Examples with DataSetType edu.neu.ccs.pyramid.dataset.DataSetType used on opensource projects

Example 6 with DataSetType

use of edu.neu.ccs.pyramid.dataset.DataSetType in project pyramid by cheng-li.

the class GBRegressor method train.

private static void train(Config config) throws Exception {
    String sparsity = config.getString("input.matrixType");
    DataSetType dataSetType = null;
    switch(sparsity) {
        case "dense":
            dataSetType = DataSetType.REG_DENSE;
            break;
        case "sparse":
            dataSetType = DataSetType.REG_SPARSE;
            break;
        default:
            throw new IllegalArgumentException("input.matrixType should be dense or sparse");
    }
    RegDataSet trainSet = TRECFormat.loadRegDataSet(config.getString("input.trainData"), dataSetType, true);
    RegDataSet testSet = null;
    if (config.getBoolean("train.showTestProgress")) {
        testSet = TRECFormat.loadRegDataSet(config.getString("input.testData"), dataSetType, true);
    }
    LSBoost lsBoost = new LSBoost();
    RegTreeConfig regTreeConfig = new RegTreeConfig().setMaxNumLeaves(config.getInt("train.numLeaves"));
    RegTreeFactory regTreeFactory = new RegTreeFactory(regTreeConfig);
    LSBoostOptimizer optimizer = new LSBoostOptimizer(lsBoost, trainSet, regTreeFactory);
    optimizer.setShrinkage(config.getDouble("train.shrinkage"));
    optimizer.initialize();
    int progressInterval = config.getInt("train.showProgress.interval");
    int numIterations = config.getInt("train.numIterations");
    for (int i = 1; i <= numIterations; i++) {
        System.out.println("iteration " + i);
        optimizer.iterate();
        if (config.getBoolean("train.showTrainProgress") && (i % progressInterval == 0 || i == numIterations)) {
            System.out.println("training RMSE = " + RMSE.rmse(lsBoost, trainSet));
        }
        if (config.getBoolean("train.showTestProgress") && (i % progressInterval == 0 || i == numIterations)) {
            System.out.println("test RMSE = " + RMSE.rmse(lsBoost, testSet));
        }
    }
    System.out.println("training done!");
    String output = config.getString("output.folder");
    new File(output).mkdirs();
    File serializedModel = new File(output, "model");
    Serialization.serialize(lsBoost, serializedModel);
    System.out.println("model saved to " + serializedModel.getAbsolutePath());
    File reportFile = new File(output, "train_predictions.txt");
    report(lsBoost, trainSet, reportFile);
    System.out.println("predictions on the training set are written to " + reportFile.getAbsolutePath());
}

Example 7 with DataSetType

use of edu.neu.ccs.pyramid.dataset.DataSetType in project pyramid by cheng-li.

the class GBRegressor method test.

private static void test(Config config, Logger logger) throws Exception {
    String output = config.getString("output.folder");
    File serializedModel = new File(output, "model");
    LSBoost lsBoost = (LSBoost) Serialization.deserialize(serializedModel);
    String sparsity = config.getString("input.matrixType");
    DataSetType dataSetType = null;
    switch(sparsity) {
        case "dense":
            dataSetType = DataSetType.REG_DENSE;
            break;
        case "sparse":
            dataSetType = DataSetType.REG_SPARSE;
            break;
        default:
            throw new IllegalArgumentException("input.matrixType should be dense or sparse");
    }
    RegDataSet testSet = TRECFormat.loadRegDataSet(config.getString("input.testData"), dataSetType, true);
    logger.info("test RMSE = " + RMSE.rmse(lsBoost, testSet));
    String testReportName = config.getString("output.testReportFolderName");
    File reportFile = Paths.get(output, testReportName, "test_predictions.txt").toFile();
    report(lsBoost, testSet, reportFile);
    logger.info("predictions on the test set are written to " + reportFile.getAbsolutePath());
}