Package org.apache.mahout.classifier

Examples of org.apache.mahout.classifier.ResultAnalyzer

124
125
126
127
128
129
130
131
132
133
134
135
    Collection<String> categories
      = new ArrayList<String>(catCount);
    for (int i=0; i < catCount; i++) {
      categories.add(categorizer.getCategory(i));
    }
    ResultAnalyzer resultAnalyzer = //<co id="tmx.results"/>
        new ResultAnalyzer(categories, "unknown");
    runTest(inputFiles, categorizer, tokenizer, resultAnalyzer); //<co id="tmx.run"/>
    /*<calloutlist>
    <callout arearefs="tmx.feature">Setup Feature Generators</callout>
    <callout arearefs="tmx.modelreader">Load Model</callout>
    <callout arearefs="tmx.categorizer">Create Categorizer</callout>
View Full Code Here
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
      String line = null;
      //<start id="lucene.examples.mlt.test"/>
      final ClassifierResult UNKNOWN = new ClassifierResult("unknown",
              1.0);
     
      ResultAnalyzer resultAnalyzer = //<co id="co.mlt.ra"/>
        new ResultAnalyzer(categorizer.getCategories(),
            UNKNOWN.getLabel());

      for (File ff: inputFiles) { //<co id="co.mlt.read"/>
        BufferedReader in =
            new BufferedReader(
                new InputStreamReader(
                    new FileInputStream(ff),
                    "UTF-8"));
        while ((line = in.readLine()) != null) {
          String[] parts = line.split("\t");
          if (parts.length != 2) {
            continue;
          }
         
          CategoryHits[] hits //<co id="co.mlt.cat"/>
            = categorizer.categorize(new StringReader(parts[1]));
          ClassifierResult result = hits.length > 0 ? hits[0] : UNKNOWN;
          resultAnalyzer.addInstance(parts[0], result); //<co id="co.mlt.an"/>
        }
       
        in.close();
      }

      System.out.println(resultAnalyzer.toString());//<co id="co.mlt.print"/>
      /*
      <calloutlist>
        <callout arearefs="co.mlt.ra">Create <classname>ResultAnalyzer</classname></callout>
        <callout arearefs="co.mlt.read">Read Test data</callout>
        <callout arearefs="co.mlt.cat">Categorize</callout>
View Full Code Here
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
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
    } 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"));
    TimingStatistics totalStatistics = new TimingStatistics();
    if (subdirs != null) {
     
      for (File file : subdirs) {
        if (verbose) {
          log.info("--------------");
          log.info("Testing: {}", file);
        }
        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()) {
            String correctLabel = stringListEntry.getKey();
            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, classifiedLabel);
            if (verbose) {
              // We have one document per line
              log.info("Line Number: {} Line(30): {} Expected Label: {} Classified Label: {} Correct: {}",
                new Object[] {lineNum, line.length() > 30 ? line.substring(0, 30) : line, correctLabel,
                              classifiedLabel.getLabel(), correct,});
            }
            // log.info("{} {}", correctLabel, classifiedLabel);
           
          }
          lineNum++;
        }
        /*
         * log.info("{}\t{}\t{}/{}", new Object[] {correctLabel,
         * resultAnalyzer.getConfusionMatrix().getAccuracy(correctLabel),
         * resultAnalyzer.getConfusionMatrix().getCorrect(correctLabel),
         * resultAnalyzer.getConfusionMatrix().getTotal(correctLabel)});
         */
        log.info("Classified instances from {}", file.getName());
        if (verbose) {
          log.info("Performance stats {}", operationStats.toString());
        }
      }
     
    }
    if (verbose) {
      log.info("{}", totalStatistics.toString());
    }
    log.info(resultAnalyzer.summarize());
  }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
   
    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], Integer.parseInt(params.get("gramSize")))
          .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();
    for (int i = 0; i < 3; i++) {
      for (int j = 0; j < 3; j++) {
        if (i == j)
          assertEquals(4, matrix[i][j]);
        else
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
   
