public Evaluator(RANKER_TYPE rType, String trainMetric, String testMetric) {
this.type = rType;
trainScorer = mFact.createScorer(trainMetric);
testScorer = mFact.createScorer(testMetric);
if (qrelFile.compareTo("") != 0) {
trainScorer.loadExternalRelevanceJudgment(qrelFile);
testScorer.loadExternalRelevanceJudgment(qrelFile);
}
}
/**
* Evaluate the currently selected ranking algorithm using percenTrain% of the training samples
* for training the rest as validation data. Test data is specified separately.
*
* @param trainFile
* @param percentTrain
* @param testFile Empty string for "no test data"
* @param featureDefFile
*/
public void evaluate(
String trainFile, double percentTrain, String testFile, String featureDefFile) {
List<RankList> train = new ArrayList<RankList>();
List<RankList> validation = new ArrayList<RankList>();
int[] features =
prepareSplit(trainFile, featureDefFile, percentTrain, normalize, train, validation);
List<RankList> test = null;
if (testFile.compareTo("") != 0) test = readInput(testFile);
Ranker ranker = rFact.createRanker(type, train, features);
ranker.set(trainScorer);
ranker.setValidationSet(validation);
ranker.init();
ranker.learn();
if (test != null) {
double rankScore = evaluate(ranker, test);
System.out.println(testScorer.name() + " on test data: " + SimpleMath.round(rankScore, 4));
}
if (modelFile.compareTo("") != 0) {
System.out.println("");
ranker.save(modelFile);
System.out.println("Model saved to: " + modelFile);
}
}
/**
* Evaluate the currently selected ranking algorithm using <training data, validation data,
* testing data and the defined features>.
*
* @param trainFile
* @param validationFile
* @param testFile
* @param featureDefFile
*/
public void evaluate(
String trainFile, String validationFile, String testFile, String featureDefFile) {
List<RankList> train = readInput(trainFile); // read input
List<RankList> validation = null;
if (validationFile.compareTo("") != 0) validation = readInput(validationFile);
List<RankList> test = null;
if (testFile.compareTo("") != 0) test = readInput(testFile);
int[] features = readFeature(featureDefFile); // read features
if (features == null) // no features specified ==> use all features in the training file
features = getFeatureFromSampleVector(train);
if (normalize) {
normalize(train, features);
if (validation != null) normalize(validation, features);
if (test != null) normalize(test, features);
}
/*if(newFeatureFile.compareTo("")!=0)
{
System.out.print("Loading new feature description file... ");
List<String> descriptions = FileUtils.readLine(newFeatureFile, "ASCII");
int taken = 0;
for(int i=0;i<descriptions.size();i++)
{
if(descriptions.get(i).indexOf("##")==0)
continue;
LinearComputer lc = new LinearComputer("", descriptions.get(i));
//if we keep the orig. features ==> discard size-1 linear computer
if(!keepOrigFeatures || lc.size()>1)
{
lcList.add(lc);
taken++;
if(taken == topNew)
break;
}
//System.out.println(lc.toString());
}
applyNewFeatures(train, features);
applyNewFeatures(validation, features);
features = applyNewFeatures(test, features);
System.out.println("[Done]");//0.1195
//0.071
}*/
Ranker ranker = rFact.createRanker(type, train, features);
ranker.set(trainScorer);
ranker.setValidationSet(validation);
ranker.init();
ranker.learn();
if (test != null) {
double rankScore = evaluate(ranker, test);
System.out.println(testScorer.name() + " on test data: " + SimpleMath.round(rankScore, 4));
}
if (modelFile.compareTo("") != 0) {
System.out.println("");
ranker.save(modelFile);
System.out.println("Model saved to: " + modelFile);
}
}
public void test(String modelFile, String testFile) {
Ranker ranker = rFact.loadRanker(modelFile);
int[] features = ranker.getFeatures();
List<RankList> test = readInput(testFile);
if (normalize) normalize(test, features);
double rankScore = evaluate(ranker, test);
System.out.println(testScorer.name() + " on test data: " + SimpleMath.round(rankScore, 4));
}
public void test(String modelFile, String testFile, boolean printIndividual) {
Ranker ranker = rFact.loadRanker(modelFile);
int[] features = ranker.getFeatures();
List<RankList> test = readInput(testFile);
if (normalize) normalize(test, features);
double rankScore = 0.0;
double score = 0.0;
for (int i = 0; i < test.size(); i++) {
RankList l = ranker.rank(test.get(i));
score = testScorer.score(l);
if (printIndividual)
System.out.println(
testScorer.name() + " " + l.getID() + " " + SimpleMath.round(score, 4));
rankScore += score;
}
rankScore /= test.size();
if (printIndividual)
System.out.println(testScorer.name() + " all " + SimpleMath.round(rankScore, 4));
else System.out.println(testScorer.name() + " on test data: " + SimpleMath.round(rankScore, 4));
}
public void test(String testFile) {
List<RankList> test = readInput(testFile);
double rankScore = evaluate(null, test);
System.out.println(testScorer.name() + " on test data: " + SimpleMath.round(rankScore, 4));
}
public double evaluate(Ranker ranker, List<RankList> rl) {
List<RankList> l = rl;
if (ranker != null) l = ranker.rank(rl);
return testScorer.score(l);
}
public Evaluator(RANKER_TYPE rType, METRIC metric, int k) {
this.type = rType;
trainScorer = mFact.createScorer(metric, k);
if (qrelFile.compareTo("") != 0) trainScorer.loadExternalRelevanceJudgment(qrelFile);
testScorer = trainScorer;
}
