Java Classifier.getInstancePipe方法代码示例

import cc.mallet.classify.Classifier; //导入方法依赖的package包/类
public ConfidencePredictingClassifier (Classifier underlyingClassifier, Classifier confidencePredictingClassifier)
{
	super (underlyingClassifier.getInstancePipe());
	this.underlyingClassifier = underlyingClassifier;
	this.confidencePredictingClassifier = confidencePredictingClassifier;
	// for testing confidence accuracy
	totalCorrect = 0.0;
	totalIncorrect = 0.0;
	totalIncorrectIncorrect = 0.0;
	totalIncorrectCorrect = 0.0;
	numCorrectInstances = 0;
	numIncorrectInstances = 0;
	numConfidenceCorrect = 0;
	numFalsePositive = 0;
	 numFalseNegative = 0;

}
 

import cc.mallet.classify.Classifier; //导入方法依赖的package包/类
@Override
public void initialize(UimaContext context)
        throws ResourceInitializationException {
    super.initialize(context);
    try {
        // load model for inference
        File modelfile = new File(ReferencesHelper.REFERENCES_RESOURCES
                + "models/" + modelName);
        checkArgument(modelfile.exists(), "no modelFile at " + modelName);
        ObjectInputStream s = new ObjectInputStream(new FileInputStream(
                modelfile));
        classifier = (Classifier) s.readObject();
        s.close();
        checkArgument(classifier != null);
        pipes = classifier.getInstancePipe();
    } catch (Exception e) {
        throw new ResourceInitializationException(e);
    }
}
 

import cc.mallet.classify.Classifier; //导入方法依赖的package包/类
public static void main(String[] args){
	
   	String stopListFilePath = "data/stoplists/en.txt";
   	String dataFolderPath = "data/ex6DataEmails/train";
   	String testFolderPath = "data/ex6DataEmails/test";
   	
	ArrayList<Pipe> pipeList = new ArrayList<Pipe>();
	pipeList.add(new Input2CharSequence("UTF-8"));
	Pattern tokenPattern = Pattern.compile("[\\p{L}\\p{N}_]+");
	pipeList.add(new CharSequence2TokenSequence(tokenPattern));
	pipeList.add(new TokenSequenceLowercase());
	pipeList.add(new TokenSequenceRemoveStopwords(new File(stopListFilePath), "utf-8", false, false, false));
	pipeList.add(new TokenSequence2FeatureSequence());
	pipeList.add(new FeatureSequence2FeatureVector());
	pipeList.add(new Target2Label());
	SerialPipes pipeline = new SerialPipes(pipeList);
	
	FileIterator folderIterator = new FileIterator(
			new File[] {new File(dataFolderPath)},
	         new TxtFilter(),
	         FileIterator.LAST_DIRECTORY);

	
	InstanceList instances = new InstanceList(pipeline);
	
	instances.addThruPipe(folderIterator);
	
	ClassifierTrainer classifierTrainer = new NaiveBayesTrainer();
	Classifier classifier = classifierTrainer.train(instances);

	InstanceList testInstances = new InstanceList(classifier.getInstancePipe());
	folderIterator = new FileIterator(
			new File[] {new File(testFolderPath)},
	         new TxtFilter(),
	         FileIterator.LAST_DIRECTORY);
       testInstances.addThruPipe(folderIterator);
       
       Trial trial = new Trial(classifier, testInstances);
       
       System.out.println("Accuracy: " + trial.getAccuracy());
       System.out.println("F1 for class 'spam': " + trial.getF1("spam"));

       System.out.println("Precision for class '" +
                          classifier.getLabelAlphabet().lookupLabel(1) + "': " +
                          trial.getPrecision(1));

       System.out.println("Recall for class '" +
                          classifier.getLabelAlphabet().lookupLabel(1) + "': " +
                          trial.getRecall(1));

	
	

}
 

import cc.mallet.classify.Classifier; //导入方法依赖的package包/类
public void evaluate(Classifier classifier, File file) throws IOException {

        // Create an InstanceList that will contain the test data.
        // In order to ensure compatibility, process instances
        //  with the pipe used to process the original training
        //  instances.

        InstanceList testInstances = new InstanceList(classifier.getInstancePipe());

        // Create a new iterator that will read raw instance data from
        //  the lines of a file.
        // Lines should be formatted as:
        //
        //   [name] [label] [data ... ]

        CsvIterator reader =
                new CsvIterator(new FileReader(file),
                        "(\\w+)\\s+(\\w+)\\s+(.*)",
                        3, 2, 1);  // (data, label, name) field indices

        // Add all instances loaded by the iterator to
        //  our instance list, passing the raw input data
        //  through the classifier's original input pipe.

        testInstances.addThruPipe(reader);

        Trial trial = new Trial(classifier, testInstances);

        // The Trial class implements many standard evaluation
        //  metrics. See the JavaDoc API for more details.

        System.out.println("Accuracy: " + trial.getAccuracy());

        // precision, recall, and F1 are calcuated for a specific
        //  class, which can be identified by an object (usually
        //  a String) or the integer ID of the class

        System.out.println("F1 for class 'good': " + trial.getF1("good"));

        System.out.println("Precision for class '" +
                classifier.getLabelAlphabet().lookupLabel(1) + "': " +
                trial.getPrecision(1));
    }