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

Example 16 with Vector

use of org.apache.ignite.ml.math.primitives.vector.Vector 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 17 with Vector

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

the class Step_15_Parallel_Random_Search method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 15 (Parallel Random Search) 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(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);
            NormalizationTrainer<Integer, Vector> normalizationTrainer = new NormalizationTrainer<Integer, Vector>().withP(1);
            Preprocessor<Integer, Vector> normalizationPreprocessor = normalizationTrainer.fit(ignite, dataCache, minMaxScalerPreprocessor);
            // Tune hyper-parameters with K-fold Cross-Validation on the split training set.
            DecisionTreeClassificationTrainer trainerCV = new DecisionTreeClassificationTrainer();
            CrossValidation<DecisionTreeModel, Integer, Vector> scoreCalculator = new CrossValidation<>();
            ParamGrid paramGrid = new ParamGrid().withParameterSearchStrategy(new RandomStrategy().withMaxTries(10).withSeed(12L)).addHyperParam("p", normalizationTrainer::withP, new Double[] { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 }).addHyperParam("maxDeep", trainerCV::withMaxDeep, new Double[] { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 }).addHyperParam("minImpurityDecrease", trainerCV::withMinImpurityDecrease, new Double[] { 0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0 });
            scoreCalculator.withIgnite(ignite).withUpstreamCache(dataCache).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withParallelismStrategyTypeDependency(ParallelismStrategy.ON_DEFAULT_POOL).withLoggingFactoryDependency(ConsoleLogger.Factory.LOW)).withTrainer(trainerCV).isRunningOnPipeline(false).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).withPreprocessor(normalizationPreprocessor).withAmountOfFolds(3).withParamGrid(paramGrid);
            CrossValidationResult crossValidationRes = scoreCalculator.tuneHyperParameters();
            System.out.println("Train with maxDeep: " + crossValidationRes.getBest("maxDeep") + " and minImpurityDecrease: " + crossValidationRes.getBest("minImpurityDecrease"));
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer().withMaxDeep(crossValidationRes.getBest("maxDeep")).withMinImpurityDecrease(crossValidationRes.getBest("minImpurityDecrease"));
            System.out.println(crossValidationRes);
            System.out.println("Best score: " + Arrays.toString(crossValidationRes.getBestScore()));
            System.out.println("Best hyper params: " + crossValidationRes.getBestHyperParams());
            System.out.println("Best average score: " + crossValidationRes.getBestAvgScore());
            crossValidationRes.getScoringBoard().forEach((hyperParams, score) -> System.out.println("Score " + Arrays.toString(score) + " for hyper params " + hyperParams));
            // 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 15 (Parallel Random Search) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 18 with Vector

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

the class SandboxMLCache method fillCacheWith.

/**
 * Fills cache with data and returns it.
 *
 * @param dataset The chosen dataset.
 * @return Filled Ignite Cache.
 * @throws FileNotFoundException If file not found.
 */
public IgniteCache<Integer, Vector> fillCacheWith(MLSandboxDatasets dataset) throws FileNotFoundException {
    IgniteCache<Integer, Vector> cache = getCache();
    String fileName = dataset.getFileName();
    File file = IgniteUtils.resolveIgnitePath(fileName);
    if (file == null)
        throw new FileNotFoundException(fileName);
    Scanner scanner = new Scanner(file);
    int cnt = 0;
    while (scanner.hasNextLine()) {
        String row = scanner.nextLine();
        if (dataset.hasHeader() && cnt == 0) {
            cnt++;
            continue;
        }
        String[] cells = row.split(dataset.getSeparator());
        double[] data = new double[cells.length];
        NumberFormat format = NumberFormat.getInstance(Locale.FRANCE);
        for (int i = 0; i < cells.length; i++) try {
            if (cells[i].isEmpty())
                data[i] = Double.NaN;
            else
                data[i] = Double.valueOf(cells[i]);
        } catch (NumberFormatException e) {
            try {
                data[i] = format.parse(cells[i]).doubleValue();
            } catch (ParseException e1) {
                throw new FileParsingException(cells[i], i, Paths.get(dataset.getFileName()));
            }
        }
        cache.put(cnt++, VectorUtils.of(data));
    }
    return cache;
}

Example 19 with Vector

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

the class SandboxMLCache method getCache.

/**
 * Fills cache with data and returns it.
 *
 * @return Filled Ignite Cache.
 */
private IgniteCache<Integer, Vector> getCache() {
    CacheConfiguration<Integer, Vector> cacheConfiguration = new CacheConfiguration<>();
    cacheConfiguration.setName("ML_EXAMPLE_" + UUID.randomUUID());
    cacheConfiguration.setAffinity(new RendezvousAffinityFunction(false, 10));
    return ignite.createCache(cacheConfiguration);
}

Example 20 with Vector

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

the class SVMBinaryClassificationExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> SVM Binary classification model 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.TWO_CLASSED_IRIS);
            SVMLinearClassificationTrainer trainer = new SVMLinearClassificationTrainer();
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            SVMLinearClassificationModel mdl = trainer.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> SVM model " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, MetricName.ACCURACY);
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println(">>> SVM Binary classification model over cache based dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}