use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class Step_17_Parallel_Genetic_Programming_Search method main.
/**
* Run example.
*/
public static void main(String[] args) {
System.out.println();
System.out.println(">>> Tutorial step 17 (Parallel 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).withEnvironmentBuilder(LearningEnvironmentBuilder.defaultBuilder().withParallelismStrategyTypeDependency(ParallelismStrategy.ON_DEFAULT_POOL).withLoggingFactoryDependency(ConsoleLogger.Factory.LOW)).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 17 (Parallel Genetic Programming) example completed.");
} catch (FileNotFoundException e) {
e.printStackTrace();
}
} finally {
System.out.flush();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel 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();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel 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();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class Step_5_Scaling method main.
/**
* Run example.
*/
public static void main(String[] args) {
System.out.println();
System.out.println(">>> Tutorial step 5 (scaling) 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);
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, normalizationPreprocessor);
System.out.println("\n>>> Trained model: " + mdl);
double accuracy = Evaluator.evaluate(dataCache, mdl, normalizationPreprocessor, new Accuracy<>());
System.out.println("\n>>> Accuracy " + accuracy);
System.out.println("\n>>> Test Error " + (1 - accuracy));
System.out.println(">>> Tutorial step 5 (scaling) example completed.");
} catch (FileNotFoundException e) {
e.printStackTrace();
}
} finally {
System.out.flush();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class DecisionTreeRegressionTrainerExample method main.
/**
* Executes example.
*
* @param args Command line arguments, none required.
*/
public static void main(String... args) {
System.out.println(">>> Decision tree regression 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);
// Fill training data.
generatePoints(trainingSet);
// Create regression trainer.
DecisionTreeRegressionTrainer trainer = new DecisionTreeRegressionTrainer(10, 0);
// Train decision tree model.
DecisionTreeModel mdl = trainer.fit(ignite, trainingSet, new LabeledDummyVectorizer<>());
System.out.println(">>> Decision tree regression model: " + mdl);
System.out.println(">>> ---------------------------------");
System.out.println(">>> | Prediction\t| Ground Truth\t|");
System.out.println(">>> ---------------------------------");
// Calculate score.
for (int x = 0; x < 10; x++) {
double predicted = mdl.predict(VectorUtils.of(x));
System.out.printf(">>> | %.4f\t\t| %.4f\t\t|\n", predicted, Math.sin(x));
}
System.out.println(">>> ---------------------------------");
System.out.println(">>> Decision tree regression trainer example completed.");
} finally {
trainingSet.destroy();
}
} finally {
System.out.flush();
}
}
Aggregations