictionary().getName(),
                            doc, map);

View Full Code Here

TOP

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.