Java AttributeSelection类代码示例

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
/**
 * uses the filter
 */
protected static void useFilter(Instances data) throws Exception {
    System.out.println("\n2. Filter");
    weka.filters.supervised.attribute.AttributeSelection filter = new weka.filters.supervised.attribute.AttributeSelection();
    CfsSubsetEval eval = new CfsSubsetEval();
    GreedyStepwise search = new GreedyStepwise();
    search.setSearchBackwards(true);
    filter.setEvaluator(eval);
    System.out.println("Set the evaluator : " + eval.toString());
    filter.setSearch(search);
    System.out.println("Set the search : " + search.toString());
    filter.setInputFormat(data);
    System.out.println("Set the input format : " + data.toString());
    Instances newData = Filter.useFilter(data, filter);
    System.out.println("Results of Filter:\n" + newData);

}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public static Instances preProcessData(Instances data) throws Exception{
	
	/* 
	 * Remove useless attributes
	 */
	RemoveUseless removeUseless = new RemoveUseless();
	removeUseless.setOptions(new String[] { "-M", "99" });	// threshold
	removeUseless.setInputFormat(data);
	data = Filter.useFilter(data, removeUseless);

	
	/* 
	 * Remove useless attributes
	 */
	ReplaceMissingValues fixMissing = new ReplaceMissingValues();
	fixMissing.setInputFormat(data);
	data = Filter.useFilter(data, fixMissing);
	

	/* 
	 * Remove useless attributes
	 */
	Discretize discretizeNumeric = new Discretize();
	discretizeNumeric.setOptions(new String[] {
			"-O",
			"-M",  "-1.0", 
			"-B",  "4",  // no of bins
			"-R",  "first-last"}); //range of attributes
	fixMissing.setInputFormat(data);
	data = Filter.useFilter(data, fixMissing);

	/* 
	 * Select only informative attributes
	 */
	InfoGainAttributeEval eval = new InfoGainAttributeEval();
	Ranker search = new Ranker();
	search.setOptions(new String[] { "-T", "0.001" });	// information gain threshold
	AttributeSelection attSelect = new AttributeSelection();
	attSelect.setEvaluator(eval);
	attSelect.setSearch(search);
	
	// apply attribute selection
	attSelect.SelectAttributes(data);
	
	// remove the attributes not selected in the last run
	data = attSelect.reduceDimensionality(data);
	
	

	return data;
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
/**
 * Method featureSelection, which uses an algorithm to select the most representative features of
 * the data in patterns_krs table
 *
 * @param data The instances from patterns_krs table
 *
 * @return indexes The indexes of the attributes selected by the algorithm
 */
   
public int[] featureSelection(Instances data){
   
    int[] indexes = null;
    AttributeSelection attsel = new AttributeSelection();
    //FuzzyRoughSubsetEval eval = new FuzzyRoughSubsetEval();
    //HillClimber search = new HillClimber();
    CfsSubsetEval eval = new CfsSubsetEval();
    GreedyStepwise search = new GreedyStepwise();
    attsel.setEvaluator(eval);
    attsel.setSearch(search);
    try {
        attsel.SelectAttributes(data);
        indexes = attsel.selectedAttributes();
        logger.info("Selected Features: "+Utils.arrayToString(indexes));
    } catch (Exception e) {
        e.printStackTrace();
    }
   
    return indexes;
   
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public void selectFeatures(){
	AttributeSelection attSelection = new AttributeSelection();
    CfsSubsetEval eval = new CfsSubsetEval();
    BestFirst search = new BestFirst();
    attSelection.setEvaluator(eval);
    attSelection.setSearch(search);
    try {
		attSelection.SelectAttributes(iris);
		int[] attIndex = attSelection.selectedAttributes();
		System.out.println(Utils.arrayToString(attIndex));
	} catch (Exception e) {
	}
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public void selectFeaturesWithFilter(){
	weka.filters.supervised.attribute.AttributeSelection filter = new weka.filters.supervised.attribute.AttributeSelection();
    CfsSubsetEval eval = new CfsSubsetEval();
    BestFirst search = new BestFirst();
    filter.setEvaluator(eval);
    filter.setSearch(search);
    try {
		filter.setInputFormat(iris);
		Instances newData = Filter.useFilter(iris, filter);
		System.out.println(newData);
	} catch (Exception e) {
	}
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public TrainedModelPredictionMaker(String attributeSelectionObjPath, String modelObjPath, String instancesPath, String classIndex, String predictionPath)
{
    //Go forth and load some instances
    try
    {
        DataSource dataSource = new DataSource(new FileInputStream(instancesPath));
        Instances instances = dataSource.getDataSet();

        //Make sure to 
        if (instances.classIndex() == -1){
            if(classIndex.equals("last"))
                instances.setClassIndex(instances.numAttributes() - 1);
            else
                instances.setClassIndex(Integer.parseInt(classIndex));
        }

        //Load up the attribute selection if we need to
        if(attributeSelectionObjPath != null){
            AttributeSelection as = (AttributeSelection)weka.core.SerializationHelper.read(attributeSelectionObjPath);
            instances = as.reduceDimensionality(instances);
        }

        //Load up yonder classifier
        AbstractClassifier classifier = (AbstractClassifier)weka.core.SerializationHelper.read(modelObjPath);
        
