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

Example 11 with SandboxMLCache

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

the class KNNRegressionExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    System.out.println();
    System.out.println(">>> kNN regression 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.CLEARED_MACHINES);
            KNNRegressionTrainer trainer = new KNNRegressionTrainer().withK(5).withDistanceMeasure(new ManhattanDistance()).withIdxType(SpatialIndexType.BALL_TREE).withWeighted(true);
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(Vectorizer.LabelCoordinate.FIRST);
            KNNRegressionModel knnMdl = trainer.fit(ignite, dataCache, vectorizer);
            double rmse = Evaluator.evaluate(dataCache, knnMdl, vectorizer, new Rmse());
            System.out.println("\n>>> Rmse = " + rmse);
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 12 with SandboxMLCache

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

the class TargetEncoderExample method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Train Gradient Boosing Decision Tree model on amazon-employee-access-challenge_train.csv dataset.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Object[]> dataCache = new SandboxMLCache(ignite).fillObjectCacheWithCategoricalData(MLSandboxDatasets.AMAZON_EMPLOYEE_ACCESS);
            Set<Integer> featuresIndexies = new HashSet<>(Arrays.asList(1, 2, 3, 4, 5, 6, 7, 8, 9));
            Set<Integer> targetEncodedfeaturesIndexies = new HashSet<>(Arrays.asList(1, 5, 6));
            Integer targetIndex = 0;
            final Vectorizer<Integer, Object[], Integer, Object> vectorizer = new ObjectArrayVectorizer<Integer>(featuresIndexies.toArray(new Integer[0])).labeled(targetIndex);
            Preprocessor<Integer, Object[]> strEncoderPreprocessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(0).withEncodedFeatures(featuresIndexies).fit(ignite, dataCache, vectorizer);
            Preprocessor<Integer, Object[]> targetEncoderProcessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.TARGET_ENCODER).labeled(0).withEncodedFeatures(targetEncodedfeaturesIndexies).minSamplesLeaf(1).minCategorySize(1L).smoothing(1d).fit(ignite, dataCache, strEncoderPreprocessor);
            Preprocessor<Integer, Object[]> lbEncoderPreprocessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.LABEL_ENCODER).fit(ignite, dataCache, targetEncoderProcessor);
            GDBTrainer trainer = new GDBBinaryClassifierOnTreesTrainer(0.5, 500, 4, 0.).withCheckConvergenceStgyFactory(new MedianOfMedianConvergenceCheckerFactory(0.1));
            // Train model.
            ModelsComposition mdl = trainer.fit(ignite, dataCache, lbEncoderPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, lbEncoderPreprocessor, new Accuracy());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Train Gradient Boosing Decision Tree model on amazon-employee-access-challenge_train.csv dataset.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 13 with SandboxMLCache

use of org.apache.ignite.examples.ml.util.SandboxMLCache 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 14 with SandboxMLCache

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

the class DecisionTreeClassificationTrainerSQLTableExample method loadTitanicDatasets.

/**
 * Loads Titanic dataset into cache.
 *
 * @param ignite Ignite instance.
 * @throws IOException If dataset not found.
 */
static void loadTitanicDatasets(Ignite ignite, IgniteCache<?, ?> cache) throws IOException {
    List<String> titanicDatasetRows = new SandboxMLCache(ignite).loadDataset(MLSandboxDatasets.TITANIC);
    List<String> train = titanicDatasetRows.subList(0, 1000);
    List<String> test = titanicDatasetRows.subList(1000, titanicDatasetRows.size());
    insertToCache(cache, train, "titanic_train");
    insertToCache(cache, test, "titanic_test");
}

Example 15 with SandboxMLCache

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