Examples with Vector org.apache.ignite.ml.math.primitives.vector.Vector used on opensource projects

Example 36 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector in project ignite by apache.

the class Step_4_Add_age_fare method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 4 (add age and fare) 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);
            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);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            // Train decision tree model.
            DecisionTreeModel mdl = trainer.fit(ignite, dataCache, imputingPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, imputingPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 4 (add age and fare) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 37 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector in project ignite by apache.

the class Step_7_Split_train_test method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 7 (split to train and test) 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);
            // Train decision tree model.
            DecisionTreeModel mdl = trainer.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 7 (split to train and test) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 38 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector in project ignite by apache.

the class Step_8_CV method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 8 (cross-validation) 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);
            // Tune hyper-parameters with K-fold Cross-Validation on the split training set.
            int[] pSet = new int[] { 1, 2 };
            int[] maxDeepSet = new int[] { 1, 2, 3, 4, 5, 10, 20 };
            int bestP = 1;
            int bestMaxDeep = 1;
            double avg = Double.MIN_VALUE;
            for (int p : pSet) {
                for (int maxDeep : maxDeepSet) {
                    Preprocessor<Integer, Vector> normalizationPreprocessor = new NormalizationTrainer<Integer, Vector>().withP(p).fit(ignite, dataCache, minMaxScalerPreprocessor);
                    DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(maxDeep, 0);
                    CrossValidation<DecisionTreeModel, Integer, Vector> scoreCalculator = new CrossValidation<>();
                    double[] scores = scoreCalculator.withIgnite(ignite).withUpstreamCache(dataCache).withTrainer(trainer).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).withPreprocessor(normalizationPreprocessor).withAmountOfFolds(3).isRunningOnPipeline(false).scoreByFolds();
                    System.out.println("Scores are: " + Arrays.toString(scores));
                    final double currAvg = Arrays.stream(scores).average().orElse(Double.MIN_VALUE);
                    if (currAvg > avg) {
                        avg = currAvg;
                        bestP = p;
                        bestMaxDeep = maxDeep;
                    }
                    System.out.println("Avg is: " + currAvg + " with p: " + p + " with maxDeep: " + maxDeep);
                }
            }
            System.out.println("Train with p: " + bestP + " and maxDeep: " + bestMaxDeep);
            Preprocessor<Integer, Vector> normalizationPreprocessor = new NormalizationTrainer<Integer, Vector>().withP(bestP).fit(ignite, dataCache, minMaxScalerPreprocessor);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(bestMaxDeep, 0);
            // Train decision tree model.
            DecisionTreeModel bestMdl = trainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + bestMdl);
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), bestMdl, normalizationPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 8 (cross-validation) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 39 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector 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 40 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector in project ignite by apache.

the class LinearRegressionLSQRTrainerWithMinMaxScalerExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> Linear regression model with Min Max Scaling preprocessor over cached 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.MORTALITY_DATA);
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            System.out.println(">>> Create new MinMaxScaler trainer object.");
            MinMaxScalerTrainer<Integer, Vector> minMaxScalerTrainer = new MinMaxScalerTrainer<>();
            System.out.println(">>> Perform the training to get the MinMaxScaler preprocessor.");
            Preprocessor<Integer, Vector> preprocessor = minMaxScalerTrainer.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> Create new linear regression trainer object.");
            LinearRegressionLSQRTrainer trainer = new LinearRegressionLSQRTrainer();
            System.out.println(">>> Perform the training to get the model.");
            // TODO: IGNITE-11581
            LinearRegressionModel mdl = trainer.fit(ignite, dataCache, preprocessor);
            System.out.println(">>> Linear regression model: " + mdl);
            double rmse = Evaluator.evaluate(dataCache, mdl, preprocessor, MetricName.RMSE);
            System.out.println("\n>>> Rmse = " + rmse);
            System.out.println(">>> ---------------------------------");
            System.out.println(">>> Linear regression model with MinMaxScaler preprocessor over cache based dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}