Examples with DecisionTreeClassificationTrainer org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer used on opensource projects

Example 21 with DecisionTreeClassificationTrainer

use of org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer in project ignite by apache.

the class LabelEncoderExample method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Train Decision Tree model on mushrooms.csv dataset.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Object[]> dataCache = new SandboxMLCache(ignite).fillObjectCacheWithCategoricalData(MLSandboxDatasets.MUSHROOMS);
            final Vectorizer<Integer, Object[], Integer, Object> vectorizer = new ObjectArrayVectorizer<Integer>(1, 2).labeled(0);
            Preprocessor<Integer, Object[]> strEncoderPreprocessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(0).withEncodedFeature(1).fit(ignite, dataCache, vectorizer);
            Preprocessor<Integer, Object[]> lbEncoderPreprocessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.LABEL_ENCODER).fit(ignite, dataCache, strEncoderPreprocessor);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            // Train decision tree model.
            DecisionTreeModel 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 Decision Tree model on mushrooms.csv dataset.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 22 with DecisionTreeClassificationTrainer

use of org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer in project ignite by apache.

the class DecisionTreeClassificationTrainerExample method main.

/**
 * Executes example.
 *
 * @param args Command line arguments, none required.
 */
public static void main(String... args) {
    System.out.println(">>> Decision tree classification trainer example started.");
    // Start ignite grid.
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        // Create cache with training data.
        CacheConfiguration<Integer, LabeledVector<Double>> trainingSetCfg = new CacheConfiguration<>();
        trainingSetCfg.setName("TRAINING_SET");
        trainingSetCfg.setAffinity(new RendezvousAffinityFunction(false, 10));
        IgniteCache<Integer, LabeledVector<Double>> trainingSet = null;
        try {
            trainingSet = ignite.createCache(trainingSetCfg);
            Random rnd = new Random(0);
            // Fill training data.
            for (int i = 0; i < 1000; i++) trainingSet.put(i, generatePoint(rnd));
            // Create classification trainer.
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(4, 0);
            // Train decision tree model.
            LabeledDummyVectorizer<Integer, Double> vectorizer = new LabeledDummyVectorizer<>();
            DecisionTreeModel mdl = trainer.fit(ignite, trainingSet, vectorizer);
            System.out.println(">>> Decision tree classification model: " + mdl);
            // Calculate score.
            int correctPredictions = 0;
            for (int i = 0; i < 1000; i++) {
                LabeledVector<Double> pnt = generatePoint(rnd);
                double prediction = mdl.predict(pnt.features());
                double lbl = pnt.label();
                if (i % 50 == 1)
                    System.out.printf(">>> test #: %d\t\t predicted: %.4f\t\tlabel: %.4f\n", i, prediction, lbl);
                if (Precision.equals(prediction, lbl, Precision.EPSILON))
                    correctPredictions++;
            }
            System.out.println(">>> Accuracy: " + correctPredictions / 10.0 + "%");
            System.out.println(">>> Decision tree classification trainer example completed.");
        } finally {
            trainingSet.destroy();
        }
    } finally {
        System.out.flush();
    }
}

Example 23 with DecisionTreeClassificationTrainer

use of org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer in project ignite by apache.

the class Step_5_Scaling_with_Pipeline method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 5 (scaling) via Pipeline 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);
            PipelineMdl<Integer, Vector> mdl = new Pipeline<Integer, Vector, Integer, Double>().addVectorizer(vectorizer).addPreprocessingTrainer(new EncoderTrainer<Integer, Vector>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(1).withEncodedFeature(6)).addPreprocessingTrainer(new ImputerTrainer<Integer, Vector>()).addPreprocessingTrainer(new MinMaxScalerTrainer<Integer, Vector>()).addPreprocessingTrainer(new NormalizationTrainer<Integer, Vector>().withP(1)).addTrainer(new DecisionTreeClassificationTrainer(5, 0)).fit(ignite, dataCache);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, mdl.getPreprocessor(), new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 5 (scaling) via Pipeline example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 24 with DecisionTreeClassificationTrainer

use of org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer in project ignite by apache.

the class Step_8_CV_with_Param_Grid_and_pipeline method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 8 (cross-validation with param grid and pipeline) example started.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Vector> dataCache = TitanicUtils.readPassengers(ignite);
            // Extracts "pclass", "sibsp", "parch", "age", "fare".
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 4, 5, 6, 8).labeled(1);
            TrainTestSplit<Integer, Vector> split = new TrainTestDatasetSplitter<Integer, Vector>().split(0.75);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            Pipeline<Integer, Vector, Integer, Double> pipeline = new Pipeline<Integer, Vector, Integer, Double>().addVectorizer(vectorizer).addPreprocessingTrainer(new ImputerTrainer<Integer, Vector>()).addPreprocessingTrainer(new MinMaxScalerTrainer<Integer, Vector>()).addTrainer(trainer);
            // Tune hyper-parameters with K-fold Cross-Validation on the split training set.
            CrossValidation<DecisionTreeModel, Integer, Vector> scoreCalculator = new CrossValidation<>();
            ParamGrid paramGrid = new ParamGrid().addHyperParam("maxDeep", trainer::withMaxDeep, new Double[] { 1.0, 2.0, 3.0, 4.0, 5.0, 10.0 }).addHyperParam("minImpurityDecrease", trainer::withMinImpurityDecrease, new Double[] { 0.0, 0.25, 0.5 });
            scoreCalculator.withIgnite(ignite).withUpstreamCache(dataCache).withPipeline(pipeline).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).withAmountOfFolds(3).withParamGrid(paramGrid);
            CrossValidationResult crossValidationRes = scoreCalculator.tuneHyperParameters();
            System.out.println("Train with maxDeep: " + crossValidationRes.getBest("maxDeep") + " and minImpurityDecrease: " + crossValidationRes.getBest("minImpurityDecrease"));
            System.out.println(crossValidationRes);
            System.out.println("Best score: " + Arrays.toString(crossValidationRes.getBestScore()));
            System.out.println("Best hyper params: " + crossValidationRes.getBestHyperParams());
            System.out.println("Best average score: " + crossValidationRes.getBestAvgScore());
            crossValidationRes.getScoringBoard().forEach((hyperParams, score) -> System.out.println("Score " + Arrays.toString(score) + " for hyper params " + hyperParams));
            System.out.println(">>> Tutorial step 8 (cross-validation with param grid and pipeline) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}

Example 25 with DecisionTreeClassificationTrainer

use of org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer in project ignite by apache.

the class Step_3_Categorial_with_One_Hot_Encoder method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 3 (categorial with One-hot encoder) example started.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Vector> dataCache = TitanicUtils.readPassengers(ignite);
            // "pclass", "sibsp", "parch", "sex", "embarked"
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 3, 5, 6, 10).labeled(1);
            Preprocessor<Integer, Vector> oneHotEncoderPreprocessor = new EncoderTrainer<Integer, Vector>().withEncoderType(EncoderType.ONE_HOT_ENCODER).withEncodedFeature(0).withEncodedFeature(1).withEncodedFeature(4).fit(ignite, dataCache, vectorizer);
            Preprocessor<Integer, Vector> imputingPreprocessor = new ImputerTrainer<Integer, Vector>().fit(ignite, dataCache, oneHotEncoderPreprocessor);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            // Train decision tree model.
            DecisionTreeModel mdl = trainer.fit(ignite, dataCache, imputingPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, mdl, imputingPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 3 (categorial with One-hot encoder) example started.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}