/** * 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; }