/**
* @param targetTerm
* @param sourceFile
* @param trainingAlgo
* @param outputFileClassifier
* @param outputFileResults
* @param termWindowSize
* @param pipe
* @return
*/
private static List<ClassificationResult> runTrainingAndClassification(
String targetTerm,
String sourceFile,
String trainingAlgo,
String outputFileClassifier,
String outputFileResults,
int termWindowSize,
Pipe pipe,
boolean useCollocationalVector) {
// Read in concordance file and create list of Mallet training instances
// TODO: Remove duplication of code (see execConvertToMalletFormat(...))
String vectorType = useCollocationalVector ? "coll" : "bow";
InstanceList instanceList =
readConcordanceFileToInstanceList(
targetTerm, sourceFile, termWindowSize, pipe, useCollocationalVector);
// Creating splits for training and testing
double[] proportions = {0.9, 0.1};
InstanceList[] splitLists = instanceList.split(proportions);
InstanceList trainingList = splitLists[0];
InstanceList testList = splitLists[1];
// Train the classifier
ClassifierTrainer classifierTrainer = getClassifierTrainerForAlgorithm(trainingAlgo);
Classifier classifier = classifierTrainer.train(trainingList);
if (classifier.getLabelAlphabet()
!= null) { // TODO: Make sure this is not null in RandomClassifier
System.out.println("Labels:\n" + classifier.getLabelAlphabet());
System.out.println(
"Size of data alphabet (= type count of training list): "
+ classifier.getAlphabet().size());
}
// Run tests and get results
Trial trial = new Trial(classifier, testList);
List<ClassificationResult> results = new ArrayList<ClassificationResult>();
for (int i = 0; i < classifier.getLabelAlphabet().size(); i++) {
Label label = classifier.getLabelAlphabet().lookupLabel(i);
ClassificationResult result =
new MalletClassificationResult(
trainingAlgo,
targetTerm,
vectorType,
label.toString(),
termWindowSize,
trial,
sourceFile);
results.add(result);
System.out.println(result.toString());
}
// Save classifier
saveClassifierToFile(outputFileClassifier, classifier, trainingAlgo, termWindowSize);
return results;
}
public static void trainAndSaveOnWholeData(InstanceList ilist, ClassifierTrainer trainer)
throws IOException {
Classifier classifier = trainer.train(ilist);
String outputFilename = "Models/" + classifier.toString();
saveClassifier(classifier, new File(outputFilename));
}
// in the training feature table
// Lines should be formatted as:
//
// [name] [label] [data ... ]
//
public static Classifier TrainMaxent(String trainingFilename, File modelFile) throws IOException {
// build data input pipe
ArrayList<Pipe> pipes = new ArrayList<Pipe>();
// define pipe
// the features in [data ...] should like: feature:value
pipes.add(new Target2Label());
pipes.add(new Csv2FeatureVector());
Pipe pipe = new SerialPipes(pipes);
pipe.setTargetProcessing(true);
// read data
InstanceList trainingInstances = new InstanceList(pipe);
FileReader training_file_reader = new FileReader(trainingFilename);
CsvIterator reader =
new CsvIterator(
training_file_reader,
"(\\w+)\\s+([^\\s]+)\\s+(.*)",
3,
2,
1); // (data, label, name) field indices
trainingInstances.addThruPipe(reader);
training_file_reader.close();
// calculate running time
long startTime = System.currentTimeMillis();
PrintStream temp = System.err;
System.setErr(System.out);
// train a Maxent classifier (could be other classifiers)
ClassifierTrainer trainer = new MaxEntTrainer(Gaussian_Variance);
Classifier classifier = trainer.train(trainingInstances);
System.setErr(temp);
// calculate running time
long endTime = System.currentTimeMillis();
long totalTime = endTime - startTime;
System.out.println("Total training time: " + totalTime);
// write model
ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(modelFile));
oos.writeObject(classifier);
oos.close();
return classifier;
}
public Classifier train(InstanceList trainingInstances, InstanceList testingInstances) {
classifier = trainer.train(trainingInstances);
printPerformance(trainingInstances, "Training\n=======");
if (testingInstances != null) {
printPerformance(testingInstances, "Testing\n=======");
}
return classifier;
}
public void trainClassifier(File dir, String... args) throws Exception {
InstanceListCreator instanceListCreator = new InstanceListCreator();
InstanceList instanceList = instanceListCreator.createInstanceList(getTrainingDataFile(dir));
instanceList.save(new File(dir, "training-data.ser"));
String factoryName = args[0];
Class<ClassifierTrainerFactory<?>> factoryClass = createTrainerFactory(factoryName);
if (factoryClass == null) {
