Java Clustering.getNumClusters方法代码示例

import cc.mallet.cluster.Clustering; //导入方法依赖的package包/类
@Override
public double[] getEvaluationScores(Clustering truth, Clustering predicted) {
	// Precision = \sum_i [ |siprime| - |pOfsiprime| ] / \sum_i [ |siprime| - 1 ]		
	// where siprime is a predicted cluster, pOfsiprime is the set of
	// true clusters that contain elements of siprime.
	int numerator = 0;
	int denominator = 0;
	for (int i = 0; i < predicted.getNumClusters(); i++) {
		int[] siprime = predicted.getIndicesWithLabel(i);
		HashSet<Integer> pOfsiprime = new HashSet<Integer>();
		for (int j = 0; j < siprime.length; j++) 
			pOfsiprime.add(truth.getLabel(siprime[j]));
		numerator += siprime.length - pOfsiprime.size();
		denominator += siprime.length - 1;
	}
	precisionNumerator += numerator;
	precisionDenominator += denominator;
	double precision = (double)numerator / denominator;

	// Recall = \sum_i [ |si| - |pOfsi| ] / \sum_i [ |si| - 1 ]		
	// where si is a true cluster, pOfsi is the set of predicted
	// clusters that contain elements of si.
	numerator = denominator = 0;
	for (int i = 0; i < truth.getNumClusters(); i++) {
		int[] si = truth.getIndicesWithLabel(i);
		HashSet<Integer> pOfsi = new HashSet<Integer>();
		for (int j = 0; j < si.length; j++) 
			pOfsi.add(new Integer(predicted.getLabel(si[j])));
		numerator += si.length - pOfsi.size();
		denominator += si.length - 1;
	}
	recallNumerator += numerator;
	recallDenominator += denominator;
	double recall = (double)numerator / denominator;
	return new double[]{precision,recall,(2 * precision * recall / (precision + recall))};
}
 

import cc.mallet.cluster.Clustering; //导入方法依赖的package包/类
@Override
public double[] getEvaluationScores(Clustering truth, Clustering predicted) {
	int tp, fn, fp;
	tp = fn = fp = 0;
	
	for (int i = 0; i < predicted.getNumClusters(); i++) {
		int[] predIndices = predicted.getIndicesWithLabel(i);
		
		for (int j = 0; j < predIndices.length; j++) 
			for (int k = j + 1; k < predIndices.length; k++) 
				if (truth.getLabel(predIndices[j]) == truth.getLabel(predIndices[k]))
					tp++;
				else 
					fp++;
	}

	for (int i = 0; i < truth.getNumClusters(); i++) {
		int[] trueIndices = truth.getIndicesWithLabel(i);
		for (int j = 0; j < trueIndices.length; j++) 
			for (int k = j + 1; k < trueIndices.length; k++) 
				if (predicted.getLabel(trueIndices[j]) != predicted.getLabel(trueIndices[k]))
					fn++;
	}

	double pr = (double)tp / (tp+fp);
	double rec = (double)tp / (tp+fn);
	double f1 = 2*pr*rec/(pr+rec);
	this.tpTotal += tp;
	this.fpTotal += fp;
	this.fnTotal += fn;

	return new double[]{pr, rec, f1};
}
 

import cc.mallet.cluster.Clustering; //导入方法依赖的package包/类
/**
 * @param clustering 
 * @return A shallow copy of the argument where new objects are only
 * allocated for the cluster assignment.
 */
public static Clustering copyWithNewLabels (Clustering clustering) {
	int[] oldLabels = clustering.getLabels();
	int[] newLabels = new int[oldLabels.length];
	System.arraycopy(oldLabels, 0, newLabels, 0, oldLabels.length);
	return new Clustering(clustering.getInstances(),
												clustering.getNumClusters(),
												newLabels);
}