    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], Integer.parseInt(params.get("gramSize")))
          .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();
    for (int i = 0; i < 3; i++) {
      for (int j = 0; j < 3; j++) {
        if (i == j)
          assertEquals(4, matrix[i][j]);
        else
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
    SequenceFileDirIterable<Text, VectorWritable> dirIterable =
        new SequenceFileDirIterable<Text, VectorWritable>(getOutputPath(),
                                                          PathType.LIST,
                                                          PathFilters.partFilter(),
                                                          getConf());
    ResultAnalyzer analyzer = new ResultAnalyzer(labelMap.values(), "DEFAULT");
    analyzeResults(labelMap, dirIterable, analyzer);

    log.info("{} Results: {}", complementary ? "Complementary" : "Standard NB", analyzer);
    return 0;
  }
View Full Code Here
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
    } 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"));
    TimingStatistics totalStatistics = new TimingStatistics();
    if (subdirs != null) {
     
      for (File file : subdirs) {
        if (verbose) {
          log.info("--------------");
          log.info("Testing: {}", file);
        }
        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()) {
            String correctLabel = stringListEntry.getKey();
            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, classifiedLabel);
            if (verbose) {
              // We have one document per line
              log.info("Line Number: {} Line(30): {} Expected Label: {} Classified Label: {} Correct: {}",
                new Object[] {lineNum, line.length() > 30 ? line.substring(0, 30) : line, correctLabel,
                              classifiedLabel.getLabel(), correct,});
            }
            // log.info("{} {}", correctLabel, classifiedLabel);
           
          }
          lineNum++;
        }
        ConfusionMatrix matrix = resultAnalyzer.getConfusionMatrix();
        log.info("{}", matrix);
        BayesClassifierDriver.confusionMatrixSeqFileExport(params, matrix);

        log.info("ConfusionMatrix: {}", matrix.toString());
          
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
   
    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();
    for (int i = 0; i < 3; i++) {
      for (int j = 0; j < 3; j++) {
        assertEquals(i == j ? 4 : 0, matrix[i][j]);
      }
    }
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
   
    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();
    for (int i = 0; i < 3; i++) {
      for (int j = 0; j < 3; j++) {
        assertEquals(i == j ? 4 : 0, matrix[i][j]);
      }
    }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
        newsGroups.intern(newsgroup.getName());
        files.addAll(Arrays.asList(newsgroup.listFiles()));
      }
    }
    System.out.printf("%d test files\n", files.size());
    ResultAnalyzer ra = new ResultAnalyzer(newsGroups.values(), "DEFAULT");
    for (File file : files) {
      String ng = file.getParentFile().getName();

      int actual = newsGroups.intern(ng);
      NewsgroupHelper helper = new NewsgroupHelper();
      Vector input = helper.encodeFeatureVector(file, actual, 0, overallCounts);//no leak type ensures this is a normal vector
      Vector result = classifier.classifyFull(input);
      int cat = result.maxValueIndex();
      double score = result.maxValue();
      double ll = classifier.logLikelihood(actual, input);
      ClassifierResult cr = new ClassifierResult(newsGroups.values().get(cat), score, ll);
      ra.addInstance(newsGroups.values().get(actual), cr);

    }
    output.printf("%s\n\n", ra.toString());
  }
View Full Code Here
TOP

Related Classes of org.apache.mahout.classifier.ResultAnalyzer

  • com.tamingtext.classifier.maxent.TestMaxent
  • com.tamingtext.classifier.mlt.TestMoreLikeThis
  • org.apache.mahout.cf.taste.impl.common.RunningAverageAndStdDev
  • org.apache.mahout.classifier.bayes.BayesClassifierSelfTest
  • org.apache.mahout.classifier.bayes.TestClassifier
  • org.apache.mahout.classifier.df.mapreduce.TestForest
  • org.apache.mahout.classifier.naivebayes.test.TestNaiveBayesDriver
  • org.apache.mahout.classifier.sgd.TestASFEmail
  • org.apache.mahout.classifier.sgd.TestNewsGroups
  • org.apache.mahout.df.mapreduce.Classifier
    • 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.