Examples with DoubleArrayVectorizer org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer used on opensource projects

Example 16 with DoubleArrayVectorizer

use of org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer in project ignite by apache.

the class GDBOnTreesRegressionExportImportExample method main.

/**
 * Run example.
 *
 * @param args Command line arguments, none required.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> GDB regression trainer example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        // Create cache with training data.
        CacheConfiguration<Integer, double[]> trainingSetCfg = createCacheConfiguration();
        IgniteCache<Integer, double[]> trainingSet = null;
        Path jsonMdlPath = null;
        try {
            trainingSet = fillTrainingData(ignite, trainingSetCfg);
            // Create regression trainer.
            GDBTrainer trainer = new GDBRegressionOnTreesTrainer(1.0, 2000, 1, 0.).withCheckConvergenceStgyFactory(new MeanAbsValueConvergenceCheckerFactory(0.001));
            // Train decision tree model.
            GDBModel mdl = trainer.fit(ignite, trainingSet, new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.LAST));
            System.out.println("\n>>> Exported GDB regression model: " + mdl.toString(true));
            predictOnGeneratedData(mdl);
            jsonMdlPath = Files.createTempFile(null, null);
            mdl.toJSON(jsonMdlPath);
            IgniteFunction<Double, Double> lbMapper = lb -> lb;
            GDBModel modelImportedFromJSON = GDBModel.fromJSON(jsonMdlPath).withLblMapping(lbMapper);
            System.out.println("\n>>> Imported GDB regression model: " + modelImportedFromJSON.toString(true));
            predictOnGeneratedData(modelImportedFromJSON);
            System.out.println(">>> GDB regression trainer example completed.");
        } finally {
            if (trainingSet != null)
                trainingSet.destroy();
            if (jsonMdlPath != null)
                Files.deleteIfExists(jsonMdlPath);
        }
    } finally {
        System.out.flush();
    }
}

Example 17 with DoubleArrayVectorizer

use of org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer in project ignite by apache.

the class RandomForestIntegrationTest method testFit.

/**
 */
@Test
public void testFit() {
    int size = 100;
    CacheConfiguration<Integer, double[]> trainingSetCacheCfg = new CacheConfiguration<>();
    trainingSetCacheCfg.setAffinity(new RendezvousAffinityFunction(false, 10));
    trainingSetCacheCfg.setName("TRAINING_SET");
    IgniteCache<Integer, double[]> data = ignite.createCache(trainingSetCacheCfg);
    Random rnd = new Random(0);
    for (int i = 0; i < size; i++) {
        double x = rnd.nextDouble() - 0.5;
        data.put(i, new double[] { x, x > 0 ? 1 : 0 });
    }
    ArrayList<FeatureMeta> meta = new ArrayList<>();
    meta.add(new FeatureMeta("", 0, false));
    RandomForestRegressionTrainer trainer = new RandomForestRegressionTrainer(meta).withAmountOfTrees(5).withFeaturesCountSelectionStrgy(x -> 2);
    RandomForestModel mdl = trainer.fit(ignite, data, new DoubleArrayVectorizer<Integer>().labeled(1));
    assertTrue(mdl.getPredictionsAggregator() instanceof MeanValuePredictionsAggregator);
    assertEquals(5, mdl.getModels().size());
}

Example 18 with DoubleArrayVectorizer

use of org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer in project ignite by apache.

the class StackingTest method testSimpleVectorStack.

/**
 * Tests simple stack training.
 */
@Test
public void testSimpleVectorStack() {
    StackedVectorDatasetTrainer<Double, LinearRegressionModel, Double> trainer = new StackedVectorDatasetTrainer<>();
    UpdatesStrategy<SmoothParametrized, SimpleGDParameterUpdate> updatesStgy = new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG);
    MLPArchitecture arch = new MLPArchitecture(2).withAddedLayer(10, true, Activators.RELU).withAddedLayer(1, false, Activators.SIGMOID);
    DatasetTrainer<MultilayerPerceptron, Double> mlpTrainer = new MLPTrainer<>(arch, LossFunctions.MSE, updatesStgy, 3000, 10, 50, 123L).withConvertedLabels(VectorUtils::num2Arr);
    final double factor = 3;
    StackedModel<Vector, Vector, Double, LinearRegressionModel> mdl = trainer.withAggregatorTrainer(new LinearRegressionLSQRTrainer().withConvertedLabels(x -> x * factor)).addMatrix2MatrixTrainer(mlpTrainer).withEnvironmentBuilder(TestUtils.testEnvBuilder()).fit(getCacheMock(xor), parts, new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.LAST));
    assertEquals(0.0 * factor, mdl.predict(VectorUtils.of(0.0, 0.0)), 0.3);
    assertEquals(1.0 * factor, mdl.predict(VectorUtils.of(0.0, 1.0)), 0.3);
    assertEquals(1.0 * factor, mdl.predict(VectorUtils.of(1.0, 0.0)), 0.3);
    assertEquals(0.0 * factor, mdl.predict(VectorUtils.of(1.0, 1.0)), 0.3);
}

