本文整理汇总了Java中cc.mallet.types.InfoGain.getValueAtRank方法的典型用法代码示例。如果您正苦于以下问题：Java InfoGain.getValueAtRank方法的具体用法？Java InfoGain.getValueAtRank怎么用？Java InfoGain.getValueAtRank使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类cc.mallet.types.InfoGain的用法示例。
在下文中一共展示了InfoGain.getValueAtRank方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: labelFeatures
import cc.mallet.types.InfoGain; //导入方法依赖的package包/类
/**
* Label features using heuristic described in
* "Learning from Labeled Features using Generalized Expectation Criteria"
* Gregory Druck, Gideon Mann, Andrew McCallum.
*
* @param list InstanceList used to compute statistics for labeling features.
* @param features List of features to label.
* @param reject Whether to reject labeling features.
* @return Labeled features, HashMap mapping feature indices to list of labels.
*/
public static HashMap<Integer, ArrayList<Integer>> labelFeatures(InstanceList list, ArrayList<Integer> features, boolean reject) {
HashMap<Integer,ArrayList<Integer>> labeledFeatures = new HashMap<Integer,ArrayList<Integer>>();
double[][] featureLabelCounts = getFeatureLabelCounts(list,true);
int numLabels = list.getTargetAlphabet().size();
int minRank = 100 * numLabels;
InfoGain infogain = new InfoGain(list);
double sum = 0;
for (int rank = 0; rank < minRank; rank++) {
sum += infogain.getValueAtRank(rank);
}
double mean = sum / minRank;
for (int i = 0; i < features.size(); i++) {
int fi = features.get(i);
// reject features with infogain
// less than cutoff
if (reject && infogain.value(fi) < mean) {
//System.err.println("Oracle labeler rejected labeling: " + list.getDataAlphabet().lookupObject(fi));
logger.info("Oracle labeler rejected labeling: " + list.getDataAlphabet().lookupObject(fi));
continue;
}
double[] prob = featureLabelCounts[fi];
MatrixOps.plusEquals(prob,1e-8);
MatrixOps.timesEquals(prob, 1./MatrixOps.sum(prob));
int[] sortedIndices = getMaxIndices(prob);
ArrayList<Integer> labels = new ArrayList<Integer>();
if (numLabels > 2) {
// take anything within a factor of 2 of the best
// but no more than numLabels/2
boolean discard = false;
double threshold = prob[sortedIndices[0]] / 2;
for (int li = 0; li < numLabels; li++) {
if (prob[li] > threshold) {
labels.add(li);
}
if (reject && labels.size() > (numLabels / 2)) {
//System.err.println("Oracle labeler rejected labeling: " + list.getDataAlphabet().lookupObject(fi));
logger.info("Oracle labeler rejected labeling: " + list.getDataAlphabet().lookupObject(fi));
discard = true;
break;
}
}
if (discard) {
continue;
}
}
else {
labels.add(sortedIndices[0]);
}
labeledFeatures.put(fi, labels);
}
return labeledFeatures;
}