Package com.jgaap.util

Examples of com.jgaap.util.Document

83
84
85
86
87
88
89
90
91
92
  }
 
  public static List<Document> getDocumentsFromCSV(List<List<String>> documentCSV) throws Exception{
    List<Document> documents = new ArrayList<Document>();
    for(List<String> documentRow : documentCSV){
      Document document = new Document(documentRow.get(1),documentRow.get(0),(documentRow.size()>2?documentRow.get(2):null));
      documents.add(document);
    }
    return documents;
  }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
    known2.addEvent(new Event("a", null));
    known2.addEvent(new Event("peck", null));
    //known2.setAuthor("Peter");
   
    List<Document> knowns = new ArrayList<Document>();
    Document knownDocument1 = new Document();
    knownDocument1.setAuthor("Mary");
    knownDocument1.addEventSet(null, known1);
    knowns.add(knownDocument1);
    Document knownDocument2 = new Document();
    knownDocument2.setAuthor("Peter");
    knownDocument2.addEventSet(null, known2);
    knowns.add(knownDocument2);

    //Create unknown text
    EventSet unknown1 = new EventSet();

    unknown1.addEvent(new Event("mary", null));
    unknown1.addEvent(new Event("had", null));
    unknown1.addEvent(new Event("a", null));
    unknown1.addEvent(new Event("little", null));
    unknown1.addEvent(new Event("beta", null));

    Document unknownDocument = new Document();
    unknownDocument.addEventSet(null, unknown1);

    //Classify unknown based on the knowns
    WEKAMultilayerPerceptron tree = new WEKAMultilayerPerceptron();
    List<List<Pair<String, Double>>> t = new ArrayList<List<Pair<String,Double>>>();
    tree.train(knowns);
    t.add(tree.analyze(unknownDocument));
    System.out.println(t.toString());

    //Assert that the authors match
    assertTrue(t.get(0).get(0).getFirst().equals("Mary"));
   
   
    //Test 2 - Add in third known author

    EventSet known5 = new EventSet();
   
    known5.addEvent(new Event("she", null));
    known5.addEvent(new Event("sells", null));
    known5.addEvent(new Event("seashells", null));
    known5.addEvent(new Event("by", null));
    known5.addEvent(new Event("seashore", null));
    //known5.setAuthor("Susie");

    Document knownDocument5 = new Document();
    knownDocument5.setAuthor("Susie");
    knownDocument5.addEventSet(null, known5);
    knowns.add(knownDocument5);
   
    t = new ArrayList<List<Pair<String,Double>>>();
    tree.train(knowns);
    t.add(tree.analyze(unknownDocument));
    System.out.println(t.toString());

    assertTrue(t.get(0).get(0).getFirst().equals("Mary"));
   

    //Test 3 - Add in another unknown

    EventSet unknown2 = new EventSet();

    unknown2.addEvent(new Event("peter", null));
    unknown2.addEvent(new Event("piper", null));
    unknown2.addEvent(new Event("picked", null));
    unknown2.addEvent(new Event("a", null));
    unknown2.addEvent(new Event("shells", null));

    Document unknownDocument2 = new Document();
    unknownDocument2.addEventSet(null, unknown2);

    t = new ArrayList<List<Pair<String,Double>>>();
    tree.train(knowns);
    t.add(tree.analyze(unknownDocument));
    t.add(tree.analyze(unknownDocument2));
    System.out.println(t.toString());

    assertTrue(t.get(0).get(0).getFirst().equals("Mary") && t.get(1).get(0).getFirst().equals("Peter"));
   
    // Test 6 - Test unknown that is almost equally likely to be of two authors
   
    EventSet unknown3 = new EventSet();
   
    unknown3.addEvent(new Event("peter", null));
    unknown3.addEvent(new Event("piper", null));
    unknown3.addEvent(new Event("a", null));
    unknown3.addEvent(new Event("little", null));
    unknown3.addEvent(new Event("lamb", null));
   
    Document unknownDocument3 = new Document();
    unknownDocument3.addEventSet(null, unknown3);
   
    //t = tree.analyze(uesv, esv);
    tree = new WEKAMultilayerPerceptron();
    t = new ArrayList<List<Pair<String,Double>>>();
    tree.train(knowns);
    t.add(tree.analyze(unknownDocument3));
    System.out.println(t.toString());
   
    assertTrue(t.get(0).get(0).getSecond()-.5 < .1 && t.get(0).get(1).getSecond()-.5 < .1);
   