Example 19 with DoubleArrayVectorizer

use of org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer in project ignite by apache.

the class GDBTrainerTest method testFitRegression.

/**
 */
@Test
public void testFitRegression() {
    int size = 100;
    double[] xs = new double[size];
    double[] ys = new double[size];
    double from = -5.0;
    double to = 5.0;
    double step = Math.abs(from - to) / size;
    Map<Integer, double[]> learningSample = new HashMap<>();
    for (int i = 0; i < size; i++) {
        xs[i] = from + step * i;
        ys[i] = 2 * xs[i];
        learningSample.put(i, new double[] { xs[i], ys[i] });
    }
    GDBTrainer trainer = new GDBRegressionOnTreesTrainer(1.0, 2000, 3, 0.0).withUsingIdx(true);
    IgniteModel<Vector, Double> mdl = trainer.fit(learningSample, 1, new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.LAST));
    double mse = 0.0;
    for (int j = 0; j < size; j++) {
        double x = xs[j];
        double y = ys[j];
        double p = mdl.predict(VectorUtils.of(x));
        mse += Math.pow(y - p, 2);
    }
    mse /= size;
    assertEquals(0.0, mse, 0.0001);
    ModelsComposition composition = (ModelsComposition) mdl;
    assertTrue(!composition.toString().isEmpty());
    assertTrue(!composition.toString(true).isEmpty());
    assertTrue(!composition.toString(false).isEmpty());
    composition.getModels().forEach(m -> assertTrue(m instanceof DecisionTreeModel));
    assertEquals(2000, composition.getModels().size());
    assertTrue(composition.getPredictionsAggregator() instanceof WeightedPredictionsAggregator);
    trainer = trainer.withCheckConvergenceStgyFactory(new MeanAbsValueConvergenceCheckerFactory(0.1));
    assertTrue(trainer.fit(learningSample, 1, new DoubleArrayVectorizer<Integer>().labeled(1)).getModels().size() < 2000);
}

Example 20 with DoubleArrayVectorizer

use of org.apache.ignite.ml.dataset.feature.extractor.impl.DoubleArrayVectorizer in project ignite by apache.

the class BaggingTest method testNaiveBaggingLogRegression.

/**
 * Test that bagged log regression makes correct predictions.
 */
@Test
public void testNaiveBaggingLogRegression() {
    Map<Integer, double[]> cacheMock = getCacheMock(twoLinearlySeparableClasses);
    DatasetTrainer<LogisticRegressionModel, Double> trainer = new LogisticRegressionSGDTrainer().withUpdatesStgy(new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG)).withMaxIterations(30000).withLocIterations(100).withBatchSize(10).withSeed(123L);
    BaggedTrainer<Double> baggedTrainer = TrainerTransformers.makeBagged(trainer, 7, 0.7, 2, 2, new OnMajorityPredictionsAggregator()).withEnvironmentBuilder(TestUtils.testEnvBuilder());
    BaggedModel mdl = baggedTrainer.fit(cacheMock, parts, new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST));
    Vector weights = ((LogisticRegressionModel) ((AdaptableDatasetModel) ((ModelsParallelComposition) ((AdaptableDatasetModel) mdl.model()).innerModel()).submodels().get(0)).innerModel()).weights();
    TestUtils.assertEquals(firstMdlWeights.get(parts), weights, 0.0);
    TestUtils.assertEquals(0, mdl.predict(VectorUtils.of(100, 10)), PRECISION);
    TestUtils.assertEquals(1, mdl.predict(VectorUtils.of(10, 100)), PRECISION);
}