Examples of AbstractVectorClassifier

org.apache.mahout.classifier.AbstractVectorClassifier
Defines the interface for classifiers that take input as a vector. This is implemented as an abstract class so that it can implement a number of handy convenience methods related to classification of vectors.

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    CsvRecordFactory csv = lmp.getCsvRecordFactory();
    assertEquals("[1, 2]", Sets.newTreeSet(csv.getTargetCategories()).toString());
    assertEquals("[Intercept Term, x, y]", Sets.newTreeSet(csv.getPredictors()).toString());




    AbstractVectorClassifier model = TrainLogistic.getModel();
    ModelDissector md = new ModelDissector();
    List<String> data = Resources.readLines(Resources.getResource(inputFile), Charsets.UTF_8);
    for (String line : data.subList(1, data.size())) {
      Vector v = new DenseVector(lmp.getNumFeatures());
      csv.getTraceDictionary().clear();

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    CsvRecordFactory csv = lmp.getCsvRecordFactory();
    assertEquals("[1, 2]", Sets.newTreeSet(csv.getTargetCategories()).toString());
    assertEquals("[Intercept Term, x, y]", Sets.newTreeSet(csv.getPredictors()).toString());


    // verify model by building dissector
    AbstractVectorClassifier model = TrainLogistic.getModel();
    List<String> data = Resources.readLines(Resources.getResource("donut.csv"), Charsets.UTF_8);
    Map<String, Double> expectedValues = ImmutableMap.of("x", -0.7, "y", -0.43, "Intercept Term", -0.15);
    verifyModel(lmp, csv, data, model, expectedValues);


    // test saved model

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    trainNaiveBayes.run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(),
        "-el", "--tempDir", tempDir.getAbsolutePath() });


    NaiveBayesModel naiveBayesModel = NaiveBayesModel.materialize(new Path(outputDir.getAbsolutePath()), conf);


    AbstractVectorClassifier classifier = new StandardNaiveBayesClassifier(naiveBayesModel);


    assertEquals(2, classifier.numCategories());


    Vector prediction = classifier.classifyFull(trainingInstance(COLOR_RED, TYPE_SUV, ORIGIN_DOMESTIC).get());


    // should be classified as not stolen
    assertTrue(prediction.get(0) < prediction.get(1));
  }

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

        "-el", "--trainComplementary",
        "--tempDir", tempDir.getAbsolutePath() });


    NaiveBayesModel naiveBayesModel = NaiveBayesModel.materialize(new Path(outputDir.getAbsolutePath()), conf);


    AbstractVectorClassifier classifier = new ComplementaryNaiveBayesClassifier(naiveBayesModel);


    assertEquals(2, classifier.numCategories());


    Vector prediction = classifier.classifyFull(trainingInstance(COLOR_RED, TYPE_SUV, ORIGIN_DOMESTIC).get());


    // should be classified as not stolen
    assertTrue(prediction.get(0) < prediction.get(1));
  }

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    CsvRecordFactory csv = lmp.getCsvRecordFactory();
    assertEquals("[1, 2]", Sets.newTreeSet(csv.getTargetCategories()).toString());
    assertEquals("[Intercept Term, x, y]", Sets.newTreeSet(csv.getPredictors()).toString());


    // verify model by building dissector
    AbstractVectorClassifier model = TrainLogistic.getModel();
    List<String> data = Resources.readLines(Resources.getResource("donut.csv"), Charsets.UTF_8);
    Map<String, Double> expectedValues = ImmutableMap.of("x", -0.7, "y", -0.43, "Intercept Term", -0.15);
    verifyModel(lmp, csv, data, model, expectedValues);


    // test saved model

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    trainNaiveBayes.run(new String[] { "--input", inputFile.getAbsolutePath(), "--output", outputDir.getAbsolutePath(),
        "-el", "--tempDir", tempDir.getAbsolutePath() });


    NaiveBayesModel naiveBayesModel = NaiveBayesModel.materialize(new Path(outputDir.getAbsolutePath()), conf);


    AbstractVectorClassifier classifier = new StandardNaiveBayesClassifier(naiveBayesModel);


    assertEquals(2, classifier.numCategories());


    Vector prediction = classifier.classifyFull(trainingInstance(COLOR_RED, TYPE_SUV, ORIGIN_DOMESTIC).get());


    // should be classified as not stolen
    assertTrue(prediction.get(0) < prediction.get(1));
  }

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

        "-el", "--trainComplementary",
        "--tempDir", tempDir.getAbsolutePath() });


    NaiveBayesModel naiveBayesModel = NaiveBayesModel.materialize(new Path(outputDir.getAbsolutePath()), conf);


    AbstractVectorClassifier classifier = new ComplementaryNaiveBayesClassifier(naiveBayesModel);


    assertEquals(2, classifier.numCategories());


    Vector prediction = classifier.classifyFull(trainingInstance(COLOR_RED, TYPE_SUV, ORIGIN_DOMESTIC).get());


    // should be classified as not stolen
    assertTrue(prediction.get(0) < prediction.get(1));
  }

View Full Code Here

Examples of org.apache.mahout.classifier.AbstractVectorClassifier

    CsvRecordFactory csv = lmp.getCsvRecordFactory();
    assertEquals("[1, 2]", Sets.newTreeSet(csv.getTargetCategories()).toString());
    assertEquals("[Intercept Term, x, y]", Sets.newTreeSet(csv.getPredictors()).toString());


    // verify model by building dissector
    AbstractVectorClassifier model = TrainLogistic.getModel();
    List<String> data = Resources.readLines(Resources.getResource("donut.csv"), Charsets.UTF_8);
    Map<String, Double> expectedValues = ImmutableMap.of("x", -0.7, "y", -0.43, "Intercept Term", -0.15);
    verifyModel(lmp, csv, data, model, expectedValues);


    // test saved model

View Full Code Here

0 1

TOP

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.