Esempio n. 1
0
  /**
   * 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;
  }
Esempio n. 2
0
 /**
  * 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;
 }