Examples with ColumnDecisionTreeTrainerInput org.apache.ignite.ml.trees.trainers.columnbased.ColumnDecisionTreeTrainerInput used on opensource projects

Example 1 with ColumnDecisionTreeTrainerInput

use of org.apache.ignite.ml.trees.trainers.columnbased.ColumnDecisionTreeTrainerInput in project ignite by apache.

the class SplitDataGenerator method testByGen.

/**
 */
<D extends ContinuousRegionInfo> void testByGen(int totalPts, IgniteFunction<ColumnDecisionTreeTrainerInput, ? extends ContinuousSplitCalculator<D>> calc, IgniteFunction<ColumnDecisionTreeTrainerInput, IgniteFunction<DoubleStream, Double>> catImpCalc, IgniteFunction<DoubleStream, Double> regCalc, Ignite ignite) {
    List<IgniteBiTuple<Integer, V>> lst = points(totalPts, (i, rn) -> i).collect(Collectors.toList());
    Collections.shuffle(lst, rnd);
    SparseDistributedMatrix m = new SparseDistributedMatrix(totalPts, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    Map<Integer, List<LabeledVectorDouble>> byRegion = new HashMap<>();
    int i = 0;
    for (IgniteBiTuple<Integer, V> bt : lst) {
        byRegion.putIfAbsent(bt.get1(), new LinkedList<>());
        byRegion.get(bt.get1()).add(asLabeledVector(bt.get2().getStorage().data()));
        m.setRow(i, bt.get2().getStorage().data());
        i++;
    }
    ColumnDecisionTreeTrainer<D> trainer = new ColumnDecisionTreeTrainer<>(3, calc, catImpCalc, regCalc, ignite);
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, catFeaturesInfo));
    byRegion.keySet().forEach(k -> mdl.apply(byRegion.get(k).get(0).features()));
}

Example 2 with ColumnDecisionTreeTrainerInput

use of org.apache.ignite.ml.trees.trainers.columnbased.ColumnDecisionTreeTrainerInput in project ignite by apache.

the class ColumnDecisionTreeTrainerTest method testByGen.

/**
 */
private <D extends ContinuousRegionInfo> void testByGen(int totalPts, HashMap<Integer, Integer> catsInfo, SplitDataGenerator<DenseLocalOnHeapVector> gen, IgniteFunction<ColumnDecisionTreeTrainerInput, ? extends ContinuousSplitCalculator<D>> calc, IgniteFunction<ColumnDecisionTreeTrainerInput, IgniteFunction<DoubleStream, Double>> catImpCalc, IgniteFunction<DoubleStream, Double> regCalc, Random rnd) {
    List<IgniteBiTuple<Integer, DenseLocalOnHeapVector>> lst = gen.points(totalPts, (i, rn) -> i).collect(Collectors.toList());
    int featCnt = gen.featuresCnt();
    Collections.shuffle(lst, rnd);
    SparseDistributedMatrix m = new SparseDistributedMatrix(totalPts, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    Map<Integer, List<LabeledVectorDouble>> byRegion = new HashMap<>();
    int i = 0;
    for (IgniteBiTuple<Integer, DenseLocalOnHeapVector> bt : lst) {
        byRegion.putIfAbsent(bt.get1(), new LinkedList<>());
        byRegion.get(bt.get1()).add(asLabeledVector(bt.get2().getStorage().data()));
        m.setRow(i, bt.get2().getStorage().data());
        i++;
    }
    ColumnDecisionTreeTrainer<D> trainer = new ColumnDecisionTreeTrainer<>(3, calc, catImpCalc, regCalc, ignite);
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, catsInfo));
    byRegion.keySet().forEach(k -> {
        LabeledVectorDouble sp = byRegion.get(k).get(0);
        Tracer.showAscii(sp.features());
        X.println("Actual and predicted vectors [act=" + sp.label() + " " + ", pred=" + mdl.apply(sp.features()) + "]");
        assert mdl.apply(sp.features()) == sp.doubleLabel();
    });
}