/**
* Extract (dense) rows from given chunks, one Vec at a time - should be slightly faster than
* per-row
*
* @param chunks - chunk of dataset
* @return array of dense rows
*/
public final Row[] extractDenseRowsVertical(Chunk[] chunks) {
Row[] rows = new Row[chunks[0]._len];
for (int i = 0; i < rows.length; ++i) {
rows[i] = new Row(false, _nums, _cats, _responses, 0);
rows[i].rid = chunks[0].start() + i;
if (_offset) {
rows[i].offset = chunks[offsetChunkId()].atd(i);
if (Double.isNaN(rows[i].offset)) rows[i].bad = true;
}
if (_weights) {
rows[i].weight = chunks[weightChunkId()].atd(i);
if (Double.isNaN(rows[i].weight)) rows[i].bad = true;
}
}
for (int i = 0; i < _cats; ++i) {
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
if (chunks[i].isNA(r)) {
if (_skipMissing) {
row.bad = true;
} else
row.binIds[row.nBins++] =
_catOffsets[i + 1] - 1; // missing value turns into extra (last) factor
} else {
int c = getCategoricalId(i, (int) chunks[i].at8(r));
if (c >= 0) row.binIds[row.nBins++] = c;
}
}
}
int numStart = numStart();
// generic numbers
for (int cid = 0; cid < _nums; ++cid) {
Chunk c = chunks[_cats + cid];
for (int r = 0; r < c._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
if (c.isNA(r)) row.bad = _skipMissing;
double d = c.atd(r);
if (_normMul != null && _normSub != null) // either none or both
d = (d - _normSub[cid]) * _normMul[cid];
row.numVals[numStart + cid] = d;
}
}
// response(s)
for (int i = 1; i <= _responses; ++i) {
Chunk rChunk = chunks[responseChunkId()];
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
row.response[row.response.length - i] = rChunk.atd(r);
if (_normRespMul != null) {
row.response[i - 1] = (row.response[i - 1] - _normRespSub[i - 1]) * _normRespMul[i - 1];
}
if (Double.isNaN(row.response[row.response.length - i])) row.bad = true;
}
}
return rows;
}
@Override
public void map(Chunk response, Chunk weight, Chunk offset) {
for (int i = 0; i < response._len; ++i) {
if (response.isNA(i)) continue;
double w = weight.atd(i);
if (w == 0) continue;
double y = response.atd(i);
double o = offset.atd(i);
_num += _dist.initFNum(w, o, y);
_denom += _dist.initFDenom(w, o);
}
}
@Override
public void map(Chunk c, Chunk w) {
for (int i = 0; i < c.len(); ++i)
if (!c.isNA(i)) {
double wt = w.atd(i);
// For now: let the user give small weights, results are probably not very good
// (same as for wtd.quantile in R)
// if (wt > 0 && wt < 1) throw new H2OIllegalArgumentException("Quantiles only
// accepts weights that are either 0 or >= 1.");
sum += wt;
}
}
@Override
public void map(Chunk chks[]) {
Chunk cy = chk_resp(chks);
for (int i = 0; i < cy._len; i++) {
if (cy.isNA(i)) continue;
if (isClassifier()) {
int cls = (int) cy.at8(i);
chk_work(chks, cls).set(i, 1L);
} else {
float pred = (float) cy.atd(i);
chk_work(chks, 0).set(i, pred);
}
}
}
public final Row extractDenseRow(Chunk[] chunks, int rid, Row row) {
row.bad = false;
row.rid = rid + chunks[0].start();
if (_weights) row.weight = chunks[weightChunkId()].atd(rid);
if (row.weight == 0) return row;
if (_skipMissing)
for (Chunk c : chunks)
if (c.isNA(rid)) {
row.bad = true;
return row;
}
int nbins = 0;
for (int i = 0; i < _cats; ++i) {
if (chunks[i].isNA(rid)) {
if (_imputeMissing) {
int c = getCategoricalId(i, _catModes[i]);
if (c >= 0) row.binIds[nbins++] = c;
} else // TODO: What if missingBucket = false?
