Examples with Chunk water.fvec.Chunk used on opensource projects

Example 6 with Chunk

use of water.fvec.Chunk in project h2o-3 by h2oai.

the class KMeansModel method predictScoreImpl.

@Override
protected Frame predictScoreImpl(Frame orig, Frame adaptedFr, String destination_key, final Job j, boolean computeMetrics) {
    if (!_parms._pred_indicator) {
        return super.predictScoreImpl(orig, adaptedFr, destination_key, j, computeMetrics);
    } else {
        final int len = _output._k[_output._k.length - 1];
        String prefix = "cluster_";
        Frame adaptFrm = new Frame(adaptedFr);
        for (int c = 0; c < len; c++) adaptFrm.add(prefix + Double.toString(c + 1), adaptFrm.anyVec().makeZero());
        new MRTask() {

            @Override
            public void map(Chunk[] chks) {
                if (isCancelled() || j != null && j.stop_requested())
                    return;
                double[] tmp = new double[_output._names.length];
                double[] preds = new double[len];
                for (int row = 0; row < chks[0]._len; row++) {
                    Arrays.fill(preds, 0);
                    double[] p = score_indicator(chks, row, tmp, preds);
                    for (int c = 0; c < preds.length; c++) chks[_output._names.length + c].set(row, p[c]);
                }
                if (j != null)
                    j.update(1);
            }
        }.doAll(adaptFrm);
        // Return the predicted columns
        int x = _output._names.length, y = adaptFrm.numCols();
        // this will call vec_impl() and we cannot call the delete() below just yet
        Frame f = adaptFrm.extractFrame(x, y);
        f = new Frame(Key.<Frame>make(destination_key), f.names(), f.vecs());
        DKV.put(f);
        makeMetricBuilder(null).makeModelMetrics(this, orig, null, null);
        return f;
    }
}

Example 7 with Chunk

use of water.fvec.Chunk in project h2o-3 by h2oai.

the class PCAModel method predictScoreImpl.

@Override
protected Frame predictScoreImpl(Frame orig, Frame adaptedFr, String destination_key, final Job j, boolean computeMetrics) {
    Frame adaptFrm = new Frame(adaptedFr);
    for (int i = 0; i < _parms._k; i++) adaptFrm.add("PC" + String.valueOf(i + 1), adaptFrm.anyVec().makeZero());
    new MRTask() {

        @Override
        public void map(Chunk[] chks) {
            if (isCancelled() || j != null && j.stop_requested())
                return;
            double[] tmp = new double[_output._names.length];
            double[] preds = new double[_parms._k];
            for (int row = 0; row < chks[0]._len; row++) {
                double[] p = score0(chks, row, tmp, preds);
                for (int c = 0; c < preds.length; c++) chks[_output._names.length + c].set(row, p[c]);
            }
            if (j != null)
                j.update(1);
        }
    }.doAll(adaptFrm);
    // Return the projection into principal component space
    int x = _output._names.length, y = adaptFrm.numCols();
    // this will call vec_impl() and we cannot call the delete() below just yet
    Frame f = adaptFrm.extractFrame(x, y);
    f = new Frame(Key.<Frame>make(destination_key), f.names(), f.vecs());
    DKV.put(f);
    makeMetricBuilder(null).makeModelMetrics(this, orig, null, null);
    return f;
}

Example 8 with Chunk

use of water.fvec.Chunk in project h2o-3 by h2oai.

the class AggregatorModel method scoreExemplarMembers.

