Package com.digitalpebble.classification

Examples of com.digitalpebble.classification.Document

47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
            boolean create, String vector_location) throws IOException {
        File vectorFile = new File(vector_location);
        PrintWriter out = null;
        out = new PrintWriter(new FileWriter(vectorFile));
        for (int i = 0; i < documents.length; i++) {
            Document doc = documents[i];
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = doc.getFeatureVector(lexicon);
            out.print(label + " " + Utils.getVectorString(vector) + "\n");
        }
        out.close();
        return vectorFile;
    }
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
        out = new PrintWriter(new FileWriter(vectorFile));
        // get an iterator on the Corpus
        // and retrieve the documents one by one
        Iterator<Document> docIterator = corpus.iterator();
        while (docIterator.hasNext()) {
            Document doc = docIterator.next();
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = null;
            if (attributeMapping == null)
                vector = doc.getFeatureVector(lexicon);
            else
                vector = doc.getFeatureVector(lexicon, attributeMapping);
            out.print(label + " " + Utils.getVectorString(vector) + "\n");
        }
        out.close();
        return vectorFile;
    }
View Full Code Here
147
148
149
150
151
152
153
154
155
156
157
        // load classifier
        TextClassifier classifier = TextClassifier
            .getClassifier(new File(resourceDir));
        // create a document from a String
        String[] tokens = Tokenizer.tokenize(text.toString(), true);
        Document doc = classifier.createDocument(tokens);
        // classify
        double[] scores = classifier.classify(doc);
        // get best label
        String label = classifier.getBestLabel(scores);
        System.out.println("Classified as : "+label);
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
        // get an iterator on the Corpus
        // and retrieve the documents one by one
        Iterator<Document> docIterator = corpus.iterator();
        while (docIterator.hasNext()) {
            Document doc = docIterator.next();
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = null;
            if (attributeMapping == null)
                vector = doc.getFeatureVector(lexicon);
            else
                vector = doc.getFeatureVector(lexicon, attributeMapping);

            StringBuffer buffer = new StringBuffer("{");

            buffer.append("0 ").append(lexicon.getLabel(label));
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
        int latestRank = 0;
       
        // fill the matrix
        Iterator<Document> docIter = corpus.iterator();
        while(docIter.hasNext()){
          Document d = docIter.next(); 
          // Vector vector = d.getFeatureVector(lexicon);
          // get a vector based on the number of occurrences i.e on the raw document
          Vector vector = d.getFeatureVector(lexicon,Parameters.WeightingMethod.OCCURRENCES);
          int[] indices = vector.getIndices();
          double[] values = vector.getValues();
          int classNum = d.getLabel();
         
          for (int i=0;i<indices.length;i++){
            int index = indices[i];
            double value = values[i];
            if (value==0) continue;         
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
      int latestRank = 0;
     
      // fill the matrix
      Iterator<Document> docIter = corpus.iterator();
      while(docIter.hasNext()){
        Document d = docIter.next(); 
        Vector vector = d.getFeatureVector(lexicon);
        // get a vector based on the number of occurrences i.e on the raw document
        // Vector vector = d.getFeatureVector(lexicon,Parameters.WeightingMethod.OCCURRENCES);
        int[] indices = vector.getIndices();
        double[] values = vector.getValues();
        int classNum = d.getLabel();
       
        for (int i=0;i<indices.length;i++){
          int index = indices[i];
          double value = values[i];
          if (value==0) continue;         
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
        // load classifier
        TextClassifier classifier = TextClassifier
            .getClassifier(new File(resourceDir));
        // create a document from a String
        String[] tokens = Tokenizer.tokenize(text.toString(), true);
        Document doc = classifier.createDocument(tokens);
        // classify
        double[] scores = classifier.classify(doc);
        // get best label
        String label = classifier.getBestLabel(scores);
        System.out.println("Classified as : " + label);
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
            boolean create, String vector_location) throws IOException {
        File vectorFile = new File(vector_location);
        PrintWriter out = null;
        out = new PrintWriter(new FileWriter(vectorFile));
        for (int i = 0; i < documents.length; i++) {
            Document doc = documents[i];
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = doc.getFeatureVector(lexicon);
            out.print(label + " " + Utils.getVectorString(vector) + "\n");
        }
        out.close();
        return vectorFile;
    }
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
        out = new PrintWriter(new FileWriter(vectorFile));
        // get an iterator on the Corpus
        // and retrieve the documents one by one
        Iterator<Document> docIterator = corpus.iterator();
        while (docIterator.hasNext()) {
            Document doc = docIterator.next();
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = null;
            if (attributeMapping == null)
                vector = doc.getFeatureVector(lexicon);
            else
                vector = doc.getFeatureVector(lexicon, attributeMapping);
            out.print(label + " " + Utils.getVectorString(vector) + "\n");
        }
        out.close();
        return vectorFile;
    }
View Full Code Here
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
        // get an iterator on the Corpus
        // and retrieve the documents one by one
        Iterator<Document> docIterator = corpus.iterator();
        while (docIterator.hasNext()) {
            Document doc = docIterator.next();
            int label = doc.getLabel();
            // get a vector from the document
            // need a metric (e.g. relative frequency / binary)
            // and a lexicon
            // the vector is represented as a string directly
            Vector vector = null;
            if (attributeMapping == null)
                vector = doc.getFeatureVector(lexicon);
            else
                vector = doc.getFeatureVector(lexicon, attributeMapping);

            StringBuffer buffer = new StringBuffer("{");

            buffer.append("0 ").append(lexicon.getLabel(label));
View Full Code Here
TOP

Related Classes of com.digitalpebble.classification.Document

  • com.digitalpebble.classification.libsvm.Utils
  • com.digitalpebble.classification.test.classifyDoc
  • com.digitalpebble.classification.test.TestMultiFieldDocs
  • com.digitalpebble.classification.test.TestTrainingCorpus
  • com.digitalpebble.classification.test.TestWeightingSchemes
  • com.digitalpebble.classification.util.ModelUtils
  • com.digitalpebble.classification.util.scorers.chiSquareAttributeScorer
  • com.digitalpebble.classification.util.scorers.logLikelihoodAttributeScorer
    • 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.