public static Key makeByteVec(Key k, String... data) {
   byte[][] chunks = new byte[data.length][];
   long[] espc = new long[data.length + 1];
   for (int i = 0; i < chunks.length; ++i) {
     chunks[i] = data[i].getBytes();
     espc[i + 1] = espc[i] + data[i].length();
   }
   Futures fs = new Futures();
   Key key = Vec.newKey();
   ByteVec bv = new ByteVec(key, Vec.ESPC.rowLayout(key, espc));
   for (int i = 0; i < chunks.length; ++i) {
     Key chunkKey = bv.chunkKey(i);
     DKV.put(
         chunkKey,
         new Value(chunkKey, chunks[i].length, chunks[i], TypeMap.C1NCHUNK, Value.ICE),
         fs);
   }
   DKV.put(bv._key, bv, fs);
   Frame fr = new Frame(k, new String[] {"makeByteVec"}, new Vec[] {bv});
   DKV.put(k, fr, fs);
   fs.blockForPending();
   return k;
 }
Beispiel #2
0
  @Override
  Val apply(Env env, Env.StackHelp stk, AST asts[]) {

    // Execute all args.  Find a canonical frame; all Frames must look like this one.
    // Each argument turns into either a Frame (whose rows are entirely
    // inlined) or a scalar (which is replicated across as a single row).
    Frame fr = null; // Canonical Frame; all frames have the same column count, types and names
    int nchks = 0; // Total chunks
    Val vals[] = new Val[asts.length]; // Computed AST results
    for (int i = 1; i < asts.length; i++) {
      vals[i] = stk.track(asts[i].exec(env));
      if (vals[i].isFrame()) {
        fr = vals[i].getFrame();
        nchks += fr.anyVec().nChunks(); // Total chunks
      } else nchks++; // One chunk per scalar
    }
    // No Frame, just a pile-o-scalars?
    Vec zz = null; // The zero-length vec for the zero-frame frame
    if (fr == null) { // Zero-length, 1-column, default name
      fr = new Frame(new String[] {Frame.defaultColName(0)}, new Vec[] {zz = Vec.makeZero(0)});
      if (asts.length == 1) return new ValFrame(fr);
    }

    // Verify all Frames are the same columns, names, and types.  Domains can vary, and will be the
    // union
    final Frame frs[] = new Frame[asts.length]; // Input frame
    final byte[] types = fr.types(); // Column types
    final int ncols = fr.numCols();
    final long[] espc = new long[nchks + 1]; // Compute a new layout!
    int coffset = 0;

    for (int i = 1; i < asts.length; i++) {
      Val val = vals[i]; // Save values computed for pass 2
      Frame fr0 =
          val.isFrame()
              ? val.getFrame()
              // Scalar: auto-expand into a 1-row frame
              : stk.track(new Frame(fr._names, Vec.makeCons(val.getNum(), 1L, fr.numCols())));

      // Check that all frames are compatible
      if (fr.numCols() != fr0.numCols())
        throw new IllegalArgumentException(
            "rbind frames must have all the same columns, found "
                + fr.numCols()
                + " and "
                + fr0.numCols()
                + " columns.");
      if (!Arrays.deepEquals(fr._names, fr0._names))
        throw new IllegalArgumentException(
            "rbind frames must have all the same column names, found "
                + Arrays.toString(fr._names)
                + " and "
                + Arrays.toString(fr0._names));
      if (!Arrays.equals(types, fr0.types()))
        throw new IllegalArgumentException(
            "rbind frames must have all the same column types, found "
                + Arrays.toString(types)
                + " and "
                + Arrays.toString(fr0.types()));

      frs[i] = fr0; // Save frame

      // Roll up the ESPC row counts
      long roffset = espc[coffset];
      long[] espc2 = fr0.anyVec().espc();
      for (int j = 1; j < espc2.length; j++) // Roll up the row counts
      espc[coffset + j] = (roffset + espc2[j]);
      coffset += espc2.length - 1; // Chunk offset
    }
    if (zz != null) zz.remove();

    // build up the new domains for each vec
    HashMap<String, Integer>[] dmap = new HashMap[types.length];
    String[][] domains = new String[types.length][];
    int[][][] cmaps = new int[types.length][][];
    for (int k = 0; k < types.length; ++k) {
      dmap[k] = new HashMap<>();
      int c = 0;
      byte t = types[k];
      if (t == Vec.T_CAT) {
        int[][] maps = new int[frs.length][];
        for (int i = 1; i < frs.length; i++) {
          maps[i] = new int[frs[i].vec(k).domain().length];
          for (int j = 0; j < maps[i].length; j++) {
            String s = frs[i].vec(k).domain()[j];
            if (!dmap[k].containsKey(s)) dmap[k].put(s, maps[i][j] = c++);
            else maps[i][j] = dmap[k].get(s);
          }
        }
        cmaps[k] = maps;
      } else {
        cmaps[k] = new int[frs.length][];
      }
      domains[k] = c == 0 ? null : new String[c];
      for (Map.Entry<String, Integer> e : dmap[k].entrySet()) domains[k][e.getValue()] = e.getKey();
    }

    // Now make Keys for the new Vecs
    Key<Vec>[] keys = fr.anyVec().group().addVecs(fr.numCols());
    Vec[] vecs = new Vec[fr.numCols()];
    int rowLayout = Vec.ESPC.rowLayout(keys[0], espc);
    for (int i = 0; i < vecs.length; i++)
      vecs[i] = new Vec(keys[i], rowLayout, domains[i], types[i]);

    // Do the row-binds column-by-column.
    // Switch to F/J thread for continuations
    ParallelRbinds t;
    H2O.submitTask(t = new ParallelRbinds(frs, espc, vecs, cmaps)).join();
    return new ValFrame(new Frame(fr.names(), t._vecs));
  }