Examples with SandboxMLCache org.apache.ignite.examples.ml.util.SandboxMLCache used on opensource projects

Example 6 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache in project ignite by apache.

the class RandomForestClassificationExportImportExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> Random Forest multi-class classification algorithm over cached dataset usage example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println("\n>>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = null;
        Path jsonMdlPath = null;
        try {
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.WINE_RECOGNITION);
            AtomicInteger idx = new AtomicInteger(0);
            RandomForestClassifierTrainer classifier = new RandomForestClassifierTrainer(IntStream.range(0, dataCache.get(1).size() - 1).mapToObj(x -> new FeatureMeta("", idx.getAndIncrement(), false)).collect(Collectors.toList())).withAmountOfTrees(101).withFeaturesCountSelectionStrgy(FeaturesCountSelectionStrategies.ONE_THIRD).withMaxDepth(4).withMinImpurityDelta(0.).withSubSampleSize(0.3).withSeed(0);
            System.out.println(">>> Configured trainer: " + classifier.getClass().getSimpleName());
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            RandomForestModel mdl = classifier.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> Exported Random Forest classification model: " + mdl.toString(true));
            double accuracy = evaluateModel(dataCache, mdl);
            System.out.println("\n>>> Accuracy for exported Random Forest classification model " + accuracy);
            jsonMdlPath = Files.createTempFile(null, null);
            mdl.toJSON(jsonMdlPath);
            RandomForestModel modelImportedFromJSON = RandomForestModel.fromJSON(jsonMdlPath);
            System.out.println("\n>>> Imported Random Forest classification model: " + modelImportedFromJSON);
            accuracy = evaluateModel(dataCache, mdl);
            System.out.println("\n>>> Accuracy for imported Random Forest classification model " + accuracy);
            System.out.println("\n>>> Random Forest multi-class classification algorithm over cached dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
            if (jsonMdlPath != null)
                Files.deleteIfExists(jsonMdlPath);
        }
    } finally {
        System.out.flush();
    }
}

Example 7 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache in project ignite by apache.

the class LogRegFromSparkThroughPMMLExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> Logistic regression model loaded from PMML 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 {
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.TWO_CLASSED_IRIS);
            String path = IgniteUtils.resolveIgnitePath("examples/src/main/resources/models/spark/iris.pmml").toPath().toAbsolutePath().toString();
            LogisticRegressionModel mdl = PMMLParser.load(path);
            System.out.println(">>> Logistic regression model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    }
}

Example 8 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache in project ignite by apache.

the class RandomForestRegressionExportImportExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> Random Forest regression algorithm over cached dataset usage example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println("\n>>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = null;
        Path jsonMdlPath = null;
        try {
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.BOSTON_HOUSE_PRICES);
            AtomicInteger idx = new AtomicInteger(0);
            RandomForestRegressionTrainer trainer = new RandomForestRegressionTrainer(IntStream.range(0, dataCache.get(1).size() - 1).mapToObj(x -> new FeatureMeta("", idx.getAndIncrement(), false)).collect(Collectors.toList())).withAmountOfTrees(101).withFeaturesCountSelectionStrgy(FeaturesCountSelectionStrategies.ONE_THIRD).withMaxDepth(4).withMinImpurityDelta(0.).withSubSampleSize(0.3).withSeed(0);
            trainer.withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withParallelismStrategyTypeDependency(ParallelismStrategy.ON_DEFAULT_POOL).withLoggingFactoryDependency(ConsoleLogger.Factory.LOW));
            System.out.println("\n>>> Configured trainer: " + trainer.getClass().getSimpleName());
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            RandomForestModel mdl = trainer.fit(ignite, dataCache, vectorizer);
            System.out.println("\n>>> Exported Random Forest regression model: " + mdl.toString(true));
            double mae = evaluateModel(dataCache, mdl);
            System.out.println("\n>>> Mean absolute error (MAE) for exported Random Forest regression model " + mae);
            jsonMdlPath = Files.createTempFile(null, null);
            mdl.toJSON(jsonMdlPath);
            RandomForestModel modelImportedFromJSON = RandomForestModel.fromJSON(jsonMdlPath);
            System.out.println("\n>>> Exported Random Forest regression model: " + modelImportedFromJSON.toString(true));
            mae = evaluateModel(dataCache, modelImportedFromJSON);
            System.out.println("\n>>> Mean absolute error (MAE) for exported Random Forest regression model " + mae);
            System.out.println("\n>>> Random Forest regression algorithm over cached dataset usage example completed.");
        } finally {
            if (dataCache != null)
                dataCache.destroy();
            if (jsonMdlPath != null)
                Files.deleteIfExists(jsonMdlPath);
        }
    } finally {
        System.out.flush();
    }
}

Example 9 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache 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();
    }
}

Example 10 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache 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();
    }
}