MCPcopy Create free account
hub / github.com/catboost/catboost / ReadCDForSampler

Method ReadCDForSampler

catboost/libs/data/sampler.cpp:18–41  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

16
17
18void NCB::ReadCDForSampler(
19 const TPathWithScheme& cdPath,
20 bool onlyFeaturesData,
21 bool loadSampleIds,
22 TVector<TColumn>* columnsDescription,
23 TMaybe<size_t>* sampleIdColumnIdx
24) {
25 if (!cdPath.Inited()) {
26 return;
27 }
28 *columnsDescription = ReadCD(cdPath, TCdParserDefaults(EColumn::Num));
29 for (auto i : xrange(columnsDescription->size())) {
30 auto& column = (*columnsDescription)[i];
31 if (column.Type == EColumn::SampleId) {
32 CB_ENSURE(!(*sampleIdColumnIdx).Defined(), "Duplicate SampleId columns in CD file");
33 (*sampleIdColumnIdx) = i;
34 if (onlyFeaturesData && !loadSampleIds) {
35 column.Type = EColumn::Auxiliary;
36 }
37 } else if (onlyFeaturesData && !IsFactorColumn(column.Type)) {
38 column.Type = EColumn::Auxiliary;
39 }
40 }
41}
42
43
44static TDataProviderPtr ReadDatasetForSampler(

Callers

nothing calls this directly

Calls 7

ReadCDFunction · 0.85
TCdParserDefaultsClass · 0.85
xrangeFunction · 0.85
IsFactorColumnFunction · 0.85
InitedMethod · 0.45
sizeMethod · 0.45
DefinedMethod · 0.45

Tested by

no test coverage detected