row.binIds[nbins++] =
_catOffsets[i + 1] - 1; // missing value turns into extra (last) factor
} else {
int c = getCategoricalId(i, (int) chunks[i].at8(rid));
if (c >= 0) row.binIds[nbins++] = c;
}
}
row.nBins = nbins;
final int n = _nums;
for (int i = 0; i < n; ++i) {
double d = chunks[_cats + i].atd(rid); // can be NA if skipMissing() == false
if (_imputeMissing && Double.isNaN(d)) d = _numMeans[i];
if (_normMul != null && _normSub != null) d = (d - _normSub[i]) * _normMul[i];
row.numVals[i] = d;
}
for (int i = 0; i < _responses; ++i) {
row.response[i] = chunks[responseChunkId()].atd(rid);
if (_normRespMul != null)
row.response[i] = (row.response[i] - _normRespSub[i]) * _normRespMul[i];
if (Double.isNaN(row.response[i])) {
row.bad = true;
return row;
}
}
if (_offset) row.offset = chunks[offsetChunkId()].atd(rid);
return row;
}
@Override
public void map(Chunk cs) {
int idx = _chunkOffset + cs.cidx();
Key ckey = Vec.chunkKey(_v._key, idx);
if (_cmap != null) {
assert !cs.hasFloat()
: "Input chunk (" + cs.getClass() + ") has float, but is expected to be categorical";
NewChunk nc = new NewChunk(_v, idx);
// loop over rows and update ints for new domain mapping according to vecs[c].domain()
for (int r = 0; r < cs._len; ++r) {
if (cs.isNA(r)) nc.addNA();
else nc.addNum(_cmap[(int) cs.at8(r)], 0);
}
nc.close(_fs);
} else {
DKV.put(ckey, cs.deepCopy(), _fs, true);
}
}
@Override
public void map(Chunk[] chks) {
final Chunk y = importance ? chk_resp(chks) : null; // Response
final double[] rpred = importance ? new double[1 + _nclass] : null; // Row prediction
final double[] rowdata = importance ? new double[_ncols] : null; // Pre-allocated row data
final Chunk oobt = chk_oobt(chks); // Out-of-bag rows counter over all trees
// Iterate over all rows
for (int row = 0; row < oobt._len; row++) {
final boolean wasOOBRow = ScoreBuildHistogram.isOOBRow((int) chk_nids(chks, 0).at8(row));
// For all tree (i.e., k-classes)
for (int k = 0; k < _nclass; k++) {
final DTree tree = _trees[k];
if (tree == null) continue; // Empty class is ignored
final Chunk nids = chk_nids(chks, k); // Node-ids for this tree/class
int nid = (int) nids.at8(row); // Get Node to decide from
// Update only out-of-bag rows
// This is out-of-bag row - but we would like to track on-the-fly prediction for the row
if (wasOOBRow) {
final Chunk ct =
chk_tree(chks, k); // k-tree working column holding votes for given row
nid = ScoreBuildHistogram.oob2Nid(nid);
if (tree.node(nid) instanceof UndecidedNode) // If we bottomed out the tree
nid = tree.node(nid).pid(); // Then take parent's decision
int leafnid;
if (tree.root() instanceof LeafNode) {
leafnid = 0;
} else {
DecidedNode dn = tree.decided(nid); // Must have a decision point
if (dn._split.col() == -1) // Unable to decide?
dn = tree.decided(tree.node(nid).pid()); // Then take parent's decision
leafnid = dn.ns(chks, row); // Decide down to a leafnode
}
// Setup Tree(i) - on the fly prediction of i-tree for row-th row
// - for classification: cumulative number of votes for this row
// - for regression: cumulative sum of prediction of each tree - has to be
// normalized by number of trees
double prediction =
((LeafNode) tree.node(leafnid))
.pred(); // Prediction for this k-class and this row
if (importance)
rpred[1 + k] = (float) prediction; // for both regression and classification
ct.set(row, (float) (ct.atd(row) + prediction));
}
// reset help column for this row and this k-class
nids.set(row, 0);
} /* end of k-trees iteration */
// For this tree this row is out-of-bag - i.e., a tree voted for this row
if (wasOOBRow) oobt.set(row, oobt.atd(row) + 1); // track number of trees
if (importance) {
if (wasOOBRow && !y.isNA(row)) {
if (isClassifier()) {
int treePred = getPrediction(rpred, data_row(chks, row, rowdata), _threshold);
int actuPred = (int) y.at8(row);
if (treePred == actuPred) rightVotes++; // No miss !
} else { // regression
double treePred = rpred[1];
double actuPred = y.atd(row);
sse += (actuPred - treePred) * (actuPred - treePred);
}
allRows++;
}
}
}
}
@Override
public void map(Chunk chks[]) {
Chunk ys = chk_resp(chks);
for (int row = 0; row < ys._len; row++)
if (ys.isNA(row)) for (int t = 0; t < _nclass; t++) chk_nids(chks, t).set(row, -1);
}
/**
* Extract (sparse) rows from given chunks. Note: 0 remains 0 - _normSub of DataInfo isn't used
* (mean shift during standarization is not reverted) - UNLESS offset is specified (for GLM only)
* Essentially turns the dataset 90 degrees.
