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

Example 1 with MatrixColumnDecisionTreeTrainerInput

use of org.apache.ignite.ml.trees.trainers.columnbased.MatrixColumnDecisionTreeTrainerInput 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 MatrixColumnDecisionTreeTrainerInput

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

the class ColumnDecisionTreeTrainerBenchmark method tstMNISTSparseDistributedMatrix.

/**
 * Run decision tree classifier on MNIST using sparse distributed matrix as a storage for dataset.
 * To run this test rename this method so it starts from 'test'.
 *
 * @throws IOException In case of loading MNIST dataset errors.
 */
public void tstMNISTSparseDistributedMatrix() throws IOException {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    int ptsCnt = 30_000;
    int featCnt = 28 * 28;
    Properties props = loadMNISTProperties();
    Stream<DenseLocalOnHeapVector> trainingMnistStream = MnistUtils.mnist(props.getProperty(PROP_TRAINING_IMAGES), props.getProperty(PROP_TRAINING_LABELS), new Random(123L), ptsCnt);
    Stream<DenseLocalOnHeapVector> testMnistStream = MnistUtils.mnist(props.getProperty(PROP_TEST_IMAGES), props.getProperty(PROP_TEST_LABELS), new Random(123L), 10_000);
    SparseDistributedMatrix m = new SparseDistributedMatrix(ptsCnt, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    SparseDistributedMatrixStorage sto = (SparseDistributedMatrixStorage) m.getStorage();
    loadVectorsIntoSparseDistributedMatrixCache(sto.cache().getName(), sto.getUUID(), trainingMnistStream.iterator(), featCnt + 1);
    ColumnDecisionTreeTrainer<GiniSplitCalculator.GiniData> trainer = new ColumnDecisionTreeTrainer<>(10, ContinuousSplitCalculators.GINI.apply(ignite), RegionCalculators.GINI, RegionCalculators.MOST_COMMON, ignite);
    X.println("Training started");
    long before = System.currentTimeMillis();
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, new HashMap<>()));
    X.println("Training finished in " + (System.currentTimeMillis() - before));
    IgniteTriFunction<Model<Vector, Double>, Stream<IgniteBiTuple<Vector, Double>>, Function<Double, Double>, Double> mse = Estimators.errorsPercentage();
    Double accuracy = mse.apply(mdl, testMnistStream.map(v -> new IgniteBiTuple<>(v.viewPart(0, featCnt), v.getX(featCnt))), Function.identity());
    X.println("Errors percentage: " + accuracy);
    Assert.assertEquals(0, SplitCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, FeaturesCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, ContextCache.getOrCreate(ignite).size());
    Assert.assertEquals(0, ProjectionsCache.getOrCreate(ignite).size());
}

Example 3 with MatrixColumnDecisionTreeTrainerInput

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

the class ColumnDecisionTreeTrainerBenchmark method testByGenStreamerLoad.

