public void rank(String modelFile, String testFile, String indriRanking) {
Ranker ranker = rFact.loadRanker(modelFile);
int[] features = ranker.getFeatures();
List<RankList> test = readInput(testFile);
if (normalize) normalize(test, features);
try {
BufferedWriter out =
new BufferedWriter(new OutputStreamWriter(new FileOutputStream(indriRanking), "ASCII"));
for (int i = 0; i < test.size(); i++) {
RankList l = test.get(i);
double[] scores = new double[l.size()];
for (int j = 0; j < l.size(); j++) scores[j] = ranker.eval(l.get(j));
int[] idx = MergeSorter.sort(scores, false);
for (int j = 0; j < idx.length; j++) {
int k = idx[j];
String str =
l.getID()
+ " Q0 "
+ l.get(k).getDescription().replace("#", "").trim()
+ " "
+ (j + 1)
+ " "
+ SimpleMath.round(scores[k], 5)
+ " indri";
out.write(str);
out.newLine();
}
}
out.close();
} catch (Exception ex) {
System.out.println("Error in Evaluator::rank(): " + ex.toString());
}
}
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 rank(String modelFile, String testFile) {
Ranker ranker = rFact.loadRanker(modelFile);
int[] features = ranker.getFeatures();
List<RankList> test = readInput(testFile);
if (normalize) normalize(test, features);
for (int i = 0; i < test.size(); i++) {
RankList l = test.get(i);
double[] scores = new double[l.size()];
for (int j = 0; j < l.size(); j++) scores[j] = ranker.eval(l.get(j));
int[] idx = Sorter.sort(scores, false);
List<Integer> ll = new ArrayList<Integer>();
for (int j = 0; j < idx.length; j++) ll.add(idx[j]);
for (int j = 0; j < l.size(); j++) {
int index = ll.indexOf(j) + 1;
System.out.print(index + ((j == l.size() - 1) ? "" : " "));
}
System.out.println("");
}
}
public void score(String modelFile, String testFile, String outputFile) {
Ranker ranker = rFact.loadRanker(modelFile);
int[] features = ranker.getFeatures();
List<RankList> test = readInput(testFile);
if (normalize) normalize(test, features);
try {
BufferedWriter out =
new BufferedWriter(new OutputStreamWriter(new FileOutputStream(outputFile), "ASCII"));
for (int i = 0; i < test.size(); i++) {
RankList l = test.get(i);
for (int j = 0; j < l.size(); j++) {
out.write(ranker.eval(l.get(j)) + "");
out.newLine();
}
}
out.close();
} catch (Exception ex) {
System.out.println("Error in Evaluator::rank(): " + ex.toString());
}
}
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));
}
/**
* 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 <data, defined features> with k-fold
* cross validation.
*
* @param sampleFile
* @param featureDefFile
* @param nFold
*/
public void evaluate(String sampleFile, String featureDefFile, int nFold) {
List<List<RankList>> trainingData = new ArrayList<List<RankList>>();
List<List<RankList>> testData = new ArrayList<List<RankList>>();
int[] features =
prepareCV(sampleFile, featureDefFile, nFold, normalize, trainingData, testData);
Ranker ranker = null;
double origScore = 0.0;
double rankScore = 0.0;
double oracleScore = 0.0;
for (int i = 0; i < nFold; i++) {
List<RankList> train = trainingData.get(i);
List<RankList> test = testData.get(i);
ranker = rFact.createRanker(type, train, features);
ranker.set(trainScorer);
ranker.init();
ranker.learn();
double s1 = evaluate(null, test);
origScore += s1;
double s2 = evaluate(ranker, test);
rankScore += s2;
double s3 = evaluate(null, createOracles(test));
oracleScore += s3;
}
System.out.println(
"Total: "
+ SimpleMath.round(origScore / nFold, 4)
+ "\t"
+ SimpleMath.round(rankScore / nFold, 4)
+ "\t"
+ SimpleMath.round(oracleScore / nFold, 4)
+ "\t");
}
/**
* 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 double evaluate(Ranker ranker, List<RankList> rl) {
List<RankList> l = rl;
if (ranker != null) l = ranker.rank(rl);
return testScorer.score(l);
}
