Examples with ValFrame water.rapids.vals.ValFrame used on opensource projects

Example 6 with ValFrame

use of water.rapids.vals.ValFrame in project h2o-3 by h2oai.

the class AstRowSlice method apply.

@Override
public ValFrame apply(Env env, Env.StackHelp stk, AstRoot[] asts) {
    Frame fr = stk.track(asts[1].exec(env)).getFrame();
    Frame returningFrame;
    long nrows = fr.numRows();
    if (asts[2] instanceof AstNumList) {
        final AstNumList nums = (AstNumList) asts[2];
        if (!nums._isSort && !nums.isEmpty() && nums._bases[0] >= 0)
            throw new IllegalArgumentException("H2O does not currently reorder rows, please sort your row selection first");
        long[] rows = (nums._isList || nums.min() < 0) ? nums.expand8Sort() : null;
        if (rows != null) {
            if (rows.length == 0) {
            // Empty inclusion list?
            } else if (rows[0] >= 0) {
                // Positive (inclusion) list
                if (rows[rows.length - 1] > nrows)
                    throw new IllegalArgumentException("Row must be an integer from 0 to " + (nrows - 1));
            } else {
                // Negative (exclusion) list
                if (rows[rows.length - 1] >= 0)
                    throw new IllegalArgumentException("Cannot mix negative and postive row selection");
                // Invert the list to make a positive list, ignoring out-of-bounds values
                BitSet bs = new BitSet((int) nrows);
                for (long row : rows) {
                    // The positive index
                    int idx = (int) (-row - 1);
                    if (idx >= 0 && idx < nrows)
                        // Set column to EXCLUDE
                        bs.set(idx);
                }
                rows = new long[(int) nrows - bs.cardinality()];
                for (int i = bs.nextClearBit(0), j = 0; i < nrows; i = bs.nextClearBit(i + 1)) rows[j++] = i;
            }
        }
        final long[] ls = rows;
        returningFrame = new MRTask() {

            @Override
            public void map(Chunk[] cs, NewChunk[] ncs) {
                if (nums.cnt() == 0)
                    return;
                if (ls != null && ls.length == 0)
                    return;
                long start = cs[0].start();
                long end = start + cs[0]._len;
                // exclusive max to inclusive max when stride == 1
                long min = ls == null ? (long) nums.min() : ls[0], max = ls == null ? (long) nums.max() - 1 : ls[ls.length - 1];
                //5                   [ nums ]  nums run rite:  start <= nums.min() && end < nums.max()
                if (!(max < start || min > end)) {
                    // not situation 1 or 2 above
                    // situation 4 and 5 => min > start;
                    long startOffset = (min > start ? min : start);
                    for (int i = (int) (startOffset - start); i < cs[0]._len; ++i) {
                        if ((ls == null && nums.has(start + i)) || (ls != null && Arrays.binarySearch(ls, start + i) >= 0)) {
                            for (int c = 0; c < cs.length; ++c) {
                                if (cs[c] instanceof CStrChunk)
                                    ncs[c].addStr(cs[c], i);
                                else if (cs[c] instanceof C16Chunk)
                                    ncs[c].addUUID(cs[c], i);
                                else if (cs[c].isNA(i))
                                    ncs[c].addNA();
                                else
                                    ncs[c].addNum(cs[c].atd(i));
                            }
                        }
                    }
                }
            }
        }.doAll(fr.types(), fr).outputFrame(fr.names(), fr.domains());
    } else if ((asts[2] instanceof AstNum)) {
        long[] rows = new long[] { (long) (((AstNum) asts[2]).getNum()) };
        returningFrame = fr.deepSlice(rows, null);
    } else if ((asts[2] instanceof AstExec) || (asts[2] instanceof AstId)) {
        Frame predVec = stk.track(asts[2].exec(env)).getFrame();
        if (predVec.numCols() != 1)
            throw new IllegalArgumentException("Conditional Row Slicing Expression evaluated to " + predVec.numCols() + " columns.  Must be a boolean Vec.");
        returningFrame = fr.deepSlice(predVec, null);
    } else
        throw new IllegalArgumentException("Row slicing requires a number-list as the last argument, but found a " + asts[2].getClass());
    return new ValFrame(returningFrame);
}

Example 7 with ValFrame

use of water.rapids.vals.ValFrame in project h2o-3 by h2oai.

the class AstScale method apply.

@Override
public ValFrame apply(Env env, Env.StackHelp stk, AstRoot[] asts) {
    Frame fr = stk.track(asts[1].exec(env)).getFrame();
    int ncols = fr.numCols();
    // Peel out the bias/shift/mean
    double[] means;
    if (asts[2] instanceof AstNumList) {
        means = ((AstNumList) asts[2]).expand();
        if (means.length != ncols)
            throw new IllegalArgumentException("Numlist must be the same length as the columns of the Frame");
    } else {
        double d = asts[2].exec(env).getNum();
        if (// No change on means, so zero-filled
        d == 0)
            // No change on means, so zero-filled
            means = new double[ncols];
        else if (d == 1)
            means = fr.means();
        else
            throw new IllegalArgumentException("Only true or false allowed");
    }
    // Peel out the scale/stddev
    double[] mults;
    if (asts[3] instanceof AstNumList) {
        mults = ((AstNumList) asts[3]).expand();
        if (mults.length != ncols)
            throw new IllegalArgumentException("Numlist must be the same length as the columns of the Frame");
    } else {
        Val v = asts[3].exec(env);
        if (v instanceof ValFrame) {
            mults = toArray(v.getFrame().anyVec());
        } else {
            double d = v.getNum();
            if (d == 0)
                // No change on mults, so one-filled
                Arrays.fill(mults = new double[ncols], 1.0);
            else if (d == 1)
                mults = fr.mults();
            else
                throw new IllegalArgumentException("Only true or false allowed");
        }
    }
    // Update in-place.
    // Make final copy for closure
    final double[] fmeans = means;
    // Make final copy for closure
    final double[] fmults = mults;
    new MRTask() {

        @Override
        public void map(Chunk[] cs) {
            for (int i = 0; i < cs.length; i++) for (int row = 0; row < cs[i]._len; row++) cs[i].set(row, (cs[i].atd(row) - fmeans[i]) * fmults[i]);
        }
    }.doAll(fr);
    return new ValFrame(fr);
}

Example 8 with ValFrame

use of water.rapids.vals.ValFrame in project h2o-3 by h2oai.

the class AstSetDomain method apply.