/**
 */
private void testByGenStreamerLoad(int ptsPerReg, HashMap<Integer, Integer> catsInfo, SplitDataGenerator<DenseLocalOnHeapVector> gen, Random rnd) {
    List<IgniteBiTuple<Integer, DenseLocalOnHeapVector>> lst = gen.points(ptsPerReg, (i, rn) -> i).collect(Collectors.toList());
    int featCnt = gen.featuresCnt();
    Collections.shuffle(lst, rnd);
    int numRegs = gen.regsCount();
    SparseDistributedMatrix m = new SparseDistributedMatrix(numRegs * ptsPerReg, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    IgniteFunction<DoubleStream, Double> regCalc = s -> s.average().orElse(0.0);
    Map<Integer, List<LabeledVectorDouble>> byRegion = new HashMap<>();
    SparseDistributedMatrixStorage sto = (SparseDistributedMatrixStorage) m.getStorage();
    long before = System.currentTimeMillis();
    X.println("Batch loading started...");
    loadVectorsIntoSparseDistributedMatrixCache(sto.cache().getName(), sto.getUUID(), gen.points(ptsPerReg, (i, rn) -> i).map(IgniteBiTuple::get2).iterator(), featCnt + 1);
    X.println("Batch loading took " + (System.currentTimeMillis() - before) + " ms.");
    for (IgniteBiTuple<Integer, DenseLocalOnHeapVector> bt : lst) {
        byRegion.putIfAbsent(bt.get1(), new LinkedList<>());
        byRegion.get(bt.get1()).add(asLabeledVector(bt.get2().getStorage().data()));
    }
    ColumnDecisionTreeTrainer<VarianceSplitCalculator.VarianceData> trainer = new ColumnDecisionTreeTrainer<>(2, ContinuousSplitCalculators.VARIANCE, RegionCalculators.VARIANCE, regCalc, ignite);
    before = System.currentTimeMillis();
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, catsInfo));
    X.println("Training took: " + (System.currentTimeMillis() - before) + " ms.");
    byRegion.keySet().forEach(k -> {
        LabeledVectorDouble sp = byRegion.get(k).get(0);
        Tracer.showAscii(sp.features());
        X.println("Predicted value and label [pred=" + mdl.apply(sp.features()) + ", label=" + sp.doubleLabel() + "]");
        assert mdl.apply(sp.features()) == sp.doubleLabel();
    });
}

Example 4 with MatrixColumnDecisionTreeTrainerInput

use of org.apache.ignite.ml.trees.trainers.columnbased.MatrixColumnDecisionTreeTrainerInput 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();
    });
}

Example 5 with MatrixColumnDecisionTreeTrainerInput

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

the class ColumnDecisionTreeTrainerBenchmark method tstF1.

/**
 * Test decision tree regression.
 * To run this test rename this method so it starts from 'test'.
 */
public void tstF1() {
    IgniteUtils.setCurrentIgniteName(ignite.configuration().getIgniteInstanceName());
    int ptsCnt = 10000;
    Map<Integer, double[]> ranges = new HashMap<>();
    ranges.put(0, new double[] { -100.0, 100.0 });
    ranges.put(1, new double[] { -100.0, 100.0 });
    ranges.put(2, new double[] { -100.0, 100.0 });
    int featCnt = 100;
    double[] defRng = { -1.0, 1.0 };
    Vector[] trainVectors = vecsFromRanges(ranges, featCnt, defRng, new Random(123L), ptsCnt, f1);
    SparseDistributedMatrix m = new SparseDistributedMatrix(ptsCnt, featCnt + 1, StorageConstants.COLUMN_STORAGE_MODE, StorageConstants.RANDOM_ACCESS_MODE);
    SparseDistributedMatrixStorage sto = (SparseDistributedMatrixStorage) m.getStorage();
    loadVectorsIntoSparseDistributedMatrixCache(sto.cache().getName(), sto.getUUID(), Arrays.stream(trainVectors).iterator(), featCnt + 1);
    IgniteFunction<DoubleStream, Double> regCalc = s -> s.average().orElse(0.0);
    ColumnDecisionTreeTrainer<VarianceSplitCalculator.VarianceData> trainer = new ColumnDecisionTreeTrainer<>(10, ContinuousSplitCalculators.VARIANCE, RegionCalculators.VARIANCE, regCalc, ignite);
    X.println("Training started.");
    long before = System.currentTimeMillis();
    DecisionTreeModel mdl = trainer.train(new MatrixColumnDecisionTreeTrainerInput(m, new HashMap<>()));
    X.println("Training finished in: " + (System.currentTimeMillis() - before) + " ms.");
    Vector[] testVectors = vecsFromRanges(ranges, featCnt, defRng, new Random(123L), 20, f1);
    IgniteTriFunction<Model<Vector, Double>, Stream<IgniteBiTuple<Vector, Double>>, Function<Double, Double>, Double> mse = Estimators.MSE();
    Double accuracy = mse.apply(mdl, Arrays.stream(testVectors).map(v -> new IgniteBiTuple<>(v.viewPart(0, featCnt), v.getX(featCnt))), Function.identity());
    X.println("MSE: " + accuracy);
}