Examples with SimpleGDUpdateCalculator org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator used on opensource projects

Example 1 with SimpleGDUpdateCalculator

use of org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator in project ignite by apache.

the class Step_9_Scaling_With_Stacking method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 9 (scaling with stacking) example started.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Vector> dataCache = TitanicUtils.readPassengers(ignite);
            // Extracts "pclass", "sibsp", "parch", "sex", "embarked", "age", "fare".
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 3, 4, 5, 6, 8, 10).labeled(1);
            TrainTestSplit<Integer, Vector> split = new TrainTestDatasetSplitter<Integer, Vector>().split(0.75);
            Preprocessor<Integer, Vector> strEncoderPreprocessor = new EncoderTrainer<Integer, Vector>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(1).withEncodedFeature(// <--- Changed index here.
            6).fit(ignite, dataCache, vectorizer);
            Preprocessor<Integer, Vector> imputingPreprocessor = new ImputerTrainer<Integer, Vector>().fit(ignite, dataCache, strEncoderPreprocessor);
            Preprocessor<Integer, Vector> minMaxScalerPreprocessor = new MinMaxScalerTrainer<Integer, Vector>().fit(ignite, dataCache, imputingPreprocessor);
            Preprocessor<Integer, Vector> normalizationPreprocessor = new NormalizationTrainer<Integer, Vector>().withP(1).fit(ignite, dataCache, minMaxScalerPreprocessor);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            DecisionTreeClassificationTrainer trainer1 = new DecisionTreeClassificationTrainer(3, 0);
            DecisionTreeClassificationTrainer trainer2 = new DecisionTreeClassificationTrainer(4, 0);
            LogisticRegressionSGDTrainer aggregator = new LogisticRegressionSGDTrainer().withUpdatesStgy(new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG));
            StackedModel<Vector, Vector, Double, LogisticRegressionModel> mdl = new StackedVectorDatasetTrainer<>(aggregator).addTrainerWithDoubleOutput(trainer).addTrainerWithDoubleOutput(trainer1).addTrainerWithDoubleOutput(trainer2).fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), mdl, normalizationPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 9 (scaling with stacking) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 2 with SimpleGDUpdateCalculator

use of org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator in project ignite by apache.

the class MLPTrainerExample method main.

/**
 * Executes example.
 *
 * @param args Command line arguments, none required.
 */
public static void main(String[] args) {
    // IMPL NOTE based on MLPGroupTrainerTest#testXOR
    System.out.println(">>> Distributed multilayer perceptron 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, LabeledVector<double[]>> trainingSetCfg = new CacheConfiguration<>();
        trainingSetCfg.setName("TRAINING_SET");
        trainingSetCfg.setAffinity(new RendezvousAffinityFunction(false, 10));
        IgniteCache<Integer, LabeledVector<double[]>> trainingSet = null;
        try {
            trainingSet = ignite.createCache(trainingSetCfg);
            // Fill cache with training data.
            trainingSet.put(0, new LabeledVector<>(VectorUtils.of(0, 0), new double[] { 0 }));
            trainingSet.put(1, new LabeledVector<>(VectorUtils.of(0, 1), new double[] { 1 }));
            trainingSet.put(2, new LabeledVector<>(VectorUtils.of(1, 0), new double[] { 1 }));
            trainingSet.put(3, new LabeledVector<>(VectorUtils.of(1, 1), new double[] { 0 }));
            // Define a layered architecture.
            MLPArchitecture arch = new MLPArchitecture(2).withAddedLayer(10, true, Activators.RELU).withAddedLayer(1, false, Activators.SIGMOID);
            // Define a neural network trainer.
            MLPTrainer<SimpleGDParameterUpdate> trainer = new MLPTrainer<>(arch, LossFunctions.MSE, new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.1), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG), 3000, 4, 50, 123L);
            // Train neural network and get multilayer perceptron model.
            MultilayerPerceptron mlp = trainer.fit(ignite, trainingSet, new LabeledDummyVectorizer<>());
            int totalCnt = 4;
            int failCnt = 0;
            // Calculate score.
            for (int i = 0; i < 4; i++) {
                LabeledVector<double[]> pnt = trainingSet.get(i);
                Matrix predicted = mlp.predict(new DenseMatrix(new double[][] { { pnt.features().get(0), pnt.features().get(1) } }));
                double predictedVal = predicted.get(0, 0);
                double lbl = pnt.label()[0];
                System.out.printf(">>> key: %d\t\t predicted: %.4f\t\tlabel: %.4f\n", i, predictedVal, lbl);
                failCnt += Math.abs(predictedVal - lbl) < 0.5 ? 0 : 1;
            }
            double failRatio = (double) failCnt / totalCnt;
            System.out.println("\n>>> Fail percentage: " + (failRatio * 100) + "%.");
            System.out.println("\n>>> Distributed multilayer perceptron example completed.");
        } finally {
            trainingSet.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 3 with SimpleGDUpdateCalculator

use of org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator in project ignite by apache.

the class LogisticRegressionSGDTrainerExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> Logistic regression model over partitioned dataset usage example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = null;
        try {
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.TWO_CLASSED_IRIS);
            System.out.println(">>> Create new logistic regression trainer object.");
            LogisticRegressionSGDTrainer trainer = new LogisticRegressionSGDTrainer().withUpdatesStgy(new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG)).withMaxIterations(100000).withLocIterations(100).withBatchSize(10).withSeed(123L);
            System.out.println(">>> Perform the training to get the model.");
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            LogisticRegressionModel mdl = trainer.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> Logistic regression model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, MetricName.ACCURACY);
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println(">>> Logistic regression model over partitioned dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 4 with SimpleGDUpdateCalculator

use of org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator in project ignite by apache.

the class StackingTest method testSimpleStack.

/**
 * Tests simple stack training.
 */
@Test
public void testSimpleStack() {
    StackedDatasetTrainer<Vector, Vector, Double, LinearRegressionModel, Double> trainer = new StackedDatasetTrainer<>();
    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);
    MLPTrainer<SimpleGDParameterUpdate> trainer1 = new MLPTrainer<>(arch, LossFunctions.MSE, updatesStgy, 3000, 10, 50, 123L);
    // Convert model trainer to produce Vector -> Vector model
    DatasetTrainer<AdaptableDatasetModel<Vector, Vector, Matrix, Matrix, MultilayerPerceptron>, Double> mlpTrainer = AdaptableDatasetTrainer.of(trainer1).beforeTrainedModel((Vector v) -> new DenseMatrix(v.asArray(), 1)).afterTrainedModel((Matrix mtx) -> mtx.getRow(0)).withConvertedLabels(VectorUtils::num2Arr);
    final double factor = 3;
    StackedModel<Vector, Vector, Double, LinearRegressionModel> mdl = trainer.withAggregatorTrainer(new LinearRegressionLSQRTrainer().withConvertedLabels(x -> x * factor)).addTrainer(mlpTrainer).withAggregatorInputMerger(VectorUtils::concat).withSubmodelOutput2VectorConverter(IgniteFunction.identity()).withVector2SubmodelInputConverter(IgniteFunction.identity()).withOriginalFeaturesKept(IgniteFunction.identity()).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 5 with SimpleGDUpdateCalculator

use of org.apache.ignite.ml.optimization.updatecalculators.SimpleGDUpdateCalculator in project ignite by apache.

the class CrossValidationTest method testGridSearch.

/**
 */
@Test
public void testGridSearch() {
    Map<Integer, double[]> data = new HashMap<>();
    for (int i = 0; i < twoLinearlySeparableClasses.length; i++) data.put(i, twoLinearlySeparableClasses[i]);
    LogisticRegressionSGDTrainer trainer = new LogisticRegressionSGDTrainer().withUpdatesStgy(new UpdatesStrategy<>(new SimpleGDUpdateCalculator(0.2), SimpleGDParameterUpdate.SUM_LOCAL, SimpleGDParameterUpdate.AVG)).withMaxIterations(100000).withLocIterations(100).withBatchSize(14).withSeed(123L);
    Vectorizer<Integer, double[], Integer, Double> vectorizer = new DoubleArrayVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
    ParamGrid paramGrid = new ParamGrid().addHyperParam("maxIterations", trainer::withMaxIterations, new Double[] { 10.0, 100.0, 1000.0, 10000.0 }).addHyperParam("locIterations", trainer::withLocIterations, new Double[] { 10.0, 100.0, 1000.0, 10000.0 }).addHyperParam("batchSize", trainer::withBatchSize, new Double[] { 1.0, 2.0, 4.0, 8.0, 16.0 });
    DebugCrossValidation<LogisticRegressionModel, Integer, double[]> scoreCalculator = (DebugCrossValidation<LogisticRegressionModel, Integer, double[]>) new DebugCrossValidation<LogisticRegressionModel, Integer, double[]>().withUpstreamMap(data).withAmountOfParts(1).withTrainer(trainer).withMetric(MetricName.ACCURACY).withPreprocessor(vectorizer).withAmountOfFolds(4).isRunningOnPipeline(false).withParamGrid(paramGrid);
    CrossValidationResult crossValidationRes = scoreCalculator.tuneHyperParameters();
    assertArrayEquals(crossValidationRes.getBestScore(), new double[] { 0.9745762711864406, 1.0, 0.8968253968253969, 0.8661417322834646 }, 1e-6);
    assertEquals(crossValidationRes.getBestAvgScore(), 0.9343858500738256, 1e-6);
    assertEquals(crossValidationRes.getScoringBoard().size(), 80);
}