public StringBuilder toString(StringBuilder sb, String[] fs, long idx) {
Vec vecs[] = vecs();
for (int c = 0; c < fs.length; c++) {
Vec vec = vecs[c];
if (vec.isEnum()) {
String s = "----------";
if (!vec.isNA(idx)) {
int x = (int) vec.at8(idx);
if (x >= 0 && x < vec._domain.length) s = vec._domain[x];
}
sb.append(String.format(fs[c], s));
} else if (vec.isInt()) {
if (vec.isNA(idx)) {
Chunk C = vec.elem2BV(0); // 1st Chunk
int len = C.pformat_len0(); // Printable width
for (int i = 0; i < len; i++) sb.append('-');
} else {
try {
sb.append(String.format(fs[c], vec.at8(idx)));
} catch (IllegalFormatException ife) {
System.out.println("Format: " + fs[c] + " col=" + c + " not for ints");
ife.printStackTrace();
}
}
} else {
sb.append(String.format(fs[c], vec.at(idx)));
if (vec.isNA(idx)) sb.append(' ');
}
sb.append(' '); // Column seperator
}
sb.append('\n');
return sb;
}
@Override
public void map(Chunk chks[], NewChunk nchks[]) {
long rstart = chks[0]._start;
int rlen = chks[0]._len; // Total row count
int rx = 0; // Which row to in/ex-clude
int rlo = 0; // Lo/Hi for this block of rows
int rhi = rlen;
while (true) { // Still got rows to include?
if (_rows != null) { // Got a row selector?
if (rx >= _rows.length) break; // All done with row selections
long r = _rows[rx++] - 1; // Next row selector
if (r < 0) { // Row exclusion
if (rx > 0 && _rows[rx - 1] < _rows[rx]) throw H2O.unimpl();
long er = Math.abs(r) - 2;
if (er < rstart) continue;
// scoop up all of the rows before the first exclusion
if (rx == 1 && ((int) (er + 1 - rstart)) > 0 && _ex) {
rlo = (int) rstart;
rhi = (int) (er - rstart);
_ex = false;
rx--;
} else {
rlo = (int) (er + 1 - rstart);
// TODO: handle jumbled row indices ( e.g. -c(1,5,3) )
while (rx < _rows.length && (_rows[rx] + 1 == _rows[rx - 1] && rlo < rlen)) {
if (rx < _rows.length - 1 && _rows[rx] < _rows[rx + 1]) throw H2O.unimpl();
rx++;
rlo++; // Exclude consecutive rows
}
rhi = rx >= _rows.length ? rlen : (int) Math.abs(_rows[rx] - 1) - 2;
if (rx < _rows.length - 1 && _rows[rx] < _rows[rx + 1]) throw H2O.unimpl();
}
} else { // Positive row list?
if (r < rstart) continue;
rlo = (int) (r - rstart);
rhi = rlo + 1; // Stop at the next row
while (rx < _rows.length && (_rows[rx] - 1 - rstart) == rhi && rhi < rlen) {
rx++;
rhi++; // Grab sequential rows
}
}
}
// Process this next set of rows
// For all cols in the new set
for (int i = 0; i < _cols.length; i++) {
Chunk oc = chks[_cols[i]];
NewChunk nc = nchks[i];
if (oc._vec.isInt()) { // Slice on integer columns
for (int j = rlo; j < rhi; j++)
if (oc.isNA0(j)) nc.addNA();
else nc.addNum(oc.at80(j), 0);
} else { // Slice on double columns
for (int j = rlo; j < rhi; j++) nc.addNum(oc.at0(j));
}
}
rlo = rhi;
if (_rows == null) break;
}
}
@Override
public void map(Chunk chks[], NewChunk nchks[]) {
Chunk pred = chks[chks.length - 1];
for (int i = 0; i < pred._len; ++i) {
if (pred.at0(i) != 0)
for (int j = 0; j < chks.length - 1; ++j) nchks[j].addNum(chks[j].at0(i));
}
}
/**
* Global redistribution of a Frame (balancing of chunks), done by calling process (all-to-one +
* one-to-all)
*
* @param fr Input frame
* @param seed RNG seed
* @param shuffle whether to shuffle the data globally
* @return Shuffled frame
*/
public static Frame shuffleAndBalance(
final Frame fr, int splits, long seed, final boolean local, final boolean shuffle) {
