Examples of EntryFrequencyMap

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

89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
      sb.append(" ");
    }
    // tokenize and apply dictionary to the 'document'
    YKDocument doc = new YKDocumentImpl(docTitle, sb.toString());
    TokenList tl = TokenizationService.getTokenizationService().tokenize(doc);
    EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl);

    int[] counts = new int[keys.length+1];
    for (int ii=0; ii<keys.length; ii++) {
      Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
      counts[ii] = cnt.intValue();
    }
    // add N
    counts[keys.length] = efm1.getTokenTotal();

    return counts;
  }
View Full Code Here

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

123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
        TokenList tl1 = tcache.getTokenList(doc1);
        if (tl1 == null)
          tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
       
        // for _all_ categories
        EntryFrequencyMap efm1 = new EntryFrequencyMap(dict.getDictionaryRoot(), tl1);
        List lkeys = efm1.getSortedCategoryEntries();
        Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
        int[] counts = new int[keys.length+1];
        for (int ii=0; ii<keys.length; ii++) {
          Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
          counts[ii] = cnt.intValue();
        }
        // add N
        counts[keys.length] = efm1.getTokenTotal();

        HSSFWorkbook wb = new HSSFWorkbook();
        HSSFRow row;
        HSSFCell cell;

        HSSFSheet sheet = wb.createSheet("Category frequencies");

        // header
        row = sheet.createRow((short)0);
        for (int c=0; c<keys.length; c++){
          cell = row.createCell((short)(c+1));
          cell.setEncoding(HSSFCell.ENCODING_UTF_16);
          String nodepath = efm1.getEntryPath(keys[c]);
          cell.setCellValue(nodepath);
        }
        cell = row.createCell((short)(keys.length+1));
        cell.setEncoding(HSSFCell.ENCODING_UTF_16);
        cell.setCellValue("Total");
View Full Code Here

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

236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
        TokenList tl1 = tcache.getTokenList(doc1);
        if (tl1 == null)
          tl1 = TokenizationService.getTokenizationService().tokenize(doc1);

        // compute the dictionary counts
        EntryFrequencyMap efm1 = new EntryFrequencyMap(dict.getDictionaryRoot(), tl1);
        List lkeys = efm1.getSortedCategoryEntries();
        Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
        int[] counts = new int[keys.length+1];
        for (int ii=0; ii<keys.length; ii++) {
          Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
          counts[ii] = cnt.intValue();
        }
        // add N
        counts[keys.length] = efm1.getTokenTotal();

        for (int ii = 0; ii < keys.length; ii++) {
          String nodepath = efm1.getEntryPath(keys[ii]);

          writer.write(",");
          writer.write(FileUtil.escapeForCsv(nodepath));
        }
        writer.write(",Total\n");
View Full Code Here

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

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
        TokenList tl1 = tcache.getTokenList(doc);
        if (tl1 == null)
            tl1 = TokenizationService.getTokenizationService().tokenize(doc);
       
        // compute the dictionary counts
        EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
   
        int[] counts = new int[keys.length+1];
    for (int ii=0; ii<keys.length; ii++) {
      Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
      counts[ii] = cnt.intValue();
    }
    // add N
    counts[keys.length] = efm1.getTokenTotal();
   
    return counts;
  }
View Full Code Here

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

114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
                if (tl1 == null)
                  tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
                 YKDictionary dict = yoshikoder.getDictionary();
               
                 // compute the dictionary counts
                EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
                List lkeys = efm1.getSortedCategoryEntries();
                Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
                int[] counts = new int[keys.length+1];
            for (int ii=0; ii<keys.length; ii++) {
              Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
              counts[ii] = cnt.intValue();
            }
            // add N
            counts[keys.length] = efm1.getTokenTotal();
             
            HSSFWorkbook wb = new HSSFWorkbook();
                HSSFRow row;
                HSSFCell cell;
               
                HSSFSheet sheet = wb.createSheet("Category frequencies");
               
