Search in sources :

Example 1 with MedianOfMedianConvergenceCheckerFactory

use of org.apache.ignite.ml.composition.boosting.convergence.median.MedianOfMedianConvergenceCheckerFactory 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();
    }
}
Also used : SandboxMLCache(org.apache.ignite.examples.ml.util.SandboxMLCache) GDBTrainer(org.apache.ignite.ml.composition.boosting.GDBTrainer) FileNotFoundException(java.io.FileNotFoundException) ModelsComposition(org.apache.ignite.ml.composition.ModelsComposition) GDBBinaryClassifierOnTreesTrainer(org.apache.ignite.ml.tree.boosting.GDBBinaryClassifierOnTreesTrainer) Accuracy(org.apache.ignite.ml.selection.scoring.metric.classification.Accuracy) MedianOfMedianConvergenceCheckerFactory(org.apache.ignite.ml.composition.boosting.convergence.median.MedianOfMedianConvergenceCheckerFactory) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) HashSet(java.util.HashSet)

Example 2 with MedianOfMedianConvergenceCheckerFactory

use of org.apache.ignite.ml.composition.boosting.convergence.median.MedianOfMedianConvergenceCheckerFactory in project ignite by apache.

the class Step_11_Boosting method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 11 (Boosting) 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);
            // Create classification trainer.
            GDBTrainer trainer = new GDBBinaryClassifierOnTreesTrainer(0.5, 500, 4, 0.).withCheckConvergenceStgyFactory(new MedianOfMedianConvergenceCheckerFactory(0.1));
            // Train decision tree model.
            GDBModel mdl = trainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl.toString(true));
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), mdl, normalizationPreprocessor, MetricName.ACCURACY);
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 11 (Boosting) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : GDBTrainer(org.apache.ignite.ml.composition.boosting.GDBTrainer) GDBModel(org.apache.ignite.ml.composition.boosting.GDBModel) FileNotFoundException(java.io.FileNotFoundException) NormalizationTrainer(org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer) GDBBinaryClassifierOnTreesTrainer(org.apache.ignite.ml.tree.boosting.GDBBinaryClassifierOnTreesTrainer) MedianOfMedianConvergenceCheckerFactory(org.apache.ignite.ml.composition.boosting.convergence.median.MedianOfMedianConvergenceCheckerFactory) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Aggregations

FileNotFoundException (java.io.FileNotFoundException)2 Ignite (org.apache.ignite.Ignite)2 GDBTrainer (org.apache.ignite.ml.composition.boosting.GDBTrainer)2 MedianOfMedianConvergenceCheckerFactory (org.apache.ignite.ml.composition.boosting.convergence.median.MedianOfMedianConvergenceCheckerFactory)2 EncoderTrainer (org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer)2 GDBBinaryClassifierOnTreesTrainer (org.apache.ignite.ml.tree.boosting.GDBBinaryClassifierOnTreesTrainer)2 HashSet (java.util.HashSet)1 SandboxMLCache (org.apache.ignite.examples.ml.util.SandboxMLCache)1 ModelsComposition (org.apache.ignite.ml.composition.ModelsComposition)1 GDBModel (org.apache.ignite.ml.composition.boosting.GDBModel)1 Vector (org.apache.ignite.ml.math.primitives.vector.Vector)1 NormalizationTrainer (org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer)1 Accuracy (org.apache.ignite.ml.selection.scoring.metric.classification.Accuracy)1