Examples with ModelsComposition org.apache.ignite.ml.composition.ModelsComposition used on opensource projects

Example 6 with ModelsComposition

use of org.apache.ignite.ml.composition.ModelsComposition in project ignite by apache.

the class GBTFromSparkExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws FileNotFoundException {
    System.out.println();
    System.out.println(">>> Gradient Boosted trees model loaded from Spark through serialization 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 = TitanicUtils.readPassengersWithoutNulls(ignite);
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 5, 6).labeled(1);
            ModelsComposition mdl = (ModelsComposition) SparkModelParser.parse(SPARK_MDL_PATH, SupportedSparkModels.GRADIENT_BOOSTED_TREES, env);
            System.out.println(">>> GBT: " + mdl.toString(true));
            double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
        } finally {
            dataCache.destroy();
        }
    }
}

Example 7 with ModelsComposition

use of org.apache.ignite.ml.composition.ModelsComposition in project ignite by apache.

the class RandomForestRegressionExample 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(">>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = 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(">>> Configured trainer: " + trainer.getClass().getSimpleName());
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            ModelsComposition randomForestMdl = trainer.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> Trained model: " + randomForestMdl.toString(true));
            double mse = 0.0;
            double mae = 0.0;
            int totalAmount = 0;
            try (QueryCursor<Cache.Entry<Integer, Vector>> observations = dataCache.query(new ScanQuery<>())) {
                for (Cache.Entry<Integer, Vector> observation : observations) {
                    Vector val = observation.getValue();
                    Vector inputs = val.copyOfRange(1, val.size());
                    double groundTruth = val.get(0);
                    double prediction = randomForestMdl.predict(inputs);
                    mse += Math.pow(prediction - groundTruth, 2.0);
                    mae += Math.abs(prediction - groundTruth);
                    totalAmount++;
                }
                System.out.println("\n>>> Evaluated model on " + totalAmount + " data points.");
                mse /= totalAmount;
                System.out.println("\n>>> Mean squared error (MSE) " + mse);
                mae /= totalAmount;
                System.out.println("\n>>> Mean absolute error (MAE) " + mae);
                System.out.println(">>> Random Forest regression algorithm over cached dataset usage example completed.");
            }
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 8 with ModelsComposition

use of org.apache.ignite.ml.composition.ModelsComposition in project ignite by apache.

the class RandomForestClassificationExample 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(">>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = 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);
            ModelsComposition randomForestMdl = classifier.fit(ignite, dataCache, vectorizer);
            System.out.println(">>> Trained model: " + randomForestMdl.toString(true));
            int amountOfErrors = 0;
            int totalAmount = 0;
            try (QueryCursor<Cache.Entry<Integer, Vector>> observations = dataCache.query(new ScanQuery<>())) {
                for (Cache.Entry<Integer, Vector> observation : observations) {
                    Vector val = observation.getValue();
                    Vector inputs = val.copyOfRange(1, val.size());
                    double groundTruth = val.get(0);
                    double prediction = randomForestMdl.predict(inputs);
                    totalAmount++;
                    if (!Precision.equals(groundTruth, prediction, Precision.EPSILON))
                        amountOfErrors++;
                }
                System.out.println("\n>>> Evaluated model on " + totalAmount + " data points.");
                System.out.println("\n>>> Absolute amount of errors " + amountOfErrors);
                System.out.println("\n>>> Accuracy " + (1 - amountOfErrors / (double) totalAmount));
                System.out.println(">>> Random Forest multi-class classification algorithm over cached dataset usage example completed.");
            }
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 9 with ModelsComposition

use of org.apache.ignite.ml.composition.ModelsComposition in project ignite by apache.

the class GBTRegressionFromSparkExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws FileNotFoundException {
    System.out.println();
    System.out.println(">>> GBT Regression model loaded from Spark through serialization 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 = TitanicUtils.readPassengersWithoutNulls(ignite);
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 1, 5, 6).labeled(4);
            ModelsComposition mdl = (ModelsComposition) SparkModelParser.parse(SPARK_MDL_PATH, SupportedSparkModels.GRADIENT_BOOSTED_TREES_REGRESSION, env);
            System.out.println(">>> GBT Regression model: " + mdl);
            System.out.println(">>> ---------------------------------");
            System.out.println(">>> | Prediction\t| Ground Truth\t|");
            System.out.println(">>> ---------------------------------");
            try (QueryCursor<Cache.Entry<Integer, Vector>> observations = dataCache.query(new ScanQuery<>())) {
                for (Cache.Entry<Integer, Vector> observation : observations) {
                    LabeledVector<Double> lv = vectorizer.apply(observation.getKey(), observation.getValue());
                    Vector inputs = lv.features();
                    double groundTruth = lv.label();
                    double prediction = mdl.predict(inputs);
                    System.out.printf(">>> | %.4f\t\t| %.4f\t\t|\n", prediction, groundTruth);
                }
            }
            System.out.println(">>> ---------------------------------");
        } finally {
            dataCache.destroy();
        }
    }
}

Example 10 with ModelsComposition

use of org.apache.ignite.ml.composition.ModelsComposition in project ignite by apache.

the class RandomForestFromSparkExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws FileNotFoundException {
    System.out.println();
    System.out.println(">>> Random Forest model loaded from Spark through serialization 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 = TitanicUtils.readPassengersWithoutNulls(ignite);
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 5, 6).labeled(1);
            ModelsComposition mdl = (ModelsComposition) SparkModelParser.parse(SPARK_MDL_PATH, SupportedSparkModels.RANDOM_FOREST, env);
            System.out.println(">>> Random Forest model: " + mdl.toString(true));
            double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
        } finally {
            dataCache.destroy();
        }
    }
}