@Override
public ValFrame apply(Env env, Env.StackHelp stk, AstRoot[] asts) {
    Frame f = stk.track(asts[1].exec(env)).getFrame();
    String[] _domains = ((AstStrList) asts[2])._strs;
    if (f.numCols() != 1)
        throw new IllegalArgumentException("Must be a single column. Got: " + f.numCols() + " columns.");
    Vec v = f.anyVec();
    if (!v.isCategorical())
        throw new IllegalArgumentException("Vector must be a factor column. Got: " + v.get_type_str());
    if (_domains != null && _domains.length != v.domain().length) {
        // in this case we want to recollect the domain and check that number of levels matches _domains
        VecUtils.CollectDomainFast t = new VecUtils.CollectDomainFast((int) v.max());
        t.doAll(v);
        final long[] dom = t.domain();
        if (dom.length != _domains.length)
            throw new IllegalArgumentException("Number of replacement factors must equal current number of levels. Current number of levels: " + dom.length + " != " + _domains.length);
        new MRTask() {

            @Override
            public void map(Chunk c) {
                for (int i = 0; i < c._len; ++i) {
                    if (!c.isNA(i)) {
                        long num = Arrays.binarySearch(dom, c.at8(i));
                        if (num < 0)
                            throw new IllegalArgumentException("Could not find the categorical value!");
                        c.set(i, num);
                    }
                }
            }
        }.doAll(v);
    }
    v.setDomain(_domains);
    DKV.put(v);
    return new ValFrame(f);
}

Example 9 with ValFrame

use of water.rapids.vals.ValFrame in project h2o-3 by h2oai.

the class AstBinOp method frame_op_frame.

/**
   * Auto-widen: If one frame has only 1 column, auto-widen that 1 column to
   * the rest.  Otherwise the frames must have the same column count, and
   * auto-widen element-by-element.  Short-cut if one frame has zero
   * columns.
   */
private ValFrame frame_op_frame(Frame lf, Frame rt) {
    if (lf.numRows() != rt.numRows()) {
        // special case for broadcasting a single row of data across a frame
        if (lf.numRows() == 1 || rt.numRows() == 1) {
            if (lf.numCols() != rt.numCols())
                throw new IllegalArgumentException("Frames must have same columns, found " + lf.numCols() + " columns and " + rt.numCols() + " columns.");
            return frame_op_row(lf, rt);
        } else
            throw new IllegalArgumentException("Frames must have same rows, found " + lf.numRows() + " rows and " + rt.numRows() + " rows.");
    }
    if (lf.numCols() == 0)
        return new ValFrame(lf);
    if (rt.numCols() == 0)
        return new ValFrame(rt);
    if (lf.numCols() == 1 && rt.numCols() > 1)
        return vec_op_frame(lf.vecs()[0], rt);
    if (rt.numCols() == 1 && lf.numCols() > 1)
        return frame_op_vec(lf, rt.vecs()[0]);
    if (lf.numCols() != rt.numCols())
        throw new IllegalArgumentException("Frames must have same columns, found " + lf.numCols() + " columns and " + rt.numCols() + " columns.");
    Frame res = new MRTask() {

        @Override
        public void map(Chunk[] chks, NewChunk[] cress) {
            BufferedString lfstr = new BufferedString();
            BufferedString rtstr = new BufferedString();
            assert (cress.length << 1) == chks.length;
            for (int c = 0; c < cress.length; c++) {
                Chunk clf = chks[c];
                Chunk crt = chks[c + cress.length];
                NewChunk cres = cress[c];
                if (clf.vec().isString())
                    for (int i = 0; i < clf._len; i++) cres.addNum(str_op(clf.atStr(lfstr, i), crt.atStr(rtstr, i)));
                else
                    for (int i = 0; i < clf._len; i++) cres.addNum(op(clf.atd(i), crt.atd(i)));
            }
        }
    }.doAll(lf.numCols(), Vec.T_NUM, new Frame(lf).add(rt)).outputFrame(lf._names, null);
    // Cleanup categorical misuse
    return cleanCategorical(lf, res);
}

Example 10 with ValFrame

use of water.rapids.vals.ValFrame in project h2o-3 by h2oai.

the class AstBinOp method frame_op_vec.

private ValFrame frame_op_vec(Frame fr, Vec vec) {
    // Already checked for same rows, non-zero frame
    Frame lf = new Frame(fr);
    lf.add("", vec);
    Frame res = new MRTask() {

        @Override
        public void map(Chunk[] chks, NewChunk[] cress) {
            assert cress.length == chks.length - 1;
            Chunk crt = chks[cress.length];
            for (int c = 0; c < cress.length; c++) {
                Chunk clf = chks[c];
                NewChunk cres = cress[c];
                for (int i = 0; i < clf._len; i++) cres.addNum(op(clf.atd(i), crt.atd(i)));
            }
        }
    }.doAll(fr.numCols(), Vec.T_NUM, lf).outputFrame(fr._names, null);
    // Cleanup categorical misuse
    return cleanCategorical(fr, res);
}