use of org.tribuo.ImmutableDataset in project tribuo by oracle.
the class TestXGBoost method loadDataset.
private Dataset<Label> loadDataset(XGBoostModel<Label> model, Path path) throws IOException {
TextFeatureExtractor<Label> extractor = new TextFeatureExtractorImpl<>(new BasicPipeline(new BreakIteratorTokenizer(Locale.US), 2));
TextDataSource<Label> src = new SimpleTextDataSource<>(path, new LabelFactory(), extractor);
return new ImmutableDataset<>(src, model.getFeatureIDMap(), model.getOutputIDInfo(), false);
}
use of org.tribuo.ImmutableDataset in project tribuo by oracle.
the class DataOptions method load.
/**
* Loads the training and testing data from {@link #trainingPath} and {@link #testingPath}
* according to the other parameters specified in this class.
* @param outputFactory The output factory to use to process the inputs.
* @param <T> The dataset output type.
* @return A pair containing the training and testing datasets. The training dataset is element 'A' and the
* testing dataset is element 'B'.
* @throws IOException If the paths could not be loaded.
*/
public <T extends Output<T>> Pair<Dataset<T>, Dataset<T>> load(OutputFactory<T> outputFactory) throws IOException {
logger.info(String.format("Loading data from %s", trainingPath));
Dataset<T> train;
Dataset<T> test;
char separator;
switch(inputFormat) {
case SERIALIZED:
//
// Load Tribuo serialised datasets.
logger.info("Deserialising dataset from " + trainingPath);
try (ObjectInputStream ois = new ObjectInputStream(new BufferedInputStream(new FileInputStream(trainingPath.toFile())));
ObjectInputStream oits = new ObjectInputStream(new BufferedInputStream(new FileInputStream(testingPath.toFile())))) {
@SuppressWarnings("unchecked") Dataset<T> tmp = (Dataset<T>) ois.readObject();
train = tmp;
if (minCount > 0) {
logger.info("Found " + train.getFeatureIDMap().size() + " features");
logger.info("Removing features that occur fewer than " + minCount + " times.");
train = new MinimumCardinalityDataset<>(train, minCount);
}
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
@SuppressWarnings("unchecked") Dataset<T> deserTest = (Dataset<T>) oits.readObject();
test = new ImmutableDataset<>(deserTest, deserTest.getSourceProvenance(), deserTest.getOutputFactory(), train.getFeatureIDMap(), train.getOutputIDInfo(), true);
} catch (ClassNotFoundException e) {
throw new IllegalArgumentException("Unknown class in serialised files", e);
}
break;
case LIBSVM:
//
// Load the libsvm text-based data format.
LibSVMDataSource<T> trainSVMSource = new LibSVMDataSource<>(trainingPath, outputFactory);
train = new MutableDataset<>(trainSVMSource);
boolean zeroIndexed = trainSVMSource.isZeroIndexed();
int maxFeatureID = trainSVMSource.getMaxFeatureID();
if (minCount > 0) {
logger.info("Removing features that occur fewer than " + minCount + " times.");
train = new MinimumCardinalityDataset<>(train, minCount);
}
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
test = new ImmutableDataset<>(new LibSVMDataSource<>(testingPath, outputFactory, zeroIndexed, maxFeatureID), train.getFeatureIDMap(), train.getOutputIDInfo(), false);
break;
case TEXT:
//
// Using a simple Java break iterator to generate ngram features.
TextFeatureExtractor<T> extractor;
if (hashDim > 0) {
extractor = new TextFeatureExtractorImpl<>(new TokenPipeline(new BreakIteratorTokenizer(Locale.US), ngram, termCounting, hashDim));
} else {
extractor = new TextFeatureExtractorImpl<>(new TokenPipeline(new BreakIteratorTokenizer(Locale.US), ngram, termCounting));
}
TextDataSource<T> trainSource = new SimpleTextDataSource<>(trainingPath, outputFactory, extractor);
train = new MutableDataset<>(trainSource);
if (minCount > 0) {
logger.info("Removing features that occur fewer than " + minCount + " times.");
train = new MinimumCardinalityDataset<>(train, minCount);
}
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
TextDataSource<T> testSource = new SimpleTextDataSource<>(testingPath, outputFactory, extractor);
test = new ImmutableDataset<>(testSource, train.getFeatureIDMap(), train.getOutputIDInfo(), false);
break;
case CSV:
// Load the data using the simple CSV loader
if (csvResponseName == null) {
throw new IllegalArgumentException("Please supply a response column name");
}
separator = delimiter.value;
CSVLoader<T> loader = new CSVLoader<>(separator, outputFactory);
train = new MutableDataset<>(loader.loadDataSource(trainingPath, csvResponseName));
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
test = new MutableDataset<>(loader.loadDataSource(testingPath, csvResponseName));
break;
case COLUMNAR:
if (rowProcessor == null) {
throw new IllegalArgumentException("Please supply a RowProcessor");
}
OutputFactory<?> rowOutputFactory = rowProcessor.getResponseProcessor().getOutputFactory();
if (!rowOutputFactory.equals(outputFactory)) {
throw new IllegalArgumentException("The RowProcessor doesn't use the same kind of OutputFactory as the one supplied. RowProcessor has " + rowOutputFactory.getClass().getSimpleName() + ", supplied " + outputFactory.getClass().getName());
}
// checked by the if statement above
@SuppressWarnings("unchecked") RowProcessor<T> typedRowProcessor = (RowProcessor<T>) rowProcessor;
separator = delimiter.value;
train = new MutableDataset<>(new CSVDataSource<>(trainingPath, typedRowProcessor, true, separator, csvQuoteChar));
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
test = new MutableDataset<>(new CSVDataSource<>(testingPath, typedRowProcessor, true, separator, csvQuoteChar));
break;
default:
throw new IllegalArgumentException("Unsupported input format " + inputFormat);
}
logger.info(String.format("Loaded %d testing examples", test.size()));
if (scaleFeatures) {
logger.info("Fitting feature scaling");
TransformationMap map = new TransformationMap(Collections.singletonList(new LinearScalingTransformation()));
TransformerMap transformers = train.createTransformers(map, scaleIncZeros);
logger.info("Applying scaling to training dataset");
train = transformers.transformDataset(train);
logger.info("Applying scaling to testing dataset");
test = transformers.transformDataset(test);
}
return new Pair<>(train, test);
}
use of org.tribuo.ImmutableDataset in project tribuo by oracle.
