/**
* Sets the sigma parameter to a value that optimizes the cross-validation score given by <code>
* scorer</code>. Search for an optimal value is carried out by <code>minimizer</code>
*
* @param dataset the data set to optimize sigma on.
*/
public void crossValidateSetSigma(
GeneralDataset<L, F> dataset, int kfold, final Scorer<L> scorer, LineSearcher minimizer) {
System.err.println("##in Cross Validate, folds = " + kfold);
System.err.println("##Scorer is " + scorer);
featureIndex = dataset.featureIndex;
labelIndex = dataset.labelIndex;
final CrossValidator<L, F> crossValidator = new CrossValidator<L, F>(dataset, kfold);
final Function<
Triple<GeneralDataset<L, F>, GeneralDataset<L, F>, CrossValidator.SavedState>, Double>
score =
new Function<
Triple<GeneralDataset<L, F>, GeneralDataset<L, F>, CrossValidator.SavedState>,
Double>() {
public Double apply(
Triple<GeneralDataset<L, F>, GeneralDataset<L, F>, CrossValidator.SavedState>
fold) {
GeneralDataset<L, F> trainSet = fold.first();
GeneralDataset<L, F> devSet = fold.second();
double[] weights = (double[]) fold.third().state;
double[][] weights2D;
weights2D =
trainWeights(
trainSet, weights, true); // must of course bypass sigma tuning here.
fold.third().state = ArrayUtils.flatten(weights2D);
LinearClassifier<L, F> classifier =
new LinearClassifier<L, F>(
weights2D, trainSet.featureIndex, trainSet.labelIndex);
double score = scorer.score(classifier, devSet);
// System.out.println("score: "+score);
System.out.print(".");
return score;
}
};
Function<Double, Double> negativeScorer =
new Function<Double, Double>() {
public Double apply(Double sigmaToTry) {
// sigma = sigmaToTry;
setSigma(sigmaToTry);
Double averageScore = crossValidator.computeAverage(score);
System.err.print("##sigma = " + getSigma() + " ");
System.err.println("-> average Score: " + averageScore);
return -averageScore;
}
};
double bestSigma = minimizer.minimize(negativeScorer);
System.err.println("##best sigma: " + bestSigma);
setSigma(bestSigma);
}
/**
* Sets the sigma parameter to a value that optimizes the held-out score given by <code>scorer
* </code>. Search for an optimal value is carried out by <code>minimizer</code> dataset the data
* set to optimize sigma on. kfold
*
* @return an interim set of optimal weights: the weights
*/
public double[] heldOutSetSigma(
final GeneralDataset<L, F> trainSet,
final GeneralDataset<L, F> devSet,
final Scorer<L> scorer,
LineSearcher minimizer) {
featureIndex = trainSet.featureIndex;
labelIndex = trainSet.labelIndex;
// double[] resultWeights = null;
Timing timer = new Timing();
NegativeScorer negativeScorer = new NegativeScorer(trainSet, devSet, scorer, timer);
timer.start();
double bestSigma = minimizer.minimize(negativeScorer);
System.err.println("##best sigma: " + bestSigma);
setSigma(bestSigma);
return ArrayUtils.flatten(
trainWeights(
trainSet,
negativeScorer.weights,
true)); // make sure it's actually the interim weights from best sigma
}
