use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class DecisionTreeFromSparkExample method main.
/**
* Run example.
*/
public static void main(String[] args) throws FileNotFoundException {
System.out.println();
System.out.println(">>> Decision Tree model loaded from Spark through serialization over partitioned 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 = TitanicUtils.readPassengersWithoutNulls(ignite);
final Vectorizer<Integer, Vector, Integer, Double> vectorizer = new DummyVectorizer<Integer>(0, 5, 6, 4).labeled(1);
DecisionTreeModel mdl = (DecisionTreeModel) SparkModelParser.parse(SPARK_MDL_PATH, SupportedSparkModels.DECISION_TREE, env);
System.out.println(">>> DT: " + mdl);
double accuracy = Evaluator.evaluate(dataCache, mdl, vectorizer, new Accuracy<>());
System.out.println("\n>>> Accuracy " + accuracy);
System.out.println("\n>>> Test Error " + (1 - accuracy));
} finally {
dataCache.destroy();
}
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel 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();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class DecisionTreeClassificationTrainerSQLTableExample method main.
/**
* Run example.
*/
public static void main(String[] args) throws IgniteCheckedException, IOException {
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.");
// Dummy cache is required to perform SQL queries.
CacheConfiguration<?, ?> cacheCfg = new CacheConfiguration<>(DUMMY_CACHE_NAME).setSqlSchema("PUBLIC");
IgniteCache<?, ?> cache = null;
try {
cache = ignite.getOrCreateCache(cacheCfg);
System.out.println(">>> Creating table with training data...");
cache.query(new SqlFieldsQuery("create table titanic_train (\n" + " passengerid int primary key,\n" + " pclass int,\n" + " survived int,\n" + " name varchar(255),\n" + " sex varchar(255),\n" + " age float,\n" + " sibsp int,\n" + " parch int,\n" + " ticket varchar(255),\n" + " fare float,\n" + " cabin varchar(255),\n" + " embarked varchar(255)\n" + ") with \"template=partitioned\";")).getAll();
System.out.println(">>> Creating table with test data...");
cache.query(new SqlFieldsQuery("create table titanic_test (\n" + " passengerid int primary key,\n" + " pclass int,\n" + " survived int,\n" + " name varchar(255),\n" + " sex varchar(255),\n" + " age float,\n" + " sibsp int,\n" + " parch int,\n" + " ticket varchar(255),\n" + " fare float,\n" + " cabin varchar(255),\n" + " embarked varchar(255)\n" + ") with \"template=partitioned\";")).getAll();
loadTitanicDatasets(ignite, cache);
System.out.println(">>> Prepare trainer...");
DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(4, 0);
System.out.println(">>> Perform training...");
DecisionTreeModel mdl = trainer.fit(new SqlDatasetBuilder(ignite, "SQL_PUBLIC_TITANIC_TRAIN"), new BinaryObjectVectorizer<>("pclass", "age", "sibsp", "parch", "fare").withFeature("sex", BinaryObjectVectorizer.Mapping.create().map("male", 1.0).defaultValue(0.0)).labeled("survived"));
System.out.println("Tree is here: " + mdl.toString(true));
System.out.println(">>> Perform inference...");
try (QueryCursor<List<?>> cursor = cache.query(new SqlFieldsQuery("select " + "pclass, " + "sex, " + "age, " + "sibsp, " + "parch, " + "fare from titanic_test"))) {
for (List<?> passenger : cursor) {
Vector input = VectorUtils.of(new Double[] { asDouble(passenger.get(0)), "male".equals(passenger.get(1)) ? 1.0 : 0.0, asDouble(passenger.get(2)), asDouble(passenger.get(3)), asDouble(passenger.get(4)), asDouble(passenger.get(5)) });
double prediction = mdl.predict(input);
System.out.printf("Passenger %s will %s.\n", passenger, prediction == 0 ? "die" : "survive");
}
}
System.out.println(">>> Example completed.");
} finally {
cache.query(new SqlFieldsQuery("DROP TABLE titanic_train"));
cache.query(new SqlFieldsQuery("DROP TABLE titanic_test"));
cache.destroy();
}
} finally {
System.out.flush();
}
}
use of org.apache.ignite.ml.tree.DecisionTreeModel in project ignite by apache.
the class EncoderExampleWithNormalization 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).fillObjectCacheWithDoubleLabels(MLSandboxDatasets.MUSHROOMS);
final Vectorizer<Integer, Object[], Integer, Object> vectorizer = new ObjectArrayVectorizer<Integer>(1, 2, 3).labeled(0);
Preprocessor<Integer, Object[]> encoderPreprocessor = new EncoderTrainer<Integer, Object[]>().withEncoderType(EncoderType.STRING_ENCODER).withEncodedFeature(0).withEncodedFeature(1).withEncodedFeature(2).fit(ignite, dataCache, vectorizer);
// Defines second preprocessor that normalizes features.
Preprocessor<Integer, Object[]> normalizer = new NormalizationTrainer<Integer, Object[]>().withP(1).fit(ignite, dataCache, encoderPreprocessor);
DecisionTreeClassificationTrainer trainer = new DecisionTreeClassificationTrainer(5, 0);
// Train decision tree model.
DecisionTreeModel mdl = trainer.fit(ignite, dataCache, normalizer);
System.out.println("\n>>> Trained model: " + mdl);
double accuracy = Evaluator.evaluate(dataCache, mdl, normalizer, 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_13_RandomSearch method main.
/**
* Run example.
*/
public static void main(String[] args) {
System.out.println();
System.out.println(">>> Tutorial step 13 (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 hyperparams 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).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 13 (Random Search) example completed.");
} catch (FileNotFoundException e) {
e.printStackTrace();
}
} finally {
System.out.flush();
}
}
Aggregations