Package edu.harvard.wcfia.yoshikoder.reporting

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

149
150
151
152
153
154
155
   
    /**
     * Compute or recompute off our tokens
     */
    protected void computeWordFrequencyMap(){
      map = new WordFrequencyMap(this);
    }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
      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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
      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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
      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
31
32
33
34
35
36
37
38
39
40
41
                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

Related Classes of edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap

  • edu.harvard.wcfia.yoshikoder.document.tokenizer.Token
  • edu.harvard.wcfia.yoshikoder.document.tokenizer.TokenListImpl
  • edu.harvard.wcfia.yoshikoder.SingleDocumentWordFrequencyReportAction
  • edu.harvard.wcfia.yoshikoder.UnifiedWordFrequencyReportAction
  • java.util.regex.Matcher
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.