@Test
public void test() {
Frame frame = null;
try {
Futures fs = new Futures();
Random random = new Random();
Vec[] vecs = new Vec[1];
AppendableVec vec = new AppendableVec(Vec.newKey(), Vec.T_NUM);
for (int i = 0; i < 2; i++) {
NewChunk chunk = new NewChunk(vec, i);
for (int r = 0; r < 1000; r++) chunk.addNum(random.nextInt(1000));
chunk.close(i, fs);
}
vecs[0] = vec.layout_and_close(fs);
fs.blockForPending();
frame = new Frame(Key.<Frame>make(), null, vecs);
// Make sure we test the multi-chunk case
vecs = frame.vecs();
assert vecs[0].nChunks() > 1;
long rows = frame.numRows();
Vec v = vecs[0];
double min = Double.POSITIVE_INFINITY, max = Double.NEGATIVE_INFINITY, mean = 0, sigma = 0;
for (int r = 0; r < rows; r++) {
double d = v.at(r);
if (d < min) min = d;
if (d > max) max = d;
mean += d;
}
mean /= rows;
for (int r = 0; r < rows; r++) {
double d = v.at(r);
sigma += (d - mean) * (d - mean);
}
sigma = Math.sqrt(sigma / (rows - 1));
double epsilon = 1e-9;
assertEquals(max, v.max(), epsilon);
assertEquals(min, v.min(), epsilon);
assertEquals(mean, v.mean(), epsilon);
assertEquals(sigma, v.sigma(), epsilon);
} finally {
if (frame != null) frame.delete();
}
}
/**
* 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;
}
// Do any final actions on a completed NewVector. Mostly: compress it, and
// do a DKV put on an appropriate Key. The original NewVector goes dead
// (does not live on inside the K/V store).
public Chunk new_close(Futures fs) {
Chunk chk = compress();
if (_vec instanceof AppendableVec) ((AppendableVec) _vec).closeChunk(this);
return chk;
}
// Do any final actions on a completed NewVector. Mostly: compress it, and
// do a DKV put on an appropriate Key. The original NewVector goes dead
// (does not live on inside the K/V store).
public Chunk new_close() {
Chunk chk = compress();
if (_vec instanceof AppendableVec) ((AppendableVec) _vec).closeChunk(_cidx, chk._len);
return chk;
}
public Frame deepSlice(Object orows, Object ocols) {
// ocols is either a long[] or a Frame-of-1-Vec
long[] cols;
if (ocols == null) {
cols = (long[]) ocols;
assert cols == null;
} else {
if (ocols instanceof long[]) {
cols = (long[]) ocols;
} else if (ocols instanceof Frame) {
Frame fr = (Frame) ocols;
if (fr.numCols() != 1) {
throw new IllegalArgumentException(
"Columns Frame must have only one column (actually has "
+ fr.numCols()
+ " columns)");
}
long n = fr.anyVec().length();
if (n > MAX_EQ2_COLS) {
throw new IllegalArgumentException(
"Too many requested columns (requested " + n + ", max " + MAX_EQ2_COLS + ")");
}
cols = new long[(int) n];
Vec v = fr._vecs[0];
for (long i = 0; i < v.length(); i++) {
cols[(int) i] = v.at8(i);
}
} else {
throw new IllegalArgumentException(
"Columns is specified by an unsupported data type ("
+ ocols.getClass().getName()
+ ")");
}
}
// Since cols is probably short convert to a positive list.
int c2[] = null;
if (cols == null) {
c2 = new int[numCols()];
for (int i = 0; i < c2.length; i++) c2[i] = i;
} else if (cols.length == 0) {
c2 = new int[0];
} else if (cols[0] > 0) {
c2 = new int[cols.length];
for (int i = 0; i < cols.length; i++)
c2[i] = (int) cols[i] - 1; // Convert 1-based cols to zero-based
} else {
c2 = new int[numCols() - cols.length];
int j = 0;
for (int i = 0; i < numCols(); i++) {
if (j >= cols.length || i < (-cols[j] - 1)) c2[i - j] = i;
else j++;
}
}
for (int i = 0; i < c2.length; i++)
if (c2[i] >= numCols())
throw new IllegalArgumentException(
"Trying to select column " + c2[i] + " but only " + numCols() + " present.");
if (c2.length == 0)
throw new IllegalArgumentException(
"No columns selected (did you try to select column 0 instead of column 1?)");
// Do Da Slice
// orows is either a long[] or a Vec
if (orows == null)
return new DeepSlice((long[]) orows, c2)
.doAll(c2.length, this)
.outputFrame(names(c2), domains(c2));
else if (orows instanceof long[]) {
final long CHK_ROWS = 1000000;
long[] rows = (long[]) orows;
if (rows.length == 0)
return new DeepSlice(rows, c2).doAll(c2.length, this).outputFrame(names(c2), domains(c2));
if (rows[0] < 0)
return new DeepSlice(rows, c2).doAll(c2.length, this).outputFrame(names(c2), domains(c2));
// Vec'ize the index array
AppendableVec av = new AppendableVec("rownames");
int r = 0;
int c = 0;
while (r < rows.length) {
NewChunk nc = new NewChunk(av, c);
long end = Math.min(r + CHK_ROWS, rows.length);
for (; r < end; r++) {
nc.addNum(rows[r]);
}
nc.close(c++, null);
}
Vec c0 = av.close(null); // c0 is the row index vec
Frame fr2 =
new Slice(c2, this)
.doAll(c2.length, new Frame(new String[] {"rownames"}, new Vec[] {c0}))
.outputFrame(names(c2), domains(c2));
UKV.remove(c0._key); // Remove hidden vector
return fr2;
}
Frame frows = (Frame) orows;
Vec vrows = frows.anyVec();
// It's a compatible Vec; use it as boolean selector.
// Build column names for the result.
Vec[] vecs = new Vec[c2.length + 1];
String[] names = new String[c2.length + 1];
for (int i = 0; i < c2.length; ++i) {
vecs[i] = _vecs[c2[i]];
names[i] = _names[c2[i]];
}
vecs[c2.length] = vrows;
names[c2.length] = "predicate";
return new DeepSelect()
.doAll(c2.length, new Frame(names, vecs))
.outputFrame(names(c2), domains(c2));
}
