Java InstanceList.getFeatureSelection方法代码示例

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public C45 train (InstanceList trainingList)
{
	FeatureSelection selectedFeatures = trainingList.getFeatureSelection();
	if (selectedFeatures != null)
		// xxx Attend to FeatureSelection!!!
		throw new UnsupportedOperationException ("FeatureSelection not yet implemented.");
	C45.Node root = new C45.Node(trainingList, null, m_minNumInsts);
	splitTree(root, 0);
	C45 tree = new C45 (trainingList.getPipe(), root);
	logger.info("C45 learned: (size=" + tree.getSize() + ")\n");
	tree.print();
	if (m_doPruning) {
		tree.prune();
		logger.info("\nPruned C45: (size=" + tree.getSize() + ")\n");
		root.print();
	}
	root.stopGrowth();
	this.classifier = tree;
	return classifier;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public void evaluateInstanceList (ClassifierTrainer trainer,	InstanceList instances, String description) 
{
	Classifier classifier = trainer.getClassifier();
	if (classifier.getFeatureSelection() != instances.getFeatureSelection())
		// TODO consider if we really want to do this... but note that the old MaxEnt did this to the testing the validation sets.
		//instances.setFeatureSelection(classifier.getFeatureSelection());
   System.out.print (description+" accuracy=" + classifier.getAccuracy (instances));
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
public DecisionTree train (InstanceList trainingList) {
	FeatureSelection selectedFeatures = trainingList.getFeatureSelection();
	DecisionTree.Node root = new DecisionTree.Node (trainingList, null, selectedFeatures);
	splitTree (root, selectedFeatures, 0);
	root.stopGrowth();
	finished = true;
	System.out.println ("DecisionTree learned:");
	root.print();
	this.classifier = new DecisionTree (trainingList.getPipe(), root);
	return classifier;
}
 

import cc.mallet.types.InstanceList; //导入方法依赖的package包/类
/**
	 * Trains winnow on the instance list, updating 
	 * {@link #weights weights} according to errors
	 * @param ilist Instance list to be trained on
	 * @return Classifier object containing learned weights
	 */
	public Winnow train (InstanceList trainingList)
	{
		FeatureSelection selectedFeatures = trainingList.getFeatureSelection();
		if (selectedFeatures != null)
			// xxx Attend to FeatureSelection!!!
			throw new UnsupportedOperationException ("FeatureSelection not yet implemented.");
		// if "train" is run more than once, 
		// we will be reinitializing the weights
		// TODO: provide method to save weights
		trainingList.getDataAlphabet().stopGrowth();
		trainingList.getTargetAlphabet().stopGrowth();
		Pipe dataPipe = trainingList.getPipe ();
		Alphabet dict = (Alphabet) trainingList.getDataAlphabet ();
		int numLabels = trainingList.getTargetAlphabet().size();
		int numFeats = dict.size(); 
		this.theta =  numFeats * this.nfactor;
		this.weights = new double [numLabels][numFeats];
		// init weights to 1
		for(int i=0; i<numLabels; i++)
			for(int j=0; j<numFeats; j++)
				this.weights[i][j] = 1.0;
		//System.out.println("Init weights to 1.  Theta= "+theta);
		// loop through all instances
		for (int ii = 0; ii < trainingList.size(); ii++){
			Instance inst = (Instance) trainingList.get(ii);
			Labeling labeling = inst.getLabeling ();
			FeatureVector fv = (FeatureVector) inst.getData ();
			double[] results = new double [numLabels]; 
			int fvisize = fv.numLocations();
			int correctIndex = labeling.getBestIndex();
			
			for(int rpos=0; rpos < numLabels; rpos++)
		    results[rpos]=0;
			// sum up xi*wi for each class
			for(int fvi=0; fvi < fvisize; fvi++){
				int fi = fv.indexAtLocation(fvi);
				//System.out.println("feature index "+fi);
				for(int lpos=0; lpos < numLabels; lpos++)
			    results[lpos] += this.weights[lpos][fi];
			}
			//System.out.println("In instance " + ii);
			// make guess for each label using threshold
			// update weights according to alpha and beta 
			// upon incorrect guess
			for(int ri=0; ri < numLabels; ri++){
				if(results[ri] > this.theta){ // guess 1
					if(correctIndex != ri) // correct is 0
				    demote(ri, fv);
				}
				else{ // guess 0
					if(correctIndex == ri) // correct is 1
						promote(ri, fv);   
				}
			}
//			System.out.println("Results guessed:")
//		for(int x=0; x<numLabels; x++)
//		    System.out.println(results[x]);
//			System.out.println("Correct label: "+correctIndex );
//			System.out.println("Weights are");
//			for(int h=0; h<numLabels; h++){
//				for(int g=0; g<numFeats; g++)
//			    System.out.println(weights[h][g]);
//				System.out.println("");
//			}
		}
		classifier = new Winnow (dataPipe, weights, theta, numLabels, numFeats);
		return classifier;
	}