Package org.apache.mahout.classifier.bayes.model

Examples of org.apache.mahout.classifier.bayes.model.ClassifierContext

103
104
105
106
107
108
109
110
111
112
113
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());
  }

  public void testResults() throws Exception {
    ClassifierContext classifier = new ClassifierContext(algorithm, store);
    String[] document = { "aa", "ff" };
    ClassifierResult result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    System.out.println("Result: " + result);
  }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
    store.loadFeatureWeight("dd", "e", 50);
    store.updateVocabCount();
  }

  public void test() throws InvalidDatastoreException {
    ClassifierContext classifier = new ClassifierContext(algorithm, store);
    String[] document = {"aa", "ff"};
    ClassifierResult result = classifier.classifyDocument( document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to e", "e", result.getLabel());

    document = new String[]{"ff"};
    result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());

    document = new String[]{"cc"};
    result = classifier.classifyDocument( document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());
  }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());
  }

  public void testResults() throws Exception {
    ClassifierContext classifier = new ClassifierContext(algorithm, store);
    String[] document = {"aa", "ff"};
    ClassifierResult result = classifier.classifyDocument( document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    System.out.println("Result: " + result);
  }
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
    } else {
      throw new IllegalArgumentException("Unrecognized dataSource type: "
          + params.get("dataSource"));
    }
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    ResultAnalyzer resultAnalyzer = new ResultAnalyzer(classifier.getLabels(),
        params.get("defaultCat"));
    final TimingStatistics totalStatistics = new TimingStatistics();
    if (subdirs != null) {

      for (File file : subdirs) {
        log.info("--------------");
        log.info("Testing: " + file);
        String correctLabel = file.getName().split(".txt")[0];
        final TimingStatistics operationStats = new TimingStatistics();

        long lineNum = 0;
        for (String line : new FileLineIterable(new File(file.getPath()),
            Charset.forName(params.get("encoding")), false)) {

          Map<String, List<String>> document = new NGrams(line, Integer
              .parseInt(params.get("gramSize"))).generateNGrams();
          for (Map.Entry<String, List<String>> stringListEntry : document
              .entrySet()) {
            List<String> strings = stringListEntry.getValue();
            TimingStatistics.Call call = operationStats.newCall();
            TimingStatistics.Call outercall = totalStatistics.newCall();
            ClassifierResult classifiedLabel = classifier.classifyDocument(
                strings.toArray(new String[strings.size()]), params
                    .get("defaultCat"));
            call.end();
            outercall.end();
            boolean correct = resultAnalyzer.addInstance(correctLabel,
View Full Code Here
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
213
214
215
216
217
218
219
220
221
    } else {
      throw new IllegalArgumentException("Unrecognized dataSource type: "
          + dataSource);
    }
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    String defaultCat = "unknown";
    if (cmdLine.hasOption(defaultCatOpt)) {
      defaultCat = (String) cmdLine.getValue(defaultCatOpt);
    }
    File docPath = new File((String) cmdLine.getValue(classifyOpt));
    String encoding = "UTF-8";
    if (cmdLine.hasOption(encodingOpt)) {
      encoding = (String) cmdLine.getValue(encodingOpt);
    }
    Analyzer analyzer = null;
    if (cmdLine.hasOption(analyzerOpt)) {
      String className = (String) cmdLine.getValue(analyzerOpt);
      analyzer = Class.forName(className).asSubclass(Analyzer.class)
          .newInstance();
    }
    if (analyzer == null) {
      analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
    }

    log.info("Converting input document to proper format");
    String[] document = BayesFileFormatter.readerToDocument(analyzer,
        new InputStreamReader(new FileInputStream(docPath), Charset
            .forName(encoding)));
    StringBuilder line = new StringBuilder();
    for (String token : document) {
      line.append(token).append(' ');
    }

    List<String> doc = new NGrams(line.toString(), gramSize)
        .generateNGramsWithoutLabel();

    log.info("Done converting");
    log.info("Classifying document: {}", docPath);
    ClassifierResult category = classifier.classifyDocument(doc
        .toArray(new String[doc.size()]), defaultCat);
    log.info("Category for {} is {}", docPath, category);

  }
View Full Code Here
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
      }
     