@Override
public Frame scoreExemplarMembers(Key<Frame> destination_key, final int exemplarIdx) {
    Vec booleanCol = new MRTask() {

        @Override
        public void map(Chunk c, NewChunk nc) {
            for (int i = 0; i < c._len; ++i) nc.addNum(c.at8(i) == _exemplars[exemplarIdx].gid ? 1 : 0, 0);
        }
    }.doAll(Vec.T_NUM, new Frame(new Vec[] { _exemplar_assignment_vec_key.get() })).outputFrame().anyVec();
    Frame orig = _parms.train();
    Vec[] vecs = Arrays.copyOf(orig.vecs(), orig.vecs().length + 1);
    vecs[vecs.length - 1] = booleanCol;
    Frame ff = new Frame(orig.names(), orig.vecs());
    ff.add("predicate", booleanCol);
    Frame res = new Frame.DeepSelect().doAll(orig.types(), ff).outputFrame(destination_key, orig.names(), orig.domains());
    FrameUtils.shrinkDomainsToObservedSubset(res);
    DKV.put(res);
    assert (res.numRows() == _counts[exemplarIdx]);
    booleanCol.remove();
    return res;
}

Example 9 with Chunk

use of water.fvec.Chunk in project h2o-3 by h2oai.

the class AggregatorModel method createFrameOfExemplars.

public Frame createFrameOfExemplars(Frame orig, Key destination_key) {
    final long[] keep = new long[_exemplars.length];
    for (int i = 0; i < keep.length; ++i) keep[i] = _exemplars[i].gid;
    Vec exAssignment = _exemplar_assignment_vec_key.get();
    // preserve the original row order
    Vec booleanCol = new MRTask() {

        @Override
        public void map(Chunk c, Chunk c2) {
            for (int i = 0; i < keep.length; ++i) {
                if (keep[i] < c.start())
                    continue;
                if (keep[i] >= c.start() + c._len)
                    continue;
                c2.set((int) (keep[i] - c.start()), 1);
            }
        }
    }.doAll(new Frame(new Vec[] { exAssignment, exAssignment.makeZero() }))._fr.vec(1);
    Vec[] vecs = Arrays.copyOf(orig.vecs(), orig.vecs().length + 1);
    vecs[vecs.length - 1] = booleanCol;
    Frame ff = new Frame(orig.names(), orig.vecs());
    ff.add("predicate", booleanCol);
    Frame res = new Frame.DeepSelect().doAll(orig.types(), ff).outputFrame(destination_key, orig.names(), orig.domains());
    FrameUtils.shrinkDomainsToObservedSubset(res);
    booleanCol.remove();
    assert (res.numRows() == _exemplars.length);
    Vec cnts = res.anyVec().makeZero();
    Vec.Writer vw = cnts.open();
    for (int i = 0; i < _counts.length; ++i) vw.set(i, _counts[i]);
    vw.close();
    res.add("counts", cnts);
    DKV.put(destination_key, res);
    return res;
}

Example 10 with Chunk

use of water.fvec.Chunk in project h2o-3 by h2oai.

the class GBMTest method testNfoldsColumnNumbersFrom0.

@Test
public void testNfoldsColumnNumbersFrom0() {
    Frame tfr = null;
    Vec old = null;
    GBMModel gbm1 = null;
    try {
        tfr = parse_test_file("smalldata/junit/cars_20mpg.csv");
        // Remove unique id
        tfr.remove("name").remove();
        new MRTask() {

            @Override
            public void map(Chunk c) {
                for (int i = 0; i < c.len(); ++i) {
                    if (c.at8(i) == 3)
                        c.set(i, 0);
                    if (c.at8(i) == 4)
                        c.set(i, 1);
                    if (c.at8(i) == 5)
                        c.set(i, 2);
                    if (c.at8(i) == 6)
                        c.set(i, 3);
                    if (c.at8(i) == 8)
                        c.set(i, 4);
                }
            }
        }.doAll(tfr.vec("cylinders"));
        DKV.put(tfr);
        GBMModel.GBMParameters parms = new GBMModel.GBMParameters();
        parms._train = tfr._key;
        parms._response_column = "economy_20mpg";
        parms._fold_column = "cylinders";
        parms._ntrees = 10;
        GBM job1 = new GBM(parms);
        gbm1 = job1.trainModel().get();
        Assert.assertTrue(gbm1._output._cross_validation_models.length == 5);
    } finally {
        if (tfr != null)
            tfr.remove();
        if (old != null)
            old.remove();
        if (gbm1 != null) {
            gbm1.deleteCrossValidationModels();
            gbm1.delete();
        }
    }
}