Examples with LogisticRegressionSGDTrainer org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer used on opensource projects

Example 1 with LogisticRegressionSGDTrainer

use of org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer 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 LogisticRegressionSGDTrainer

use of org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer in project ignite by apache.

the class FraudDetectionExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = null;
        try {
            System.out.println(">>> Fill dataset cache.");
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.FRAUD_DETECTION);
            // This vectorizer works with values in cache of Vector class.
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(// LAST means "label are stored at last coordinate of vector"
            Vectorizer.LabelCoordinate.LAST);
            // Splits dataset to train and test samples with 80/20 proportion.
            TrainTestSplit<Integer, Vector> split = new TrainTestDatasetSplitter<Integer, Vector>().split(0.8);
            System.out.println(">>> Perform logistic regression.");
            trainAndEstimateModel(ignite, dataCache, new LogisticRegressionSGDTrainer().withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(0)), vectorizer, split);
            System.out.println("\n\n>>> Perform decision tree classifier.");
            trainAndEstimateModel(ignite, dataCache, new DecisionTreeClassificationTrainer().withMaxDeep(10.).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(0)), vectorizer, split);
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 3 with LogisticRegressionSGDTrainer

use of org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer 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 LogisticRegressionSGDTrainer

use of org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer 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);
}

Example 5 with LogisticRegressionSGDTrainer

use of org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer in project ignite by apache.

the class BaggedLogisticRegressionSGDTrainerExample 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(100).withLocIterations(10).withBatchSize(10).withSeed(123L);
            System.out.println(">>> Perform the training to get the model.");
            BaggedTrainer<Double> baggedTrainer = TrainerTransformers.makeBagged(trainer, 10, 0.6, 4, 3, new OnMajorityPredictionsAggregator()).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(1));
            System.out.println(">>> Perform evaluation of the model.");
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            double accuracy = Evaluator.evaluate(dataCache, baggedTrainer.fit(ignite, dataCache, vectorizer), vectorizer, MetricName.ACCURACY);
            System.out.println(">>> ---------------------------------");
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println(">>> Bagged logistic regression model over partitioned dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}