                // header
                row = sheet.createRow((short)0);
                for (int c=0; c<keys.length; c++){
                  cell = row.createCell((short)(c+1));
                    cell.setEncoding(HSSFCell.ENCODING_UTF_16);
                    String nodepath = efm1.getEntryPath(keys[c]);
                    cell.setCellValue(nodepath);
                }
                cell = row.createCell((short)(keys.length+1));
                cell.setEncoding(HSSFCell.ENCODING_UTF_16);
                cell.setCellValue("Total");
View Full Code Here

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

220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
                if (tl1 == null)
                  tl1 = TokenizationService.getTokenizationService().tokenize(doc1);
                 YKDictionary dict = yoshikoder.getDictionary();
               
                 // compute the dictionary counts
                EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
                List lkeys = efm1.getSortedCategoryEntries();
                Node[] keys = (Node[])lkeys.toArray(new Node[lkeys.size()]);
                int[] counts = new int[keys.length+1];
            for (int ii=0; ii<keys.length; ii++) {
              Integer cnt = (Integer) efm1.getEntryCount(keys[ii]);
              counts[ii] = cnt.intValue();
            }
            // add N
            counts[keys.length] = efm1.getTokenTotal();
             
            for (int ii = 0; ii < keys.length; ii++) {
          String nodepath = efm1.getEntryPath(keys[ii]);
         
          writer.write(",");
          writer.write(FileUtil.escapeForCsv(nodepath));
              }
            writer.write(",Total\n");
View Full Code Here

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

45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
        TaskWorker tworker = new TaskWorker(yoshikoder){
            YKDictionaryReportDialog dia;
          Map<YKDocument,EntryFrequencyMap> efmMap;
           
          protected void doWork() throws Exception {
            EntryFrequencyMap efm = null;
            for (YKDocument doc : concmap.keySet()) {
              TokenList tlist = new TokenListImpl();
              Concordance conc = concmap.get(doc);
              for (Iterator iter = conc.iterator(); iter.hasNext();) {
                ConcordanceLine line = (ConcordanceLine) iter.next();
                for (Iterator iterator = line.getLeftHandSide().iterator(); iterator.hasNext();) {
                  Token token = (Token) iterator.next();
                  tlist.add(token);
                }
                for (Iterator iterator = line.getRightHandSide().iterator(); iterator.hasNext();) {
                  Token token = (Token) iterator.next();
                  tlist.add(token);
                }
              }
              efm = new EntryFrequencyMap(yoshikoder.getDictionary(), tlist);
              efmMap.put(doc, efm);
            }
           
            // FIXME use efmMap in the report, not the most recent one!
           
View Full Code Here

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

66
67
68
69
70
71
72
73
74
75
76
77
                        tl2 = TokenizationService.getTokenizationService().tokenize(doc2);
                        tcache.putTokenList(doc2, tl2);
                    }
                   
                    //YKDictionary dict = yoshikoder.getDictionary();
                    EntryFrequencyMap efm1 = new EntryFrequencyMap(catnode, tl1);
                    EntryFrequencyMap efm2 = new EntryFrequencyMap(catnode, tl2);
                   
                    String key = doc1.getTitle() +
                        " vs. " + doc2.getTitle();
                    DictionaryRRDocumentComparisonReport report =
                        new DictionaryRRDocumentComparisonReport(key,
View Full Code Here

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

47
48
49
50
51
52
53
54
55
56
57
                if (tl == null){
                    tl = TokenizationService.getTokenizationService().tokenize(doc);
                    tcache.putTokenList(doc, tl);
                }
               
                EntryFrequencyMap efm = new EntryFrequencyMap(catnode, tl);
               
                DictionaryFrequencyReport catsAndPats =
                    new DictionaryFrequencyReport("Dictionary Entry Frequencies",
                            "Frequencies of each dictionary entry in " + doc.getTitle(),
                            yoshikoder.getDictionary().getName(),
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.