/** Adds invalid value to the column. */
public void addInvalidCol(int colIdx) {
++_colIdx;
if (colIdx >= _ncolumns) return;
++_invalidValues[colIdx];
if (_phase == Pass.ONE) return;
switch (_colTypes[colIdx]) {
case BYTE:
case DBYTE:
_ab.put1(-1);
break;
case SHORT:
case DSHORT:
_ab.put2((short) -1);
break;
case INT:
_ab.put4(Integer.MIN_VALUE);
break;
case LONG:
_ab.put8(Long.MIN_VALUE);
break;
case FLOAT:
_ab.put4f(Float.NaN);
break;
case DOUBLE:
_ab.put8d(Double.NaN);
break;
case STRINGCOL:
// TODO, replace with empty space!
_ab.put1(-1);
break;
default:
assert false : "illegal case: " + _colTypes[colIdx];
}
}
// Insert just the predictions: a single byte/short if we are predicting a
// single class, or else the full distribution.
@Override
protected AutoBuffer compress(AutoBuffer ab) {
assert !Double.isNaN(_pred);
return ab.put4f((float) _pred);
}
@SuppressWarnings("fallthrough")
public void addNumCol(int colIdx, long number, int exp) {
++_colIdx;
if (colIdx >= _ncolumns) return;
switch (_phase) {
case ONE:
double d = number * pow10(exp);
if (d < _min[colIdx]) _min[colIdx] = d;
if (d > _max[colIdx]) _max[colIdx] = d;
_mean[colIdx] += d;
if (exp != 0) {
if (exp < _scale[colIdx]) _scale[colIdx] = exp;
if (_colTypes[colIdx] != DCOL) {
if (Math.abs(number) > MAX_FLOAT_MANTISSA || exp < -35 || exp > 35)
_colTypes[colIdx] = DCOL;
else _colTypes[colIdx] = FCOL;
}
} else if (_colTypes[colIdx] < ICOL) {
_colTypes[colIdx] = ICOL;
}
break;
case TWO:
switch (_colTypes[colIdx]) {
case BYTE:
_ab.put1((byte) (number * pow10i(exp - _scale[colIdx]) - _bases[colIdx]));
break;
case SHORT:
_ab.put2((short) (number * pow10i(exp - _scale[colIdx]) - _bases[colIdx]));
break;
case INT:
_ab.put4((int) (number * pow10i(exp - _scale[colIdx]) - _bases[colIdx]));
break;
case LONG:
_ab.put8(number * pow10i(exp - _scale[colIdx]));
break;
case FLOAT:
_ab.put4f((float) (number * pow10(exp)));
break;
case DOUBLE:
_ab.put8d(number * pow10(exp));
break;
case DBYTE:
_ab.put1((short) (number * pow10i(exp - _scale[colIdx]) - _bases[colIdx]));
break;
case DSHORT:
// scale is computed as negative in the first pass,
// therefore to compute the positive exponent after scale, we add scale and the original
// exponent
_ab.put2((short) (number * pow10i(exp - _scale[colIdx]) - _bases[colIdx]));
break;
case STRINGCOL:
break;
}
// update sigma
if (!Double.isNaN(_mean[colIdx])) {
d = number * pow10(exp) - _mean[colIdx];
_sigma[colIdx] += d * d;
}
break;
default:
assert (false);
}
}