if ((fr.vecs()[0].nChunks() < splits || shuffle) && fr.numRows() > splits) {
Vec[] vecs = fr.vecs().clone();
Log.info("Load balancing dataset, splitting it into up to " + splits + " chunks.");
long[] idx = null;
if (shuffle) {
idx = new long[splits];
for (int r = 0; r < idx.length; ++r) idx[r] = r;
Utils.shuffleArray(idx, seed);
}
Key keys[] = new Vec.VectorGroup().addVecs(vecs.length);
final long rows_per_new_chunk = (long) (Math.ceil((double) fr.numRows() / splits));
// loop over cols (same indexing for each column)
Futures fs = new Futures();
for (int col = 0; col < vecs.length; col++) {
AppendableVec vec = new AppendableVec(keys[col]);
// create outgoing chunks for this col
NewChunk[] outCkg = new NewChunk[splits];
for (int i = 0; i < splits; ++i) outCkg[i] = new NewChunk(vec, i);
// loop over all incoming chunks
for (int ckg = 0; ckg < vecs[col].nChunks(); ckg++) {
final Chunk inCkg = vecs[col].chunkForChunkIdx(ckg);
// loop over local rows of incoming chunks (fast path)
for (int row = 0; row < inCkg._len; ++row) {
int outCkgIdx =
(int) ((inCkg._start + row) / rows_per_new_chunk); // destination chunk idx
if (shuffle)
outCkgIdx = (int) (idx[outCkgIdx]); // shuffle: choose a different output chunk
assert (outCkgIdx >= 0 && outCkgIdx < splits);
outCkg[outCkgIdx].addNum(inCkg.at0(row));
}
}
for (int i = 0; i < outCkg.length; ++i) outCkg[i].close(i, fs);
Vec t = vec.close(fs);
t._domain = vecs[col]._domain;
vecs[col] = t;
}
fs.blockForPending();
Log.info("Load balancing done.");
return new Frame(fr.names(), vecs);
}
return fr;
}
// Print fixed-width row & fixed-width headers (more compressed print
// format). Returns the column formats.
public String[] toStringHdr(StringBuilder sb) {
String[] fs = new String[numCols()];
for (int c = 0; c < fs.length; c++) {
String n = (c < _names.length) ? _names[c] : ("C" + c);
if (numRows() == 0) {
sb.append(n).append(' ');
continue;
}
int w = 0;
if (_vecs[c].isEnum()) {
String ss[] = _vecs[c]._domain;
for (int i = 0; i < ss.length; i++) w = Math.max(w, ss[i].length());
w = Math.min(w, 10);
fs[c] = "%" + w + "." + w + "s";
} else {
Chunk C = _vecs[c].elem2BV(0); // 1st Chunk
String f = fs[c] = C.pformat(); // Printable width
for (int x = 0; x < f.length(); x++) // Get printable width from format
if (Character.isDigit(f.charAt(x))) w = w * 10 + (f.charAt(x) - '0');
else if (w > 0) break;
if (f.charAt(1) == ' ') w++; // Leading blank is not in print-width
}
int len = sb.length();
if (n.length() <= w) { // Short name, big digits
sb.append(n);
for (int i = n.length(); i < w; i++) sb.append(' ');
} else if (w == 1) { // First char only
sb.append(n.charAt(0));
} else if (w == 2) { // First 2 chars only
sb.append(n.charAt(0)).append(n.charAt(1));
} else { // First char dot lastchars; e.g. Compress "Interval" to "I.val"
sb.append(n.charAt(0)).append('.');
for (int i = n.length() - (w - 2); i < n.length(); i++) sb.append(n.charAt(i));
}
assert len + w == sb.length();
sb.append(' '); // Column seperator
}
sb.append('\n');
return fs;
}
@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 ys) {
_ys = new long[_nclass];
for (int i = 0; i < ys._len; i++) if (!ys.isNA0(i)) _ys[(int) ys.at80(i)]++;
}
/**
* 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;
}
public Rows rows(Chunk[] chks) {
int cnt = 0;
for (Chunk c : chks) if (c.isSparseZero()) ++cnt;
return rows(chks, cnt > (chks.length >> 1));
}