    // Test 5 - Add in more known documents for existing authors
    EventSet known3 = new EventSet();
    EventSet known4 = new EventSet();
    EventSet known6 = new EventSet();
   
    known3.addEvent(new Event("mary", null));
    known3.addEvent(new Event("had", null));
    known3.addEvent(new Event("a", null));
    known3.addEvent(new Event("small", null));
    known3.addEvent(new Event("lamb", null));
    //known3.setAuthor("Mary");

    known4.addEvent(new Event("peter", null));
    known4.addEvent(new Event("piper", null));
    known4.addEvent(new Event("collected", null));
    known4.addEvent(new Event("a", null));
    known4.addEvent(new Event("peck", null));
    //known4.setAuthor("Peter");
   
    known6.addEvent(new Event("susie", null));
    known6.addEvent(new Event("sells", null));
    known6.addEvent(new Event("shells", null));
    known6.addEvent(new Event("by", null));
    known6.addEvent(new Event("seashore", null));
    //known6.setAuthor("Susie");

    Document knownDocument3 = new Document();
    knownDocument3.setAuthor("Mary");
    knownDocument3.addEventSet(null, known3);
    knowns.add(knownDocument3);
    Document knownDocument4 = new Document();
    knownDocument4.setAuthor("Peter");
    knownDocument4.addEventSet(null, known4);
    knowns.add(knownDocument4);
    Document knownDocument6 = new Document();
    knownDocument6.setAuthor("Susie");
    knownDocument6.addEventSet(null, known6);
    knowns.add(knownDocument6);
   
    tree = new WEKAMultilayerPerceptron();
    t = new ArrayList<List<Pair<String,Double>>>();
    tree.train(knowns);
View Full Code Here
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
    unknown.addEvent(new Event("white", null));
    unknown.addEvent(new Event("as", null));
    unknown.addEvent(new Event("snow.", null));

    List<Document> knowns = new ArrayList<Document>();
    Document knownDocument1 = new Document();
    knownDocument1.setAuthor("Mary");
    knownDocument1.addEventSet(null, known1);
    knowns.add(knownDocument1);
    Document knownDocument2 = new Document();
    knownDocument2.setAuthor("Peter");
    knownDocument2.addEventSet(null, known2);
    knowns.add(knownDocument2);
   
    Document unknownDocument = new Document();
    unknownDocument.addEventSet(null, unknown);
   
    AnalysisDriver analysisDriver = new MahalanobisDistance();
    analysisDriver.train(knowns);
    List<Pair<String, Double>> t = analysisDriver.analyze(unknownDocument);
    for(Pair<String, Double> element : t){
View Full Code Here
135
136
137
138
139
140
141
142
   * @return - a reference to the document generated
   * @throws Exception - if there is a problem loading the document from file web or parsing file format
   */
  public Document addDocument(String filepath, String author, String title)
      throws Exception {
    Document document = new Document(filepath, author, title);
    return addDocument(document);
  }
View Full Code Here
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
      }else {
        Iterator<Future<Document>> documentIterator = documentsProcessing.iterator();
        while(documentIterator.hasNext()){
          Future<Document> futureDocument = documentIterator.next();
          if(futureDocument.isDone()){
            Document document = futureDocument.get();
            if(document.hasFailed()){
              throw new Exception("One or more documents could not be read / parsed / canonicized Experiment Failed");
            }
            logger.info("Document: "+document.getTitle()+" has finished processing.");
            documentIterator.remove();
          }
        }
      }
    }
View Full Code Here
TOP

Related Classes of com.jgaap.util.Document

  • com.jgaap.backend.API
  • com.jgaap.backend.Utils
  • com.jgaap.classifiers.LDATest
  • com.jgaap.classifiers.MahalanobisDistanceTest
  • com.jgaap.classifiers.MarkovChainAnalysisTest
  • com.jgaap.classifiers.NearestNeighborDriverTest
  • com.jgaap.classifiers.NullAnalysisTest
  • com.jgaap.classifiers.NullHistAnalysisTest
  • com.jgaap.classifiers.WEKADecisionStumpTest
  • com.jgaap.classifiers.WEKAJ48DecisionTreeTest
    • 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.