the class TestLibLinearModel method loadDataset.
private Dataset<Label> loadDataset(LibLinearClassificationModel model, Path path) throws IOException {
TextFeatureExtractor<Label> extractor = new TextFeatureExtractorImpl<>(new BasicPipeline(new BreakIteratorTokenizer(Locale.US), 2));
TextDataSource<Label> src = new SimpleTextDataSource<>(path, new LabelFactory(), extractor);
return new ImmutableDataset<>(src, model.getFeatureIDMap(), model.getOutputIDInfo(), false);
}
use of org.tribuo.ImmutableDataset in project tribuo by oracle.
the class MNISTDemo method main.
public static void main(String[] args) throws IOException {
//
// Use the labs format logging.
LabsLogFormatter.setAllLogFormatters();
LabelFactory labelFactory = new LabelFactory();
logger.info("Loading training data.");
//
// Load the libsvm text-based data format.
LibSVMDataSource<Label> trainSource = new LibSVMDataSource<>(new File(args[0]).toPath(), labelFactory);
MutableDataset<Label> train = new MutableDataset<>(trainSource);
boolean zeroIndexed = trainSource.isZeroIndexed();
int maxFeatureID = trainSource.getMaxFeatureID();
logger.info(String.format("Loaded %d training examples for %s", train.size(), train.getOutputs().toString()));
logger.info("Found " + train.getFeatureIDMap().size() + " features, and " + train.getOutputInfo().size() + " response dimensions");
LibSVMDataSource<Label> testSource = new LibSVMDataSource<>(new File(args[1]).toPath(), labelFactory, zeroIndexed, maxFeatureID);
ImmutableDataset<Label> test = new ImmutableDataset<>(testSource, train.getFeatureIDMap(), train.getOutputIDInfo(), false);
logger.info(String.format("Loaded %d testing examples", test.size()));
// public XGBoostClassificationTrainer(int numTrees, double eta, double gamma, int maxDepth, double minChildWeight, double subsample, double featureSubsample, double lambda, double alpha, long seed) {
XGBoostClassificationTrainer trainer = new XGBoostClassificationTrainer(50);
Model<Label> model = trainer.train(train);
logger.info("Finished training model");
// SparseTrainer<Regressor> limeTrainer = new LARSLassoTrainer(numFeatures);
SparseTrainer<Regressor> limeTrainer = new CARTJointRegressionTrainer((int) (Math.log(numFeatures) / Math.log(2)));
LIMEBase lime = new LIMEBase(new SplittableRandom(1), model, limeTrainer, 200);
LIMEExplanation e = lime.explain(test.getData().get(0));
logger.info("Finished lime");
logger.info("Explanation = " + e.toString());
LabelEvaluator labelEvaluator = new LabelEvaluator();
LabelEvaluation evaluation = labelEvaluator.evaluate(model, test);
logger.info("Finished evaluating model");
System.out.println(labelEvaluator.toString());
System.out.println();
ConfusionMatrix<Label> matrix = evaluation.getConfusionMatrix();
System.out.println(matrix.toString());
}
use of org.tribuo.ImmutableDataset in project tribuo by oracle.
the class TestLibSVM method testOnnxSerialization.
@Test
public void testOnnxSerialization() throws IOException, OrtException {
Pair<Dataset<Label>, Dataset<Label>> binary = LabelledDataGenerator.binarySparseTrainTest();
Map<Label, Integer> mapping = new HashMap<>();
mapping.put(new Label("Foo"), 0);
mapping.put(new Label("Bar"), 1);
ImmutableOutputInfo<Label> newInfo = new LabelFactory().constructInfoForExternalModel(mapping);
ImmutableDataset<Label> newTrain = ImmutableDataset.copyDataset(binary.getA(), binary.getA().getFeatureIDMap(), newInfo);
ImmutableDataset<Label> newTest = ImmutableDataset.copyDataset(binary.getB(), binary.getA().getFeatureIDMap(), newInfo);
testOnnxSerialization(new Pair<>(newTrain, newTest), C_LINEAR);
testOnnxSerialization(binary, C_LINEAR);
testOnnxSerialization(binary, C_RBF);
testOnnxSerialization(binary, NU_LINEAR);
testOnnxSerialization(binary, NU_RBF);
SVMParameters<Label> params = new SVMParameters<>(new SVMClassificationType(SVMMode.NU_SVC), KernelType.RBF);
params.setProbability();
LibSVMClassificationTrainer probTrainer = new LibSVMClassificationTrainer(params);
testOnnxSerialization(binary, probTrainer);
}
Aggregations