    } else {
      throw new IllegalArgumentException("Unrecognized dataSource type: " + dataSource);
    }
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    String defaultCat = "unknown";
    if (cmdLine.hasOption(defaultCatOpt)) {
      defaultCat = (String) cmdLine.getValue(defaultCatOpt);
    }
    File docPath = new File((String) cmdLine.getValue(classifyOpt));
    String encoding = "UTF-8";
    if (cmdLine.hasOption(encodingOpt)) {
      encoding = (String) cmdLine.getValue(encodingOpt);
    }
    Analyzer analyzer = null;
    if (cmdLine.hasOption(analyzerOpt)) {
      String className = (String) cmdLine.getValue(analyzerOpt);
      analyzer = Class.forName(className).asSubclass(Analyzer.class).newInstance();
    }
    if (analyzer == null) {
      analyzer = new StandardAnalyzer(Version.LUCENE_30);
    }
   
    log.info("Converting input document to proper format");

    String[] document =
        BayesFileFormatter.readerToDocument(analyzer,Files.newReader(docPath, Charset.forName(encoding)));
    StringBuilder line = new StringBuilder();
    for (String token : document) {
      line.append(token).append(' ');
    }
   
    List<String> doc = new NGrams(line.toString(), gramSize).generateNGramsWithoutLabel();
   
    log.info("Done converting");
    log.info("Classifying document: {}", docPath);
    ClassifierResult category = classifier.classifyDocument(doc.toArray(new String[doc.size()]), defaultCat);
    log.info("Category for {} is {}", docPath, category);
   
  }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
   
  }

  @Test
  public void test() throws Exception {
    ClassifierContext classifier = new ClassifierContext(algorithm, store);
    String[] document = {"aa", "ff"};
    ClassifierResult result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to e", "e", result.getLabel());
   
    document = new String[] {"dd"};
    result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());
   
    document = new String[] {"cc"};
    result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
    assertEquals(result + " is not equal to d", "d", result.getLabel());
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
    assertEquals(result + " is not equal to d", "d", result.getLabel());
  }

  @Test
  public void testResults() throws Exception {
    ClassifierContext classifier = new ClassifierContext(algorithm, store);
    String[] document = {"aa", "ff"};
    ClassifierResult result = classifier.classifyDocument(document, "unknown");
    assertNotNull("category is null and it shouldn't be", result);
  }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
    params.set("encoding", "UTF-8");
    params.set("alpha_i", "1.0");
   
    Algorithm algorithm = new BayesAlgorithm();
    Datastore datastore = new InMemoryBayesDatastore(params);
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    ResultAnalyzer resultAnalyzer = new ResultAnalyzer(classifier.getLabels(), params.get("defaultCat"));
   
    for (String[] entry : ClassifierData.DATA) {
      List<String> document = new NGrams(entry[1], params.getGramSize()).generateNGramsWithoutLabel();
      assertEquals(3, classifier.classifyDocument(document.toArray(new String[document.size()]),
        params.get("defaultCat"), 100).length);
      ClassifierResult result = classifier.classifyDocument(document.toArray(new String[document.size()]), params
          .get("defaultCat"));
      assertEquals(entry[0], result.getLabel());
      resultAnalyzer.addInstance(entry[0], result);
    }
    int[][] matrix = resultAnalyzer.getConfusionMatrix().getConfusionMatrix();
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
    params.set("encoding", "UTF-8");
    params.set("alpha_i", "1.0");
   
    Algorithm algorithm = new CBayesAlgorithm();
    Datastore datastore = new InMemoryBayesDatastore(params);
    ClassifierContext classifier = new ClassifierContext(algorithm, datastore);
    classifier.initialize();
    ResultAnalyzer resultAnalyzer = new ResultAnalyzer(classifier.getLabels(), params.get("defaultCat"));
    for (String[] entry : ClassifierData.DATA) {
      List<String> document = new NGrams(entry[1], params.getGramSize()).generateNGramsWithoutLabel();
      assertEquals(3, classifier.classifyDocument(document.toArray(new String[document.size()]),
        params.get("defaultCat"), 100).length);
      ClassifierResult result = classifier.classifyDocument(document.toArray(new String[document.size()]), params
          .get("defaultCat"));
      assertEquals(entry[0], result.getLabel());
      resultAnalyzer.addInstance(entry[0], result);
    }
    int[][] matrix = resultAnalyzer.getConfusionMatrix().getConfusionMatrix();
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.bayes.model.ClassifierContext

  • org.apache.mahout.classifier.bayes.BayesClassifierSelfTest
  • org.apache.mahout.classifier.bayes.BayesClassifierTest
  • org.apache.mahout.classifier.bayes.CBayesClassifierTest
  • org.apache.mahout.classifier.bayes.mapreduce.bayes.BayesClassifierMapper
  • org.apache.mahout.classifier.bayes.TestClassifier
  • org.apache.mahout.classifier.Classify
    • 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.