Search in sources :

Example 6 with DecisionTreeModel

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

the class Step_3_Categorial method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 3 (categorial) 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> strEncoderPreprocessor = new EncoderTrainer<Integer, Vector>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(1).withEncodedFeature(4).fit(ignite, dataCache, vectorizer);
            Preprocessor<Integer, Vector> imputingPreprocessor = new ImputerTrainer<Integer, Vector>().fit(ignite, dataCache, strEncoderPreprocessor);
            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) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 7 with DecisionTreeModel

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

the class Step_4_Add_age_fare method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 4 (add age and fare) 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);
            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);
            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 4 (add age and fare) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 8 with DecisionTreeModel

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

the class Step_7_Split_train_test method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 7 (split to train and test) 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);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            // Train decision tree model.
            DecisionTreeModel mdl = trainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), mdl, normalizationPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 7 (split to train and test) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) NormalizationTrainer(org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 9 with DecisionTreeModel

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

the class Step_8_CV method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 8 (cross-validation) 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);
            // Tune hyper-parameters with K-fold Cross-Validation on the split training set.
            int[] pSet = new int[] { 1, 2 };
            int[] maxDeepSet = new int[] { 1, 2, 3, 4, 5, 10, 20 };
            int bestP = 1;
            int bestMaxDeep = 1;
            double avg = Double.MIN_VALUE;
            for (int p : pSet) {
                for (int maxDeep : maxDeepSet) {
                    Preprocessor<Integer, Vector> normalizationPreprocessor = new NormalizationTrainer<Integer, Vector>().withP(p).fit(ignite, dataCache, minMaxScalerPreprocessor);
                    DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(maxDeep, 0);
                    CrossValidation<DecisionTreeModel, Integer, Vector> scoreCalculator = new CrossValidation<>();
                    double[] scores = scoreCalculator.withIgnite(ignite).withUpstreamCache(dataCache).withTrainer(trainer).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).withPreprocessor(normalizationPreprocessor).withAmountOfFolds(3).isRunningOnPipeline(false).scoreByFolds();
                    System.out.println("Scores are: " + Arrays.toString(scores));
                    final double currAvg = Arrays.stream(scores).average().orElse(Double.MIN_VALUE);
                    if (currAvg > avg) {
                        avg = currAvg;
                        bestP = p;
                        bestMaxDeep = maxDeep;
                    }
                    System.out.println("Avg is: " + currAvg + " with p: " + p + " with maxDeep: " + maxDeep);
                }
            }
            System.out.println("Train with p: " + bestP + " and maxDeep: " + bestMaxDeep);
            Preprocessor<Integer, Vector> normalizationPreprocessor = new NormalizationTrainer<Integer, Vector>().withP(bestP).fit(ignite, dataCache, minMaxScalerPreprocessor);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(bestMaxDeep, 0);
            // Train decision tree model.
            DecisionTreeModel bestMdl = trainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + bestMdl);
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), bestMdl, normalizationPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 8 (cross-validation) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) NormalizationTrainer(org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) Ignite(org.apache.ignite.Ignite) CrossValidation(org.apache.ignite.ml.selection.cv.CrossValidation) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 10 with DecisionTreeModel

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

the class Step_15_Parallel_Random_Search method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 15 (Parallel Random Search) 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(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);
            NormalizationTrainer<Integer, Vector> normalizationTrainer = new NormalizationTrainer<Integer, Vector>().withP(1);
            Preprocessor<Integer, Vector> normalizationPreprocessor = normalizationTrainer.fit(ignite, dataCache, minMaxScalerPreprocessor);
            // Tune hyper-parameters with K-fold Cross-Validation on the split training set.
            DecisionTreeClassificationTrainer trainerCV = new DecisionTreeClassificationTrainer();
            CrossValidation<DecisionTreeModel, Integer, Vector> scoreCalculator = new CrossValidation<>();
            ParamGrid paramGrid = new ParamGrid().withParameterSearchStrategy(new RandomStrategy().withMaxTries(10).withSeed(12L)).addHyperParam("p", normalizationTrainer::withP, new Double[] { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 }).addHyperParam("maxDeep", trainerCV::withMaxDeep, new Double[] { 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0 }).addHyperParam("minImpurityDecrease", trainerCV::withMinImpurityDecrease, new Double[] { 0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0 });
            scoreCalculator.withIgnite(ignite).withUpstreamCache(dataCache).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withParallelismStrategyTypeDependency(ParallelismStrategy.ON_DEFAULT_POOL).withLoggingFactoryDependency(ConsoleLogger.Factory.LOW)).withTrainer(trainerCV).isRunningOnPipeline(false).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).withPreprocessor(normalizationPreprocessor).withAmountOfFolds(3).withParamGrid(paramGrid);
            CrossValidationResult crossValidationRes = scoreCalculator.tuneHyperParameters();
            System.out.println("Train with maxDeep: " + crossValidationRes.getBest("maxDeep") + " and minImpurityDecrease: " + crossValidationRes.getBest("minImpurityDecrease"));
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer().withMaxDeep(crossValidationRes.getBest("maxDeep")).withMinImpurityDecrease(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));
            // Train decision tree model.
            DecisionTreeModel bestMdl = trainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + bestMdl);
            double accuracy = Evaluator.evaluate(dataCache, split.getTestFilter(), bestMdl, normalizationPreprocessor, new Accuracy<>());
            System.out.println("\n>>> Accuracy " + accuracy);
            System.out.println("\n>>> Test Error " + (1 - accuracy));
            System.out.println(">>> Tutorial step 15 (Parallel Random Search) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) Ignite(org.apache.ignite.Ignite) EncoderTrainer(org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer) Vector(org.apache.ignite.ml.math.primitives.vector.Vector) CrossValidationResult(org.apache.ignite.ml.selection.cv.CrossValidationResult) ParamGrid(org.apache.ignite.ml.selection.paramgrid.ParamGrid) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) RandomStrategy(org.apache.ignite.ml.selection.paramgrid.RandomStrategy) CrossValidation(org.apache.ignite.ml.selection.cv.CrossValidation)

Aggregations

DecisionTreeModel (org.apache.ignite.ml.tree.DecisionTreeModel)32 Ignite (org.apache.ignite.Ignite)27 DecisionTreeClassificationTrainer (org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer)26 Vector (org.apache.ignite.ml.math.primitives.vector.Vector)20 FileNotFoundException (java.io.FileNotFoundException)18 EncoderTrainer (org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer)12 CrossValidation (org.apache.ignite.ml.selection.cv.CrossValidation)9 CrossValidationResult (org.apache.ignite.ml.selection.cv.CrossValidationResult)7 ParamGrid (org.apache.ignite.ml.selection.paramgrid.ParamGrid)7 CacheConfiguration (org.apache.ignite.configuration.CacheConfiguration)6 LabeledVector (org.apache.ignite.ml.structures.LabeledVector)6 HashMap (java.util.HashMap)5 RendezvousAffinityFunction (org.apache.ignite.cache.affinity.rendezvous.RendezvousAffinityFunction)5 NormalizationTrainer (org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer)5 Test (org.junit.Test)4 Random (java.util.Random)3 SandboxMLCache (org.apache.ignite.examples.ml.util.SandboxMLCache)3 LabeledDummyVectorizer (org.apache.ignite.ml.dataset.feature.extractor.impl.LabeledDummyVectorizer)3 Path (java.nio.file.Path)2 List (java.util.List)2