@Override
public void trainMostSimilar(List<EnsembleSim> simList) {
if (simList.isEmpty()) {
throw new IllegalStateException("no examples to train on!");
}
mostSimilarInterpolator.trainMostSimilar(simList);
// Remove things that have no observed metrics
List<EnsembleSim> pruned = new ArrayList<EnsembleSim>();
for (EnsembleSim es : simList) {
if (es != null && es.getNumMetricsWithScore() > 0) {
pruned.add(es);
}
}
double[][] X = new double[pruned.size()][numMetrics * 2];
double[] Y = new double[pruned.size()];
for (int i = 0; i < pruned.size(); i++) {
Y[i] = pruned.get(i).knownSim.similarity;
EnsembleSim es = mostSimilarInterpolator.interpolate(pruned.get(i));
for (int j = 0; j < numMetrics; j++) {
X[i][2 * j] = es.getScores().get(j);
X[i][2 * j + 1] = Math.log(es.getRanks().get(j) + 1);
}
}
OLSMultipleLinearRegression regression = new OLSMultipleLinearRegression();
regression.newSampleData(Y, X);
mostSimilarCoefficients = new TDoubleArrayList(regression.estimateRegressionParameters());
double pearson = Math.sqrt(regression.calculateRSquared());
LOG.info("coefficients are " + mostSimilarCoefficients.toString());
LOG.info("pearson for multiple regression is " + pearson);
}
@Override
public void trainSimilarity(List<EnsembleSim> simList) {
if (simList.isEmpty()) {
throw new IllegalArgumentException("no examples to train on!");
}
similarityInterpolator.trainSimilarity(simList);
double[][] X = new double[simList.size()][numMetrics];
double[] Y = new double[simList.size()];
for (int i = 0; i < simList.size(); i++) {
Y[i] = simList.get(i).knownSim.similarity;
EnsembleSim es = similarityInterpolator.interpolate(simList.get(i));
for (int j = 0; j < numMetrics; j++) {
X[i][j] = es.getScores().get(j);
}
}
OLSMultipleLinearRegression regression = new OLSMultipleLinearRegression();
regression.newSampleData(Y, X);
simlarityCoefficients = new TDoubleArrayList(regression.estimateRegressionParameters());
double pearson = Math.sqrt(regression.calculateRSquared());
LOG.info("coefficients are " + simlarityCoefficients.toString());
LOG.info("pearson for multiple regression is " + pearson);
}