Search in sources :

Example 1 with RandomForestClassifierTrainer

use of org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer 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();
    }
}
Also used : Path(java.nio.file.Path) SandboxMLCache(org.apache.ignite.examples.ml.util.SandboxMLCache) RandomForestModel(org.apache.ignite.ml.tree.randomforest.RandomForestModel) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) FeatureMeta(org.apache.ignite.ml.dataset.feature.FeatureMeta) RandomForestClassifierTrainer(org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer) Ignite(org.apache.ignite.Ignite) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 2 with RandomForestClassifierTrainer

use of org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer 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();
    }
}
Also used : SandboxMLCache(org.apache.ignite.examples.ml.util.SandboxMLCache) ModelsComposition(org.apache.ignite.ml.composition.ModelsComposition) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) FeatureMeta(org.apache.ignite.ml.dataset.feature.FeatureMeta) RandomForestClassifierTrainer(org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer) Ignite(org.apache.ignite.Ignite) Vector(org.apache.ignite.ml.math.primitives.vector.Vector) IgniteCache(org.apache.ignite.IgniteCache) SandboxMLCache(org.apache.ignite.examples.ml.util.SandboxMLCache) Cache(javax.cache.Cache)

Aggregations

AtomicInteger (java.util.concurrent.atomic.AtomicInteger)2 Ignite (org.apache.ignite.Ignite)2 SandboxMLCache (org.apache.ignite.examples.ml.util.SandboxMLCache)2 FeatureMeta (org.apache.ignite.ml.dataset.feature.FeatureMeta)2 Vector (org.apache.ignite.ml.math.primitives.vector.Vector)2 RandomForestClassifierTrainer (org.apache.ignite.ml.tree.randomforest.RandomForestClassifierTrainer)2 Path (java.nio.file.Path)1 Cache (javax.cache.Cache)1 IgniteCache (org.apache.ignite.IgniteCache)1 ModelsComposition (org.apache.ignite.ml.composition.ModelsComposition)1 RandomForestModel (org.apache.ignite.ml.tree.randomforest.RandomForestModel)1