*
* @param chunks - chunk of dataset
* @param offset - adjustment for 0s if running with on-the-fly standardization (i.e. zeros are
* not really zeros because of centering)
* @return array of sparse rows
*/
public final Row[] extractSparseRows(Chunk[] chunks, double offset) {
Row[] rows = new Row[chunks[0]._len];
for (int i = 0; i < rows.length; ++i) {
rows[i] = new Row(true, Math.min(_nums, 16), _cats, _responses, offset);
rows[i].rid = chunks[0].start() + i;
if (_offset) {
rows[i].offset = chunks[offsetChunkId()].atd(i);
if (Double.isNaN(rows[i].offset)) rows[i].bad = true;
}
if (_weights) {
rows[i].weight = chunks[weightChunkId()].atd(i);
if (Double.isNaN(rows[i].weight)) rows[i].bad = true;
}
}
// categoricals
for (int i = 0; i < _cats; ++i) {
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
if (chunks[i].isNA(r)) {
if (_skipMissing) {
row.bad = true;
} else
row.binIds[row.nBins++] =
_catOffsets[i + 1] - 1; // missing value turns into extra (last) factor
} else {
int c = getCategoricalId(i, (int) chunks[i].at8(r));
if (c >= 0) row.binIds[row.nBins++] = c;
}
}
}
int numStart = numStart();
// generic numbers
for (int cid = 0; cid < _nums; ++cid) {
Chunk c = chunks[_cats + cid];
int oldRow = -1;
for (int r = c.nextNZ(-1); r < c._len; r = c.nextNZ(r)) {
if (c.atd(r) == 0) continue;
assert r > oldRow;
oldRow = r;
Row row = rows[r];
if (row.bad) continue;
if (c.isNA(r)) row.bad = _skipMissing;
double d = c.atd(r);
if (_normMul != null) d *= _normMul[cid];
row.addNum(cid + numStart, d);
}
}
// response(s)
for (int i = 1; i <= _responses; ++i) {
Chunk rChunk = chunks[responseChunkId()];
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
row.response[row.response.length - i] = rChunk.atd(r);
if (_normRespMul != null) {
row.response[i - 1] = (row.response[i - 1] - _normRespSub[i - 1]) * _normRespMul[i - 1];
}
if (Double.isNaN(row.response[row.response.length - i])) row.bad = true;
}
}
return rows;
}
/**
* Extract (sparse) rows from given chunks. Note: 0 remains 0 - _normSub of DataInfo isn't used
* (mean shift during standarization is not reverted) - UNLESS offset is specified (for GLM only)
* Essentially turns the dataset 90 degrees.
*
* @param chunks - chunk of dataset
* @return array of sparse rows
*/
public final Row[] extractSparseRows(Chunk[] chunks) {
Row[] rows = new Row[chunks[0]._len];
long startOff = chunks[0].start();
for (int i = 0; i < rows.length; ++i) {
rows[i] =
new Row(
true,
Math.min(_nums, 16),
_cats,
_responses,
i,
startOff); // if sparse, _nums is the correct number of nonzero values! i.e., do not
// use numNums()
rows[i].rid = chunks[0].start() + i;
if (_offset) {
rows[i].offset = chunks[offsetChunkId()].atd(i);
if (Double.isNaN(rows[i].offset)) rows[i].bad = true;
}
if (_weights) {
rows[i].weight = chunks[weightChunkId()].atd(i);
if (Double.isNaN(rows[i].weight)) rows[i].bad = true;
}
if (_skipMissing) {
int N = _cats + _nums;
for (int c = 0; c < N; ++c) if (chunks[c].isNA(i)) rows[i].bad = true;
}
}
// categoricals
for (int i = 0; i < _cats; ++i) {
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
int cid = getCategoricalId(i, chunks[i].isNA(r) ? _catModes[i] : (int) chunks[i].at8(r));
if (cid >= 0) row.binIds[row.nBins++] = cid;
}
}
// generic numbers + interactions
int interactionOffset = 0;
for (int cid = 0; cid < _nums; ++cid) {
Chunk c = chunks[_cats + cid];
int oldRow = -1;
if (c
instanceof
InteractionWrappedVec
.InteractionWrappedChunk) { // for each row, only 1 value in an interaction is 'hot'
// all other values are off (i.e., are 0)
for (int r = 0;
r < c._len;
++r) { // the vec is "vertically" dense and "horizontally" sparse (i.e., every row has
// one, and only one, value)
Row row = rows[r];
if (row.bad) continue;
if (c.isNA(r)) row.bad = _skipMissing;
int cidVirtualOffset =
getInteractionOffset(
chunks, _cats + cid, r); // the "virtual" offset into the hot-expanded interaction
row.addNum(
_numOffsets[cid] + cidVirtualOffset,
c.atd(r)); // FIXME: if this produces a "true" NA then should sub with mean? with?
}
interactionOffset += nextNumericIdx(cid);
} else {
for (int r = c.nextNZ(-1); r < c._len; r = c.nextNZ(r)) {
if (c.atd(r) == 0) continue;
assert r > oldRow;
oldRow = r;
Row row = rows[r];
if (row.bad) continue;
if (c.isNA(r)) row.bad = _skipMissing;
double d = c.atd(r);
if (Double.isNaN(d)) d = _numMeans[cid];
if (_normMul != null) d *= _normMul[interactionOffset];
row.addNum(_numOffsets[cid], d);
}
interactionOffset++;
}
}
// response(s)
for (int i = 1; i <= _responses; ++i) {
int rid = responseChunkId(i - 1);
Chunk rChunk = chunks[rid];
for (int r = 0; r < chunks[0]._len; ++r) {
Row row = rows[r];
if (row.bad) continue;
row.response[i - 1] = rChunk.atd(r);
if (_normRespMul != null) {
row.response[i - 1] = (row.response[i - 1] - _normRespSub[i - 1]) * _normRespMul[i - 1];
}
if (Double.isNaN(row.response[row.response.length - i])) row.bad = true;
}
}
return rows;
}
