Examples with SimpleTextDataSource org.tribuo.data.text.impl.SimpleTextDataSource used on opensource projects

Example 1 with SimpleTextDataSource

use of org.tribuo.data.text.impl.SimpleTextDataSource 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);
}

Example 2 with SimpleTextDataSource

use of org.tribuo.data.text.impl.SimpleTextDataSource 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);
}

Example 3 with SimpleTextDataSource

use of org.tribuo.data.text.impl.SimpleTextDataSource 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);
}

Example 4 with SimpleTextDataSource

use of org.tribuo.data.text.impl.SimpleTextDataSource in project tribuo by oracle.

the class TestLibSVM method loadDataset.

private Dataset<Label> loadDataset(LibSVMModel<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);
}

Example 5 with SimpleTextDataSource

use of org.tribuo.data.text.impl.SimpleTextDataSource in project tribuo by oracle.

the class Test method load.

/**
 * Loads in the model and the dataset from the options.
 * @param o The options.
 * @return The model and the dataset.
 * @throws IOException If either the model or dataset could not be read.
 */
// deserialising generically typed datasets.
@SuppressWarnings("unchecked")
public static Pair<Model<Label>, Dataset<Label>> load(ConfigurableTestOptions o) throws IOException {
    Path modelPath = o.modelPath;
    Path datasetPath = o.testingPath;
    logger.info(String.format("Loading model from %s", modelPath));
    Model<Label> model;
    try (ObjectInputStream mois = new ObjectInputStream(new BufferedInputStream(new FileInputStream(modelPath.toFile())))) {
        model = (Model<Label>) mois.readObject();
        boolean valid = model.validate(Label.class);
        if (!valid) {
            throw new ClassCastException("Failed to cast deserialised Model to Model<Label>");
        }
    } catch (ClassNotFoundException e) {
        throw new IllegalArgumentException("Unknown class in serialised model", e);
    }
    logger.info(String.format("Loading data from %s", datasetPath));
    Dataset<Label> test;
    switch(o.inputFormat) {
        case SERIALIZED:
            // 
            // Load Tribuo serialised datasets.
            logger.info("Deserialising dataset from " + datasetPath);
            try (ObjectInputStream oits = new ObjectInputStream(new BufferedInputStream(new FileInputStream(datasetPath.toFile())))) {
                Dataset<Label> deserTest = (Dataset<Label>) oits.readObject();
                test = ImmutableDataset.copyDataset(deserTest, model.getFeatureIDMap(), model.getOutputIDInfo());
                logger.info(String.format("Loaded %d testing examples for %s", test.size(), test.getOutputs().toString()));
            } catch (ClassNotFoundException e) {
                throw new IllegalArgumentException("Unknown class in serialised dataset", e);
            }
            break;
        case LIBSVM:
            // 
            // Load the libsvm text-based data format.
            boolean zeroIndexed = o.zeroIndexed;
            int maxFeatureID = model.getFeatureIDMap().size() - 1;
            LibSVMDataSource<Label> testSVMSource = new LibSVMDataSource<>(datasetPath, new LabelFactory(), zeroIndexed, maxFeatureID);
            test = new ImmutableDataset<>(testSVMSource, model, true);
            logger.info(String.format("Loaded %d training examples for %s", test.size(), test.getOutputs().toString()));
            break;
        case TEXT:
            // 
            // Using a simple Java break iterator to generate ngram features.
            TextFeatureExtractor<Label> extractor;
            if (o.hashDim > 0) {
                extractor = new TextFeatureExtractorImpl<>(new TokenPipeline(new BreakIteratorTokenizer(Locale.US), o.ngram, o.termCounting, o.hashDim));
            } else {
                extractor = new TextFeatureExtractorImpl<>(new TokenPipeline(new BreakIteratorTokenizer(Locale.US), o.ngram, o.termCounting));
            }
            TextDataSource<Label> testSource = new SimpleTextDataSource<>(datasetPath, new LabelFactory(), extractor);
            test = new ImmutableDataset<>(testSource, model.getFeatureIDMap(), model.getOutputIDInfo(), true);
            logger.info(String.format("Loaded %d testing examples for %s", test.size(), test.getOutputs().toString()));
            break;
        case CSV:
            // Load the data using the simple CSV loader
            if (o.csvResponseName == null) {
                throw new IllegalArgumentException("Please supply a response column name");
            }
            CSVLoader<Label> loader = new CSVLoader<>(new LabelFactory());
            test = new ImmutableDataset<>(loader.loadDataSource(datasetPath, o.csvResponseName), model.getFeatureIDMap(), model.getOutputIDInfo(), true);
            logger.info(String.format("Loaded %d testing examples for %s", test.size(), test.getOutputs().toString()));
            break;
        default:
            throw new IllegalArgumentException("Unsupported input format " + o.inputFormat);
    }
    return new Pair<>(model, test);
}