Search in sources :

Example 6 with DecisionTreeClassificationTrainer

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

the class FraudDetectionExample method main.

/**
 * Run example.
 */
public static void main(String[] args) throws IOException {
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        System.out.println(">>> Ignite grid started.");
        IgniteCache<Integer, Vector> dataCache = null;
        try {
            System.out.println(">>> Fill dataset cache.");
            dataCache = new SandboxMLCache(ignite).fillCacheWith(MLSandboxDatasets.FRAUD_DETECTION);
            // This vectorizer works with values in cache of Vector class.
            Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>().labeled(// LAST means "label are stored at last coordinate of vector"
            Vectorizer.LabelCoordinate.LAST);
            // Splits dataset to train and test samples with 80/20 proportion.
            TrainTestSplit<Integer, Vector> split = new TrainTestDatasetSplitter<Integer, Vector>().split(0.8);
            System.out.println(">>> Perform logistic regression.");
            trainAndEstimateModel(ignite, dataCache, new LogisticRegressionSGDTrainer().withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(0)), vectorizer, split);
            System.out.println("\n\n>>> Perform decision tree classifier.");
            trainAndEstimateModel(ignite, dataCache, new DecisionTreeClassificationTrainer().withMaxDeep(10.).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(0)), vectorizer, split);
        } finally {
            if (dataCache != null)
                dataCache.destroy();
        }
    } finally {
        System.out.flush();
    }
}
Also used : LogisticRegressionSGDTrainer(org.apache.ignite.ml.regressions.logistic.LogisticRegressionSGDTrainer) SandboxMLCache(org.apache.ignite.examples.ml.util.SandboxMLCache) DecisionTreeClassificationTrainer(org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer) Ignite(org.apache.ignite.Ignite) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 7 with DecisionTreeClassificationTrainer

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

the class Step_10_Bagging method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 10 (Bagging) 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);
            BaggedTrainer<Double> baggedTrainer = TrainerTransformers.makeBagged(trainer, 10, 0.6, 4, 3, new OnMajorityPredictionsAggregator()).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withRNGSeed(1));
            BaggedModel mdl = baggedTrainer.fit(ignite, dataCache, split.getTrainFilter(), normalizationPreprocessor);
            System.out.println("\n>>> Trained model: " + mdl);
            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 10 (Bagging) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : OnMajorityPredictionsAggregator(org.apache.ignite.ml.composition.predictionsaggregator.OnMajorityPredictionsAggregator) 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) BaggedModel(org.apache.ignite.ml.composition.bagging.BaggedModel)

Example 8 with DecisionTreeClassificationTrainer

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

the class Step_2_Imputing method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 2 (imputing) example started.");
    try (Ignite ignite = Ignition.start("examples/config/example-ignite.xml")) {
        try {
            IgniteCache<Integer, Vector> dataCache = TitanicUtils.readPassengers(ignite);
            final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 5, 6).labeled(1);
            Preprocessor<Integer, Vector> imputingPreprocessor = new ImputerTrainer<Integer, Vector>().fit(ignite, dataCache, // "pclass", "sibsp", "parch"
            vectorizer);
            DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
            // Train decision tree model.
            DecisionTreeModel mdl = trainer.fit(ignite, dataCache, vectorizer);
            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 2 (imputing) 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) Vector(org.apache.ignite.ml.math.primitives.vector.Vector)

Example 9 with DecisionTreeClassificationTrainer

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

the class Step_14_Parallel_Brute_Force_Search method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 14 (Brute Force) 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 BruteForceStrategy()).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 14 (Brute Force) 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) BruteForceStrategy(org.apache.ignite.ml.selection.paramgrid.BruteForceStrategy) CrossValidation(org.apache.ignite.ml.selection.cv.CrossValidation)

Example 10 with DecisionTreeClassificationTrainer

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

the class Step_16_Genetic_Programming_Search method main.

/**
 * Run example.
 */
public static void main(String[] args) {
    System.out.println();
    System.out.println(">>> Tutorial step 16 (Genetic Programming) 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 EvolutionOptimizationStrategy()).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).withTrainer(trainerCV).withMetric(MetricName.ACCURACY).withFilter(split.getTrainFilter()).isRunningOnPipeline(false).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 16 (Genetic Programming) example completed.");
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        }
    } finally {
        System.out.flush();
    }
}
Also used : DecisionTreeModel(org.apache.ignite.ml.tree.DecisionTreeModel) FileNotFoundException(java.io.FileNotFoundException) EvolutionOptimizationStrategy(org.apache.ignite.ml.selection.paramgrid.EvolutionOptimizationStrategy) 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) CrossValidation(org.apache.ignite.ml.selection.cv.CrossValidation)

Aggregations

DecisionTreeClassificationTrainer (org.apache.ignite.ml.tree.DecisionTreeClassificationTrainer)31 Ignite (org.apache.ignite.Ignite)28 DecisionTreeModel (org.apache.ignite.ml.tree.DecisionTreeModel)26 FileNotFoundException (java.io.FileNotFoundException)21 Vector (org.apache.ignite.ml.math.primitives.vector.Vector)21 EncoderTrainer (org.apache.ignite.ml.preprocessing.encoding.EncoderTrainer)14 NormalizationTrainer (org.apache.ignite.ml.preprocessing.normalization.NormalizationTrainer)9 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 SandboxMLCache (org.apache.ignite.examples.ml.util.SandboxMLCache)5 CacheConfiguration (org.apache.ignite.configuration.CacheConfiguration)4 LabeledVector (org.apache.ignite.ml.structures.LabeledVector)4 HashMap (java.util.HashMap)3 Random (java.util.Random)3 RendezvousAffinityFunction (org.apache.ignite.cache.affinity.rendezvous.RendezvousAffinityFunction)3 LabeledDummyVectorizer (org.apache.ignite.ml.dataset.feature.extractor.impl.LabeledDummyVectorizer)3 MinMaxScalerTrainer (org.apache.ignite.ml.preprocessing.minmaxscaling.MinMaxScalerTrainer)3 Test (org.junit.Test)3 List (java.util.List)2