Logo ROOT  

Reference Guide
 
Loading...
Searching...
No Matches
List of all members | Public Member Functions | Private Attributes | List of all members
ROOT::Experimental::Internal::ML::RDatasetLoader Class Reference

Load the whole dataset into memory.

In this class the whole dataset is loaded into memory. The dataset is further shuffled and spit into training and validation sets with the user-defined validation split fraction.

Definition at line 37 of file RDatasetLoader.hxx.

Public Member Functions

 RDatasetLoader (const std::vector< ROOT::RDF::RNode > &rdfs, const float validationSplit, const std::vector< std::string > &cols, const std::vector< std::size_t > &vecSizes={}, const float vecPadding=0.0, bool shuffle=true, const std::size_t setSeed=0)
 
void ConcatenateDatasets ()
 Concatenate the datasets to a dataset.
 
std::size_t GetNumTrainingEntries ()
 
std::size_t GetNumValidationEntries ()
 
RFlat2DMatrix ReleaseTrainingDataset ()
 
std::vector< RFlat2DMatrix > ReleaseTrainingDatasets ()
 
RFlat2DMatrix ReleaseValidationDataset ()
 
std::vector< RFlat2DMatrix > ReleaseValidationDatasets ()
 
void SplitDataframe (ROOT::RDF::RNode &rdf, RFlat2DMatrix &TrainingDataset, RFlat2DMatrix &ValidationDataset)
 Split an individual dataframe into a training and validation dataset.
 
void SplitDatasets ()
 Split the dataframes in a training and validation dataset.
 

Private Attributes

std::vector< ROOT::RDF::RNode > f_rdfs
 
std::vector< std::string > fCols
 
std::size_t fNumCols
 
std::size_t fNumDatasetCols
 
std::size_t fNumTrainingEntries
 
std::size_t fNumValidationEntries
 
std::size_t fSetSeed
 
bool fShuffle
 
std::size_t fSumVecSizes
 
std::unique_ptr< RFlat2DMatrixOperators > fTensorOperators
 
RFlat2DMatrix fTrainingDataset
 
std::vector< RFlat2DMatrix > fTrainingDatasets
 
RFlat2DMatrix fValidationDataset
 
std::vector< RFlat2DMatrix > fValidationDatasets
 
float fValidationSplit
 
float fVecPadding
 
std::vector< std::size_t > fVecSizes
 

#include </github/home/ROOT-CI/src/tree/ml/src/RDatasetLoader.hxx>

Constructor & Destructor Documentation

◆ RDatasetLoader()

ROOT::Experimental::Internal::ML::RDatasetLoader::RDatasetLoader ( const std::vector< ROOT::RDF::RNode > & rdfs,
const float validationSplit,
const std::vector< std::string > & cols,
const std::vector< std::size_t > & vecSizes = {},
const float vecPadding = 0.0,
bool shuffle = true,
const std::size_t setSeed = 0 )

Definition at line 5 of file RDatasetLoader.cxx.

Member Function Documentation

◆ ConcatenateDatasets()

void ROOT::Experimental::Internal::ML::RDatasetLoader::ConcatenateDatasets ( )

Concatenate the datasets to a dataset.

Definition at line 112 of file RDatasetLoader.cxx.

◆ GetNumTrainingEntries()

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::GetNumTrainingEntries ( )
inline

Definition at line 80 of file RDatasetLoader.hxx.

◆ GetNumValidationEntries()

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::GetNumValidationEntries ( )
inline

Definition at line 81 of file RDatasetLoader.hxx.

◆ ReleaseTrainingDataset()

RFlat2DMatrix ROOT::Experimental::Internal::ML::RDatasetLoader::ReleaseTrainingDataset ( )
inline

Definition at line 77 of file RDatasetLoader.hxx.

◆ ReleaseTrainingDatasets()

std::vector< RFlat2DMatrix > ROOT::Experimental::Internal::ML::RDatasetLoader::ReleaseTrainingDatasets ( )
inline

Definition at line 74 of file RDatasetLoader.hxx.

◆ ReleaseValidationDataset()

RFlat2DMatrix ROOT::Experimental::Internal::ML::RDatasetLoader::ReleaseValidationDataset ( )
inline

Definition at line 78 of file RDatasetLoader.hxx.

