/// <summary>
/// slice is assumed to be a slice of indexes into data on column dim.
/// Reorder the slice inline so that all indices pointing to dim-values
/// that are >= splitVal are at the front, and all others are at the back.
/// Return two new slices corresponding to those regions (the >= slice is
/// first, the < slice is second)
/// </summary>
public static Tuple <Slice <int>, Slice <int> > ReorderSlice(Slice <int> slice, Indexer <double> featureCol, double splitVal)
{
int swap;
int startIndex = 0;
int endIndex = slice.Length - 1;
while (true)
{
while (featureCol[slice[startIndex]] >= splitVal)
{
startIndex++;
}
while (featureCol[slice[endIndex]] < splitVal)
{
endIndex--;
}
if (startIndex < endIndex)
{
swap = slice[startIndex];
slice[startIndex] = slice[endIndex];
slice[endIndex] = swap;
}
else
{
return(new Tuple <Slice <int>, Slice <int> >(
slice.MakeSlice(0, startIndex),
slice.MakeSlice(startIndex, slice.Length - startIndex)
));
}
}
}
public RecordSet(List <CsvRecord> data, double nanValue = -999.0)
{
NRows = data.Count;
NFeatures = CsvRecord.NUM_FEATURES;
Index = new int[NRows];
_EventIds = new int[NRows];
EventIds = new Indexer <int>(this, _EventIds);
_FeatureCols = new double[NFeatures][];
FeatureCols = new Indexer <double> [NFeatures];
for (int featureIndex = 0; featureIndex < NFeatures; featureIndex++)
{
_FeatureCols[featureIndex] = new double[NRows];
FeatureCols[featureIndex] = new Indexer <double>(this, _FeatureCols[featureIndex]);
}
#region fill arrays
for (int rownum = 0; rownum < NRows; rownum++)
{
var row = data[rownum];
_EventIds[rownum] = row.EventId;
Index[rownum] = rownum;
_FeatureCols[0][rownum] = row.DER_mass_MMC;
_FeatureCols[1][rownum] = row.DER_mass_transverse_met_lep;
_FeatureCols[2][rownum] = row.DER_mass_vis;
_FeatureCols[3][rownum] = row.DER_pt_h;
_FeatureCols[4][rownum] = row.DER_deltaeta_jet_jet;
_FeatureCols[5][rownum] = row.DER_mass_jet_jet;
_FeatureCols[6][rownum] = row.DER_prodeta_jet_jet;
_FeatureCols[7][rownum] = row.DER_deltar_tau_lep;
_FeatureCols[8][rownum] = row.DER_pt_tot;
_FeatureCols[9][rownum] = row.DER_sum_pt;
_FeatureCols[10][rownum] = row.DER_pt_ratio_lep_tau;
_FeatureCols[11][rownum] = row.DER_met_phi_centrality;
_FeatureCols[12][rownum] = row.DER_lep_eta_centrality;
_FeatureCols[13][rownum] = row.PRI_tau_pt;
_FeatureCols[14][rownum] = row.PRI_tau_eta;
_FeatureCols[15][rownum] = row.PRI_tau_phi;
_FeatureCols[16][rownum] = row.PRI_lep_pt;
_FeatureCols[17][rownum] = row.PRI_lep_eta;
_FeatureCols[18][rownum] = row.PRI_lep_phi;
_FeatureCols[19][rownum] = row.PRI_met;
_FeatureCols[20][rownum] = row.PRI_met_phi;
_FeatureCols[21][rownum] = row.PRI_met_sumet;
_FeatureCols[22][rownum] = row.PRI_jet_num;
_FeatureCols[23][rownum] = row.PRI_jet_leading_pt;
_FeatureCols[24][rownum] = row.PRI_jet_leading_eta;
_FeatureCols[25][rownum] = row.PRI_jet_leading_phi;
_FeatureCols[26][rownum] = row.PRI_jet_subleading_pt;
_FeatureCols[27][rownum] = row.PRI_jet_subleading_eta;
_FeatureCols[28][rownum] = row.PRI_jet_subleading_phi;
_FeatureCols[29][rownum] = row.PRI_jet_all_pt;
}
#endregion
for (int featureNum = 0; featureNum < NFeatures; featureNum++)
{
Yarr.InlineReplace(
_FeatureCols[featureNum],
nanValue,
double.NaN
);
}
}