        //Make the evaluation
        eval = new Evaluation(instances);
        ClassifierRunner.EvaluatorThread thrd = new ClassifierRunner.EvaluatorThread(eval, classifier, instances, predictionPath);
        thrd.run();
    }catch(Exception e){
        throw new RuntimeException(e);
    }
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
/**
 * uses the low level approach
 */
protected static void useLowLevel(Instances data) throws Exception {
    System.out.println("\n3. Low-level");
    AttributeSelection attsel = new AttributeSelection();
    attsel.SelectAttributes(data);
    int[] indices = attsel.selectedAttributes();
    for (int i = 0; i < indices.length; i++) {
        System.out.println(data.attribute(i).toString());
    }
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
private static AttributeSelection getAttributeSelector(
		Instances trainingData) throws Exception {
	AttributeSelection selector = new AttributeSelection();
	InfoGainAttributeEval evaluator = new InfoGainAttributeEval();
	Ranker ranker = new Ranker();
	ranker.setNumToSelect(Math.min(500, trainingData.numAttributes() - 1));
	selector.setEvaluator(evaluator);
	selector.setSearch(ranker);
	selector.SelectAttributes(trainingData);
	return selector;
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
@TimeThis(task="select-attributes")
protected String selectAttributes(@SuppressWarnings("unused") ProcessingContext<Corpus> ctx, IdentifiedInstances<Element> trainingSet) throws Exception {
	ASEvaluation eval = ASEvaluation.forName(evaluator, evaluatorOptions);
	return AttributeSelection.SelectAttributes(eval, getEvalOptions(), trainingSet);
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
/**
 * 
 * Learns the rule from parsed features in a cross validation and the set
 * parameters. Additionally feature subset selection is conducted, if the
 * parameters this.forwardSelection or this.backwardSelection are set
 * accordingly.
 * 
 * @param features
 *            Contains features to learn a classifier
 */

@Override
public Performance learnParameters(FeatureVectorDataSet features) {
	// create training
	Instances trainingData = transformToWeka(features, this.trainingSet);

	try {
		Evaluation eval = new Evaluation(trainingData);
		// apply feature subset selection
		if (this.forwardSelection || this.backwardSelection) {

			GreedyStepwise search = new GreedyStepwise();
			search.setSearchBackwards(this.backwardSelection);

			this.fs = new AttributeSelection();
			WrapperSubsetEval wrapper = new WrapperSubsetEval();

			// Do feature subset selection, but using a 10-fold cross
			// validation
			wrapper.buildEvaluator(trainingData);
			wrapper.setClassifier(this.classifier);
			wrapper.setFolds(10);
			wrapper.setThreshold(0.01);

			this.fs.setEvaluator(wrapper);
			this.fs.setSearch(search);

			this.fs.SelectAttributes(trainingData);

			trainingData = fs.reduceDimensionality(trainingData);

		}
		// perform 10-fold Cross Validation to evaluate classifier
		eval.crossValidateModel(this.classifier, trainingData, 10, new Random(1));
		System.out.println(eval.toSummaryString("\nResults\n\n", false));
		
		this.classifier.buildClassifier(trainingData);
		
		int truePositive = (int) eval.numTruePositives(trainingData.classIndex());
		int falsePositive = (int) eval.numFalsePositives(trainingData.classIndex());
		int falseNegative = (int) eval.numFalseNegatives(trainingData.classIndex());
		Performance performance = new Performance(truePositive, truePositive + falsePositive,
				truePositive + falseNegative);

		return performance;

	} catch (Exception e) {
		e.printStackTrace();
		return null;
	}
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public AttributeSelectorThread(AttributeSelection selection, Instances inst)
{
    mInstances = inst;
    mSelection = selection;
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public void setAttributeSelection(AttributeSelection search)
{
    mAttributeSelection = search;
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public AttributeSelection getAttributeSelection()
{
    return mAttributeSelection;
}
 

import weka.attributeSelection.AttributeSelection; //导入依赖的package包/类
public static Model buildModel(int crisisID, int attributeID, Model oldModel)
		throws Exception {

	// TODO: Improve model training to try different classifiers and
	// different mixes of old and new data

	// Get training and evaluation data
	Instances trainingSet = DataStore.getTrainingSet(crisisID, attributeID);
	Instances evaluationSet = DataStore.getEvaluationSet(crisisID,
			attributeID, trainingSet);

	if (trainingSet.attribute(trainingSet.numAttributes() - 1).numValues() < 2) {
		logger.info("ModelFactory" + 
				"All training examples have the same label. Postponing training.");
		return oldModel;
	}
	if (evaluationSet.numInstances() < 2) {
		logger.info("ModelFactory" +
				"The evaluation set is too small. Postponing training.");
		return oldModel;
	}

	// Do attribute selection
	AttributeSelection selector = getAttributeSelector(trainingSet);
	trainingSet = selector.reduceDimensionality(trainingSet);
	evaluationSet = selector.reduceDimensionality(evaluationSet);

	// Train classifier
	Classifier classifier = trainClassifier(trainingSet);

	// Create the model object
	Model model = new Model(attributeID, classifier, getTemplateSet(trainingSet));
	model.setTrainingSampleCount(trainingSet.size());

	// Evaluate classifier
	model.evaluate(evaluationSet);
	double newPerformance = model.getWeightedPerformance();
	double oldPerformance = 0;
	if (oldModel != null) {
		oldModel.evaluate(evaluationSet);
		oldPerformance = oldModel.getWeightedPerformance();
	}

	// Koushik: Changed as per ChaTo's suggestion
	/*
       if (newPerformance > oldPerformance - EPSILON) {
           return model;
       } else {
           return oldModel;
       }*/
	if (newPerformance > oldPerformance - PERFORMANCE_IMPROVEMENT_MARGIN) {
		return model;
	} else if( model.getTrainingSampleCount() > oldModel.getTrainingSampleCount() + TRAINING_EXAMPLES_FORCE_RETRAIN) {
		return model;
	} else {
		return oldModel;
	}
}