◆ ReleaseValidationDatasets()

std::vector< RFlat2DMatrix > ROOT::Experimental::Internal::ML::RDatasetLoader::ReleaseValidationDatasets ( )
inline

Definition at line 75 of file RDatasetLoader.hxx.

◆ SplitDataframe()

void ROOT::Experimental::Internal::ML::RDatasetLoader::SplitDataframe ( ROOT::RDF::RNode & rdf,
RFlat2DMatrix & TrainingDataset,
RFlat2DMatrix & ValidationDataset )

Split an individual dataframe into a training and validation dataset.

Parameters
[in]rdfDataframe that will be split into training and validation
[in]TrainingDatasetTensor for the training dataset
[in]ValidationDatasetTensor for the validation dataset

Definition at line 28 of file RDatasetLoader.cxx.

◆ SplitDatasets()

void ROOT::Experimental::Internal::ML::RDatasetLoader::SplitDatasets ( )

Split the dataframes in a training and validation dataset.

Definition at line 91 of file RDatasetLoader.cxx.

Member Data Documentation

◆ f_rdfs

std::vector<ROOT::RDF::RNode> ROOT::Experimental::Internal::ML::RDatasetLoader::f_rdfs
private

Definition at line 56 of file RDatasetLoader.hxx.

◆ fCols

std::vector<std::string> ROOT::Experimental::Internal::ML::RDatasetLoader::fCols
private

Definition at line 57 of file RDatasetLoader.hxx.

◆ fNumCols

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fNumCols
private

Definition at line 58 of file RDatasetLoader.hxx.

◆ fNumDatasetCols

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fNumDatasetCols
private

Definition at line 44 of file RDatasetLoader.hxx.

◆ fNumTrainingEntries

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fNumTrainingEntries
private

Definition at line 52 of file RDatasetLoader.hxx.

◆ fNumValidationEntries

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fNumValidationEntries
private

Definition at line 53 of file RDatasetLoader.hxx.

◆ fSetSeed

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fSetSeed
private

Definition at line 59 of file RDatasetLoader.hxx.

◆ fShuffle

bool ROOT::Experimental::Internal::ML::RDatasetLoader::fShuffle
private

Definition at line 61 of file RDatasetLoader.hxx.

◆ fSumVecSizes

std::size_t ROOT::Experimental::Internal::ML::RDatasetLoader::fSumVecSizes
private

Definition at line 42 of file RDatasetLoader.hxx.

◆ fTensorOperators

std::unique_ptr<RFlat2DMatrixOperators> ROOT::Experimental::Internal::ML::RDatasetLoader::fTensorOperators
private

Definition at line 54 of file RDatasetLoader.hxx.

◆ fTrainingDataset

RFlat2DMatrix ROOT::Experimental::Internal::ML::RDatasetLoader::fTrainingDataset
private

Definition at line 49 of file RDatasetLoader.hxx.

◆ fTrainingDatasets

std::vector<RFlat2DMatrix> ROOT::Experimental::Internal::ML::RDatasetLoader::fTrainingDatasets
private

Definition at line 46 of file RDatasetLoader.hxx.

◆ fValidationDataset

RFlat2DMatrix ROOT::Experimental::Internal::ML::RDatasetLoader::fValidationDataset
private

Definition at line 50 of file RDatasetLoader.hxx.

◆ fValidationDatasets

std::vector<RFlat2DMatrix> ROOT::Experimental::Internal::ML::RDatasetLoader::fValidationDatasets
private

Definition at line 47 of file RDatasetLoader.hxx.

◆ fValidationSplit

float ROOT::Experimental::Internal::ML::RDatasetLoader::fValidationSplit
private

Definition at line 39 of file RDatasetLoader.hxx.

◆ fVecPadding

float ROOT::Experimental::Internal::ML::RDatasetLoader::fVecPadding
private

Definition at line 43 of file RDatasetLoader.hxx.

◆ fVecSizes

std::vector<std::size_t> ROOT::Experimental::Internal::ML::RDatasetLoader::fVecSizes
private

Definition at line 41 of file RDatasetLoader.hxx.

  • tree/ml/src/RDatasetLoader.hxx
  • tree/ml/src/RDatasetLoader.cxx