String factoryName2 = "org.cleartk.ml.mallet.factory." + factoryName + "TrainerFactory";
factoryClass = createTrainerFactory(factoryName2);
}
if (factoryClass == null) {
throw new IllegalArgumentException(
String.format(
"name for classifier trainer factory is not valid: name given ='%s'. Valid classifier names include: %s, %s, %s, and %s",
factoryName,
ClassifierTrainerFactory.NAMES[0],
ClassifierTrainerFactory.NAMES[1],
ClassifierTrainerFactory.NAMES[2],
ClassifierTrainerFactory.NAMES[3]));
}
String[] factoryArgs = new String[args.length - 1];
System.arraycopy(args, 1, factoryArgs, 0, factoryArgs.length);
ClassifierTrainerFactory<?> factory = factoryClass.newInstance();
ClassifierTrainer<?> trainer = null;
try {
trainer = factory.createTrainer(factoryArgs);
} catch (Throwable t) {
throw new IllegalArgumentException(
"Unable to create trainer. Usage for "
+ factoryClass.getCanonicalName()
+ ": "
+ factory.getUsageMessage(),
t);
}
this.classifier = trainer.train(instanceList);
ObjectOutputStream oos =
new ObjectOutputStream(new FileOutputStream(new File(dir, MODEL_NAME)));
oos.writeObject(classifier);
oos.close();
}
public Classifier train(InstanceList trainingInstances) {
classifier = trainer.train(trainingInstances);
writeExtremeFeatures();
return classifier;
}
public static ArrayList<Double> getAverageCrossValidationScore(
InstanceList ilist, int i, ClassifierTrainer trainer) {
double crossValidAccSum = 0;
double crossValidPrcSum = 0;
double crossValidRecSum = 0;
double crossValidF1Sum = 0;
int count = 0;
// get gross validation folds
CrossValidationIterator cvIlists = ilist.crossValidationIterator(i);
while (cvIlists.hasNext()) {
System.out.println("#############Performing " + count + " iteration###########");
InstanceList[] ilists = cvIlists.next();
System.out.println("The train set size is " + ilists[0].size());
System.out.println("The test set size is " + ilists[1].size());
Classifier classifier = trainer.train(ilists[0]);
System.out.println("The training accuracy is " + classifier.getAccuracy(ilists[0]));
System.out.println("The testing accuracy is " + classifier.getAccuracy(ilists[1]));
System.out.println("The testing precision is " + classifier.getPrecision(ilists[1], 1));
System.out.println("The testing recall is " + classifier.getRecall(ilists[1], 1));
System.out.println("The testing f1score is " + classifier.getF1(ilists[1], 1));
crossValidAccSum += classifier.getAccuracy(ilists[1]);
crossValidPrcSum += classifier.getPrecision(ilists[1], 1);
crossValidRecSum += classifier.getRecall(ilists[1], 1);
crossValidF1Sum += classifier.getF1(ilists[1], 1);
count++;
// additional calculations
ArrayList<Classification> outClassifications = classifier.classify(ilists[1]);
int p1l1 = 0;
int p1l0 = 0;
int p0l1 = 0;
int p0l0 = 0;
int countCorrect = 0;
int countIncorrect = 0;
System.out.println("Outclassification size " + outClassifications.size());
for (int k = 0; k < outClassifications.size(); k++) {
// System.out.println("Data "+outClassifications.get(k).getInstance().getName());
// System.out.println("Labeling "+outClassifications.get(k).getLabeling()); uncomment to get
// score
double predictedLabel = outClassifications.get(k).getLabeling().getBestIndex();
// System.out.println("Predicted label "+ predictedLabel);
double targetLabel =
Double.valueOf(outClassifications.get(k).getInstance().getTarget().toString());
// System.out.println("Target "+ targetLabel);
boolean bestlabelIsCorrect = outClassifications.get(k).bestLabelIsCorrect();
// System.out.println("Prediction "+bestlabelIsCorrect);
if (bestlabelIsCorrect) countCorrect++;
else countIncorrect++;
if ((predictedLabel == 1.0) && (targetLabel == 1.0)) p1l1++;
else if ((predictedLabel == 1.0) && (targetLabel == 0.0)) p1l0++;
else if ((predictedLabel == 0.0) && (targetLabel == 1.0)) p0l1++;
else if ((predictedLabel == 0.0) && (targetLabel == 0.0)) p0l0++;
}
System.out.println("Count Correct " + countCorrect);
System.out.println("Count Incorrect " + countIncorrect);
System.out.println("p1l1 " + p1l1);
System.out.println("p1l0 " + p1l0);
System.out.println("p0l1 " + p0l1);
System.out.println("p0l0 " + p0l0);
}
ArrayList<Double> results = new ArrayList<Double>();
double crossValidAccAvg = crossValidAccSum / count;
double crossValidPrcAvg = crossValidPrcSum / count;
double crossValidRecAvg = crossValidRecSum / count;
double crossValidF1Avg = crossValidF1Sum / count;
results.add(crossValidAccAvg);
results.add(crossValidPrcAvg);
results.add(crossValidRecAvg);
results.add(crossValidF1Avg);
return results;
}